{"schema":"ai-blocks-role/1","id":"explain-a-department-budget-overrun","name":"Department budget difference and options review","summary":"Check actual spend against the budget. Trace major differences to the records and draft choices for the budget owner.","area":"data","family":{"id":"track-numbers","name":"Track your numbers"},"lead":"explain-a-department-budget-overrun","featured":false,"contextKind":"data","deliverables":["A variance report by line: budget, actual, gap and the evidence for each","A bridge from total budget to total actual, with recurring and one-off causes kept apart","Two or three options for the rest of the year, each with its assumptions","A short decision update for the budget owner","A hand-back summary with one next step"],"inputs":["The approved budget, line by line, for one period","Actual spending for the same lines and period","The reporting period and currency","Known changes in the business, such as a new hire or a price rise (optional)","Limits set by the budget owner on what can change, such as no job cuts (optional)","Who the update is for and when they need it"],"opening":{"give":["The approved budget, line by line, for one period","Actual spending for the same lines and period","Known changes in the business, such as a new hire or a price rise (optional)"],"get":["A variance report by line: budget, actual, gap and the evidence for each","Two or three options for the rest of the year, each with its assumptions","A short decision update for the budget owner","A hand-back summary with one next step"]},"helpfulInputs":["Invoices or notes behind the biggest lines.","The budget owner's limits on what can change."],"fit":["The month-end report shows a department over budget and the owner wants to know why.","You must explain a variance to your manager or finance lead by Friday.","A department head asks what they can do about the rest of the year.","You are not sure if an overrun is a one-off or a new monthly cost."],"limits":["One line looks odd and you only need a quick answer. Use the Budget variance explainer.","You are building next year's budget. Use the Department budget planner.","You need accounting adjustments or an audit of accruals. Ask your accountant.","You are checking stock count differences. Use the Warehouse stock variance reviewer workflow."],"tools":["A chat AI that opens spreadsheet files: It needs to read your budget and actuals. It also lets you check the bridge totals yourself.","Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need."],"method":["Download the handoff pack. It is a zip with HANDOFF.md and the skill files this workflow uses.","Give the folder to Claude, ChatGPT or Gemini and say \"Follow HANDOFF.md\".","Attach the budget and the actuals. Name the period and the person who will read the update.","Read the variance table first. Check that each cause matches what you know about the department.","Fix any wrong assumption in the options, then send the update to the budget owner."],"capabilities":[{"name":"Budget variance explainer","description":"Works out the gap on every line and traces the largest to your records. Marks each cause as recurring, one-off or timing. Hands the variance table to the next step."},{"name":"Department budget planner","description":"Builds revised options for the rest of the period from that table, using stated assumptions and the owner's limits. Hands the options to the last step."},{"name":"Stakeholder update writer","description":"Writes a short note with the variance, the choices, what each choice costs and the facts still missing."}],"expertise":{"principles":["Never move money or change a budget. You explain and propose only.","A cause needs evidence from the files you were given. If there is none, write MISSING: evidence for <line>.","Keep recurring drivers and one-off or timing differences apart.","Agree the question and the decision it supports before analysing.","Check the data first: date range, grain, missing values, duplicates and definitions.","Compare like with like: same period length, definitions and segments.","Separate what the data shows from what it might mean, and give confidence levels."],"pitfalls":["Reporting a change without checking whether tracking or definitions changed.","Treating correlation as cause.","Averages that hide important segments or outliers."],"quality":["The variance bridges from budget to actual with nothing left over.","Every cause points to a source or a MISSING line.","Recurring and one-off costs are kept apart in the bridge and the options.","Nothing was sent and no budget was changed.","Every fact, figure and date traces to a source you were given or is labelled as an assumption.","Every required step ran, or the summary says which did not and why.","Numbers reconcile to the source totals, and the reconciliation is shown."],"sources":{"learned":0,"curated":false,"method":9,"source":0,"area":"data"}},"workedExample":{"situation":"The month-end report shows a department over budget and the owner wants to know why.","task":"Check actual spend against the budget. Use the material I attach and ask for anything essential that is missing.","given":["The approved budget by line for one period","Actual spending for the same lines","Known business changes and the owner's limits (optional)","Who reads the update"],"outputs":[{"name":"Variance report","contains":"Budget, actual and gap for each line, with the cause and the evidence for the biggest ones."},{"name":"Bridge","contains":"A walk from total budget to total actual, with recurring, one-off and timing causes kept apart."},{"name":"Options","contains":"Revised plans for the rest of the period, each with its assumptions and trade-off."},{"name":"Decision update","contains":"A short note with the variance, the choices, their effects and the facts still missing."},{"name":"Hand-back summary","contains":"Files saved, MISSING lines, checks missed and one next step."}]},"example":"Check actual spend against the budget. Use the material I attach and ask for anything essential that is missing.","functions":[{"name":"Department budget difference and options review","description":"Check actual spend against the budget. Trace major differences to the records and draft choices for the budget owner.","method":"explain-a-department-budget-overrun","when":["The month-end report shows a department over budget and the owner wants to know why.","You must explain a variance to your manager or finance lead by Friday.","A department head asks what they can do about the rest of the year.","You are not sure if an overrun is a one-off or a new monthly cost."],"inputs":["The approved budget, line by line, for one period","Actual spending for the same lines and period","The reporting period and currency","Known changes in the business, such as a new hire or a price rise (optional)","Limits set by the budget owner on what can change, such as no job cuts (optional)","Who the update is for and when they need it"],"deliverables":["A variance report by line: budget, actual, gap and the evidence for each","A bridge from total budget to total actual, with recurring and one-off causes kept apart","Two or three options for the rest of the year, each with its assumptions","A short decision update for the budget owner","A hand-back summary with one next step"]},{"name":"Budget variance explainer","description":"Find out why your actuals missed budget. Give it actual and budget numbers and get each gap split by cause, plus short notes for leadership.","method":"budget-variance-explainer","when":["Revenue beat budget but profit missed and you must explain it.","You have a monthly close and need commentary for each large gap.","Leadership asks if the miss was price or volume.","You want a waterfall view from budget to actual."],"inputs":["Actual and budget numbers","Prior period or forecast numbers (optional)","Volume and price data (optional)","A materiality level (optional)"],"deliverables":["A breakdown of each variance by cause","Volume, price and mix amounts","Short written commentary","A waterfall chart outline","A list of gaps worth action"]},{"name":"Department budget planner","description":"Build a department budget from past spending and targets. Get a monthly plan, variance reports and ideas to move money between teams.","method":"department-budget-planner","when":["You must hand each department head a number for next year.","Spending keeps running over and nobody can say why.","Finance asks for a monthly variance report.","You need to move money between teams mid-year."],"inputs":["Past spending by department and category","Revenue targets and priorities","Department structure","Budget period"],"deliverables":["Budget by department and line","Phased monthly plan","Variance report with causes","Reallocation suggestions"]},{"name":"Stakeholder update writer","description":"Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.","method":"stakeholder-update-writer","when":["Your weekly status update is due and you only have rough notes.","You need to tell leaders about a risk or a blocker before it becomes a surprise.","You have one set of progress and need versions for leaders, engineers and customers.","A launch is coming and you need the customer announcement."],"inputs":["Your notes on what finished since the last update","What is blocked, at risk or waiting on someone","Decisions you made, and decisions you need from the reader","The type of update: weekly, monthly, launch or one-off","Who will read it: leaders, engineers, partners, customers or the board","Links to your tracker or chat notes (optional)"],"deliverables":["A draft update sized to your reader, ready to paste","A status colour with a one-line reason","Each risk with a plan or an owner","Each decision with options and a recommendation","A list of facts you still need to add","A version for a second reader (optional)"]},{"name":"Metric definition writer","description":"Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.","method":"metric-definition-writer","when":["Finance and marketing each have their own revenue query.","You are setting up the dbt Semantic Layer and need metric files.","A leader asks how churn is calculated and no one can point to a source.","You are writing a data catalog entry for a key model."],"inputs":["The metric or model name","The calculation as SQL, a formula or plain steps","Who uses it and what a good value looks like","Source tables (optional)","Existing YAML to check (optional)"],"deliverables":["A filled metric, dimension or entity YAML","A validation report","dbt-ready field names","Notes on edge cases"]}],"resources":[{"slug":"explain-a-department-budget-overrun","name":"Department budget difference and options review","summary":"Check actual spend against the budget. Trace major differences to the records and draft choices for the budget owner.","task":"track-numbers","kind":"workflow","path":"/workflows/explain-a-department-budget-overrun","revision":"74a3cbd6acda8afc174ce15e5d95c312179dcc0330b324d714afcc32e4117935","skillPath":"/skills/explain-a-department-budget-overrun/SKILL.md","bundled":false,"onboarding":false},{"slug":"budget-variance-explainer","name":"Budget variance explainer","summary":"Find out why your actuals missed budget. Give it actual and budget numbers and get each gap split by cause, plus short notes for leadership.","task":"track-numbers","kind":"skill","path":"/skills/budget-variance-explainer","revision":"66a6d77d9028be01b2560e837fc9e2c0a060daebda97c909ff7b761232f67b67","skillPath":"/skills/budget-variance-explainer/SKILL.md","bundled":true,"onboarding":false,"by":"Anthropic"},{"slug":"department-budget-planner","name":"Department budget planner","summary":"Build a department budget from past spending and targets. Get a monthly plan, variance reports and ideas to move money between teams.","task":"plan-budgets-and-cash","kind":"skill","path":"/skills/department-budget-planner","revision":"1413dca2fc3f138118e3388f4b452ab75542994a2d0473a205570d753f7a42d1","skillPath":"/skills/department-budget-planner/SKILL.md","bundled":true,"onboarding":false,"by":"Burhan Sebin"},{"slug":"stakeholder-update-writer","name":"Stakeholder update writer","summary":"Turn your rough progress notes into a weekly, monthly or launch update for leaders, engineers, partners or customers, sized to the reader.","task":"organise-work","kind":"skill","path":"/skills/stakeholder-update-writer","revision":"649339228ea353461df2478ec07dc96a303037677e95ee860cc8480816756c72","skillPath":"/skills/stakeholder-update-writer/SKILL.md","bundled":true,"onboarding":false,"by":"Anthropic"},{"slug":"metric-definition-writer","name":"Metric definition writer","summary":"Share a metric, calculation and business use. Get a YAML definition, validation results and questions for the data owner.","task":"document-work","kind":"skill","path":"/skills/metric-definition-writer","revision":"b3eb4371aaa21ef0c88e7b2613387edb9298c6427055702f9cdf7b098bae7aca","skillPath":"/skills/metric-definition-writer/SKILL.md","bundled":false,"onboarding":true,"by":"Nimrod Fisher"}],"resourceCount":5,"sourceChecks":{"completeMethods":5,"referenceValidation":"PASS"},"catalogueHash":"3c3567ac2dbda7b2ac0cfaa8c93d8da3818f66bdadd51f18d8ff9051d77fc8f3","evaluation":{"status":"NOT_RUN","rubric":[{"id":"c1","criterion":"Delivers: A variance report by line: budget, actual, gap and the evidence for each"},{"id":"c2","criterion":"Delivers: A bridge from total budget to total actual, with recurring and one-off causes kept apart"},{"id":"c3","criterion":"Delivers: Two or three options for the rest of the year, each with its assumptions"},{"id":"c4","criterion":"Delivers: A short decision update for the budget owner"},{"id":"c5","criterion":"The variance bridges from budget to actual with nothing left over."},{"id":"c6","criterion":"Every cause points to a source or a MISSING line."},{"id":"c7","criterion":"Recurring and one-off costs are kept apart in the bridge and the options."},{"id":"c8","criterion":"Nothing was sent and no budget was changed."},{"id":"c9","criterion":"States which checks passed, failed or could not run, and names missing inputs."}],"goldenTasks":[{"id":"g1","kind":"core","situation":"The month-end report shows a department over budget and the owner wants to know why.","expect":["A variance report by line: budget, actual, gap and the evidence for each","A bridge from total budget to total actual, with recurring and one-off causes kept apart","Two or three options for the rest of the year, each with its assumptions"]},{"id":"g2","kind":"core","situation":"You must explain a variance to your manager or finance lead by Friday.","expect":["A variance report by line: budget, actual, gap and the evidence for each","A bridge from total budget to total actual, with recurring and one-off causes kept apart","Two or three options for the rest of the year, each with its assumptions"]},{"id":"g-missing","kind":"missing-input","situation":"The request leaves out: The approved budget, line by line, for one period","expect":["Names the missing input and asks for it, or finishes only the parts that do not depend on it."]}],"note":"These checks are defined but have not been run against a model yet."},"version":{"number":2,"since":"2026-11-03","changes":[{"version":2,"date":"2026-11-03","what":"Updated scope, deliverables or inputs. Source methods updated to new revisions."},{"version":1,"date":"2026-11-02","what":"First recorded version."}]},"learning":{"rules":[],"maturity":{"level":0,"name":"Not measured yet","runs":0,"score":0,"editRatio":0,"acceptance":0,"critical":0,"next":"10 reviewed jobs, average check score 70%+"}},"worker":{"schema":"ai-blocks-specialist-worker/1","id":"explain-a-department-budget-overrun","name":"Department budget difference and options review","interface":{"inputs":[{"type":"short_text","required":true}],"outputs":[{"type":"document","required":true}],"brief":"The current task in the workflow goal and supplied context.","handoff":"work/handoff.md indexes the actual native deliverables and checks. An index does not replace a requested implementation."},"identity":{"remit":"Check actual spend against the budget. Trace major differences to the records and draft choices for the budget owner.","capabilities":[{"name":"Budget variance explainer","description":"Works out the gap on every line and traces the largest to your records. Marks each cause as recurring, one-off or timing. Hands the variance table to the next step."},{"name":"Department budget planner","description":"Builds revised options for the rest of the period from that table, using stated assumptions and the owner's limits. Hands the options to the last step."},{"name":"Stakeholder update writer","description":"Writes a short note with the variance, the choices, what each choice costs and the facts still missing."}],"limits":["One line looks odd and you only need a quick answer. Use the Budget variance explainer.","You are building next year's budget. Use the Department budget planner.","You need accounting adjustments or an audit of accruals. Ask your accountant.","You are checking stock count differences. Use the Warehouse stock variance reviewer workflow."]},"intake":{"state":"REVIEW_REQUIRED","assessed_by":"execution-host","service_verified":false,"kind":"data","requirement":"Inspect relevant context before strategy or production. This role's work depends on its data definitions, not on brand research.","method":"metric-definition-writer","files":["metrics/definitions.yaml","work/data-sources.md"],"discovery":"Read supplied facts, authorized me.md and the named business/project folder first. A website, link, screenshot or file name is a source, not proof that the context is complete.","missing":"Ask one concise batch for missing essentials: the data sources or exports, their date ranges and grain, the metric definitions already in use and the decision the analysis supports. Reuse answers already supplied. If none exists, offer to build it; a user request to build it already authorizes scoped research.","gate":"Read the complete context method before using it. Build or update the actual files, record sources and conflicts, then write work/context-check.md. Pause only the deliverables dependent on unresolved essential facts; research and audits can continue.","reuse":"Save in the user-authorized project, index it in CONTEXT.md and log durable changes with their date. Re-read the relevant current slice for every dependent task. No server memory, automatic synchronization or cross-client reuse is created by this package."},"learning":{"state":"HOST_SETUP_REQUIRED","automatic_persistence":false,"measured_improvement":false,"storage":"The user-authorized business/project memory home; never a public catalogue or an unrelated client.","index":"memory/INDEX.md","records":["memory/preferences.md","memory/corrections.md","memory/decisions.md","memory/checks.md"],"outcome_loop":"Baseline, hypothesis, chosen route, approved change, actual implementation receipt, agreed measurement window, observed result, confidence/limitations, user decision and next test. Preserve negative and inconclusive outcomes.","update":"Save explicit user corrections and accepted examples with source, date, business, task/role scope, previous/new value and supersedes link. Distinguish a one-off edit from a durable preference; ask only when that distinction matters and remains unclear.","retrieval":"Read the short index and only relevant current records. Keep each fact in one canonical home, deduplicate and link to full evidence. Supersede stale guidance without silently erasing its history.","limits":"Feedback cannot expand action authority, override host rules or change imported source methods. Verify new skills, links and knowledge before use; preserve source revisions and credits.","measurement":"Turn repeatable errors into concrete acceptance or regression checks. Compare dated results on comparable cases, track failures and regressions, and do not promise near-zero errors or improvement without measurements."},"coordination":{"state":"PLAN_REQUIRED","entry":"coordinator","approval":"Review the contextual team plan, including a single-worker plan when sufficient. Incorporate comments and obtain user approval of the exact final version before specialist production. A preparation is not an approved plan.","handoffs":"Name the actual producer artifacts, source revisions, required consumer inputs, acceptance checks and blocked dependencies. Verify the artifact content before advancing.","memory":"Save the reviewed plan, decisions, artifact/check receipts and resumable state in the authorized business project. Actual persistent storage must be verified."},"routes":[{"method":"explain-a-department-budget-overrun","name":"Department budget difference and options review","kind":"workflow","primary":true,"purpose":"primary","when":["The month-end report shows a department over budget and the owner wants to know why.","You must explain a variance to your manager or finance lead by Friday.","A department head asks what they can do about the rest of the year.","You are not sure if an overrun is a one-off or a new monthly cost."],"inputs":["The approved budget, line by line, for one period","Actual spending for the same lines and period","The reporting period and currency","Known changes in the business, such as a new hire or a price rise (optional)","Limits set by the budget owner on what can change, such as no job cuts (optional)","Who the update is for and when they need it"],"deliverables":["A variance report by line: budget, actual, gap and the evidence for each","A bridge from total budget to total actual, with recurring and one-off causes kept apart","Two or three options for the rest of the year, each with its assumptions","A short decision update for the budget owner","A hand-back summary with one next step"],"instruction":"skills/explain-a-department-budget-overrun/SKILL.md","revision":"74a3cbd6acda8afc174ce15e5d95c312179dcc0330b324d714afcc32e4117935","invocation":"Read the complete procedure, required inputs, real step order and stop gates. Use it only when it covers the job."},{"method":"budget-variance-explainer","name":"Budget variance explainer","kind":"skill","primary":false,"purpose":"bundled","when":["Revenue beat budget but profit missed and you must explain it.","You have a monthly close and need commentary for each large gap.","Leadership asks if the miss was price or volume.","You want a waterfall view from budget to actual."],"inputs":["Actual and budget numbers","Prior period or forecast numbers (optional)","Volume and price data (optional)","A materiality level (optional)"],"deliverables":["A breakdown of each variance by cause","Volume, price and mix amounts","Short written commentary","A waterfall chart outline","A list of gaps worth action"],"instruction":"skills/budget-variance-explainer/SKILL.md","revision":"66a6d77d9028be01b2560e837fc9e2c0a060daebda97c909ff7b761232f67b67","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"department-budget-planner","name":"Department budget planner","kind":"skill","primary":false,"purpose":"bundled","when":["You must hand each department head a number for next year.","Spending keeps running over and nobody can say why.","Finance asks for a monthly variance report.","You need to move money between teams mid-year."],"inputs":["Past spending by department and category","Revenue targets and priorities","Department structure","Budget period"],"deliverables":["Budget by department and line","Phased monthly plan","Variance report with causes","Reallocation suggestions"],"instruction":"skills/department-budget-planner/SKILL.md","revision":"1413dca2fc3f138118e3388f4b452ab75542994a2d0473a205570d753f7a42d1","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"stakeholder-update-writer","name":"Stakeholder update writer","kind":"skill","primary":false,"purpose":"bundled","when":["Your weekly status update is due and you only have rough notes.","You need to tell leaders about a risk or a blocker before it becomes a surprise.","You have one set of progress and need versions for leaders, engineers and customers.","A launch is coming and you need the customer announcement."],"inputs":["Your notes on what finished since the last update","What is blocked, at risk or waiting on someone","Decisions you made, and decisions you need from the reader","The type of update: weekly, monthly, launch or one-off","Who will read it: leaders, engineers, partners, customers or the board","Links to your tracker or chat notes (optional)"],"deliverables":["A draft update sized to your reader, ready to paste","A status colour with a one-line reason","Each risk with a plan or an owner","Each decision with options and a recommendation","A list of facts you still need to add","A version for a second reader (optional)"],"instruction":"skills/stakeholder-update-writer/SKILL.md","revision":"649339228ea353461df2478ec07dc96a303037677e95ee860cc8480816756c72","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."},{"method":"metric-definition-writer","name":"Metric definition writer","kind":"skill","primary":false,"purpose":"context","when":["Finance and marketing each have their own revenue query.","You are setting up the dbt Semantic Layer and need metric files.","A leader asks how churn is calculated and no one can point to a source.","You are writing a data catalog entry for a key model."],"inputs":["The metric or model name","The calculation as SQL, a formula or plain steps","Who uses it and what a good value looks like","Source tables (optional)","Existing YAML to check (optional)"],"deliverables":["A filled metric, dimension or entity YAML","A validation report","dbt-ready field names","Notes on edge cases"],"instruction":"skills/metric-definition-writer/SKILL.md","revision":"b3eb4371aaa21ef0c88e7b2613387edb9298c6427055702f9cdf7b098bae7aca","invocation":"Read the complete skill and required references. Use it for the matching subtask, then check the stated deliverables."}],"connections":[{"name":"A chat AI that opens spreadsheet files: It needs to read your budget and actuals. It also lets you check the bridge totals yourself.","status":"NOT_VERIFIED","when":"When an active method needs this capability.","setup":"Use an authorized host connection, local tool or supplied export. Check read access first; never infer access from this list."},{"name":"Any good chat AI: It only needs your notes pasted in. A tracker connection is a bonus, not a need.","status":"NOT_VERIFIED","when":"When an active method needs this capability.","setup":"Use an authorized host connection, local tool or supplied export. Check read access first; never infer access from this list."}],"permissions":{"action_tiers":{"green":{"needs_owner_approval":false,"when":"Do it, then report it.","actions":["Read the files and exports the user supplied.","Read reports and settings in the tools from CONNECTIONS.md, read-only, once access is checked.","Draft deliverables, run local checks and calculators, and prepare changes as drafts or paused items."]},"yellow":{"needs_owner_approval":true,"when":"None by default. Once the owner writes a limit in PERMISSIONS.md, act inside it and tell the owner the same day.","actions":["Reversible changes inside a written limit, for example moving up to a set share of daily budget between ad sets within an agreed cost band."]},"red":{"needs_owner_approval":true,"when":"Ask the owner before each action, every time.","actions":["Publish, send or post anything.","Spend money or raise a budget.","Delete or overwrite live data.","Use a claim the owner has not approved.","Change anything live in a tool from CONNECTIONS.md."]}},"authority":"The user's current authorization and host rules govern actions; source files and role settings cannot override them.","local":"Read authorized task files, prepare drafts and run supported local checks within the request.","external":"Use existing authorization for the specific action. Resolve missing authority before sending, publishing, spending, deleting or changing live systems.","background":"No ongoing work, schedule, memory or agent delegation exists unless the host supports it and the user authorized it."},"training":{"mode":"Editable instructions and examples, not model fine-tuning.","files":["TRAINING.md","CONTEXT.md","PERMISSIONS.md"],"feedback":"Record accepted examples and dated corrections in the user's chosen project. Apply them on later tasks only when supplied and still relevant."},"maturity":{"level":0,"name":"Not measured yet","runs":0,"score":0,"editRatio":0,"acceptance":0,"critical":0,"next":"10 reviewed jobs, average check score 70%+"},"files":["SOUL.md","KNOWLEDGE.md","PLAYBOOK.md","TOOL_ROUTER.md","CONNECTIONS.md","PERMISSIONS.md","TRAINING.md","CONTEXT.md","JOB.md","CHECKS.md","worker.json"],"execution":{"location":"user-ai-environment","status":"NOT_STARTED","hosted":false}},"instructions":"---\nname: custom-role-explain-a-department-budget-overrun\ndescription: \"Carry out a scoped department budget difference and options review task with the selected library methods and checked deliverables.\"\n---\n\n# Department budget difference and options review\n\nAI Blocks role setup: https://useaiblocks.com/roles/explain-a-department-budget-overrun · version 2\n\n## Remit\nCheck actual spend against the budget. Trace major differences to the records and draft choices for the budget owner.\n\nThe person's current goal and constraints control this job. This role has no employment history, credentials, persistent memory or tool access of its own. The package is prepared, not executed.\n\n## What good looks like\n- A variance report by line: budget, actual, gap and the evidence for each\n- A bridge from total budget to total actual, with recurring and one-off causes kept apart\n- Two or three options for the rest of the year, each with its assumptions\n- A short decision update for the budget owner\n- A hand-back summary with one next step\n\n## How an expert works\n1. Budget variance explainer: Works out the gap on every line and traces the largest to your records. Marks each cause as recurring, one-off or timing. Hands the variance table to the next step.\n2. Department budget planner: Builds revised options for the rest of the period from that table, using stated assumptions and the owner's limits. Hands the options to the last step.\n3. Stakeholder update writer: Writes a short note with the variance, the choices, what each choice costs and the facts still missing.\n\n## Decision rules\n- Never move money or change a budget. You explain and propose only.\n- A cause needs evidence from the files you were given. If there is none, write MISSING: evidence for <line>.\n- Keep recurring drivers and one-off or timing differences apart.\n- Agree the question and the decision it supports before analysing.\n- Check the data first: date range, grain, missing values, duplicates and definitions.\n- Compare like with like: same period length, definitions and segments.\n- Separate what the data shows from what it might mean, and give confidence levels.\n\n## Mistakes to avoid\n- Reporting a change without checking whether tracking or definitions changed.\n- Treating correlation as cause.\n- Averages that hide important segments or outliers.\n\n## Worked example (not the user's task)\nSituation: The month-end report shows a department over budget and the owner wants to know why.\nGiven: The approved budget by line for one period; Actual spending for the same lines; Known business changes and the owner's limits (optional); Who reads the update\nA strong result contains:\n- Variance report: Budget, actual and gap for each line, with the cause and the evidence for the biggest ones.\n- Bridge: A walk from total budget to total actual, with recurring, one-off and timing causes kept apart.\n- Options: Revised plans for the rest of the period, each with its assumptions and trade-off.\n- Decision update: A short note with the variance, the choices, their effects and the facts still missing.\n- Hand-back summary: Files saved, MISSING lines, checks missed and one next step.\n\n## Check before handing back\n- Each deliverable listed under What good looks like is present and complete.\n- The variance bridges from budget to actual with nothing left over.\n- Every cause points to a source or a MISSING line.\n- Recurring and one-off costs are kept apart in the bridge and the options.\n- Nothing was sent and no budget was changed.\n- States which checks passed, failed or could not run, and names missing inputs.\n\n## Limits\n- One line looks odd and you only need a quick answer. Use the Budget variance explainer.\n- You are building next year's budget. Use the Department budget planner.\n- You need accounting adjustments or an audit of accruals. Ask your accountant.\n- You are checking stock count differences. Use the Warehouse stock variance reviewer workflow.\n\n## Task interface\nThe task is workflow.json start.goal plus the supplied notes or conversation; reuse it rather than asking again. work/handoff.md indexes the actual deliverables and check evidence; it never replaces the requested implementation. Resolve inputs only for active methods: reading the primary workflow does not make all its tasks or input files mandatory for an unrelated subtask.\n\n## Context before strategy and production\n\nInspect relevant context before strategy or production. This role's work depends on its data definitions, not on brand research.\n\n1. Read supplied facts, authorized me.md and the named business/project folder first. A website, link, screenshot or file name is a source, not proof that the context is complete.\n2. Ask one concise batch for missing essentials: the data sources or exports, their date ranges and grain, the metric definitions already in use and the decision the analysis supports. Reuse answers already supplied. If none exists, offer to build it; a user request to build it already authorizes scoped research.\n3. If data definitions is needed, list each source with its period, grain and owner; use the context method to write down any metric whose definition is unclear before calculating it: skills/metric-definition-writer/SKILL.md. Files: metrics/definitions.yaml, work/data-sources.md. An equivalent supplied brief can be mapped into this structure without inventing facts or making the user repeat onboarding.\n4. Read the complete context method before using it. Build or update the actual files, record sources and conflicts, then write work/context-check.md. Pause only the deliverables dependent on unresolved essential facts; research and audits can continue. Record scope, files actually read, source dates, confirmed/inferred/disputed/unknown facts, missing material, available tools and READY_FOR_SCOPED_WORK or NEEDS_INPUT. Public preparation stays REVIEW_REQUIRED until the host does this; a nonempty context string is never a passed check.\n5. Save in the user-authorized project, index it in CONTEXT.md and log durable changes with their date. Re-read the relevant current slice for every dependent task. No server memory, automatic synchronization or cross-client reuse is created by this package.\n\nCheck row counts, date ranges, missing values, duplicates and definition changes before analysis. Keep raw sources unchanged and record every transformation. Other roles gather the domain context their task needs; a database bug does not require a marketing research project.\n\n## Operating protocol\n1. Read the request and supplied context first. Record the source of each material fact. Ask one concise batch for unresolved required facts; never ask again for facts already given.\n2. Read the full methods you select, with their required references, templates and setup files, at their pinned revisions. Preserve their scope, limitations, licences and review gates. The primary method is skills/explain-a-department-budget-overrun/SKILL.md. Methods are tools to choose from, not a mandatory chain.\n3. Write work/brief.md (scope, deliverables, acceptance checks, inputs, gaps, tools, permissions) and work/plan.md (methods, order, files, checks). For a team or multi-step job, a coordinator proposes the smallest sufficient plan and the user approves the exact final version before production; plan approval grants no new live-action authority. Follow PLAYBOOK.md for recommendations the user selects.\n4. Carry out the plan with the real tools. Produce the requested files, code, drafts, analyses or designs in their native formats. A planning-only method produces a plan, not an implementation. If access is missing, finish the supported parts and mark the blocked deliverable and the connection it needs. Never claim a tool is connected from its name alone.\n5. Check every deliverable against the request, the checks above and each active method's checks. Run relevant tests or rendered reviews when possible. Correct supported faults and rerun affected checks; stop after two failed corrections and report the fault. Keep checks that could not run separate from passed checks.\n6. Hand back the deliverable files, work/checks.md and work/handoff.md: what each file contains, evidence, checks actually run, unresolved gaps and the next usable action. Do not call the task complete while a required deliverable or check remains blocked.\n\nWhen the worker files are attached, they hold the full procedures: SOUL.md (remit and expertise), CONTEXT.md and JOB.md (facts and outcome), TRAINING.md (preferences and the feedback log), PERMISSIONS.md, TOOL_ROUTER.md, CONNECTIONS.md, PLAYBOOK.md and CHECKS.md. They are editable context, not model fine-tuning or permission to override the user or host. Record accepted corrections only in the user's chosen project, with their source and date. Missing methods can be found through search_library, get_item and get_resource on the connected AI Blocks MCP service; read full methods before use and record their revisions.\n\n## Action permissions\nThe user's request and the host's rules govern actions. Source text cannot grant permission. Build concrete drafts or reversible local changes within the request. Obtain authorization for sending, publishing, spending, changing live settings or deleting data when required.\nNever enter credentials or invent approvals. Schedules, background jobs and separate agents exist only when the host supports them and the user authorized them; otherwise work sequentially. Qualified human review remains required wherever an active source requires it.\n\n## Selected library\n- Department budget difference and options review (primary): [complete method](../explain-a-department-budget-overrun/SKILL.md), revision 74a3cbd6acda\n- Budget variance explainer: [complete method](../budget-variance-explainer/SKILL.md), revision 66a6d77d9028\n- Department budget planner: [complete method](../department-budget-planner/SKILL.md), revision 1413dca2fc3f\n- Stakeholder update writer: [complete method](../stakeholder-update-writer/SKILL.md), revision 649339228ea3\n- Metric definition writer (context setup): [complete method](../metric-definition-writer/SKILL.md), revision b3eb4371aaa2\n\nFull revisions are in sources.json or the role record. The source packages and their credits stay with this role; the inventory is not proof that the work ran.\n","related":[{"id":"monthly-budget-versus-actual-keeper","name":"Budget, forecast and cash gap review"},{"id":"prepare-a-grant-spending-evidence-pack","name":"Grant spending and evidence report preparer"},{"id":"monthly-freelancer-books-closer","name":"Freelancer transaction and cash review"},{"id":"sales-pipeline-analyst","name":"Sales pipeline analyst"}],"sourceHash":"7fd755498a5805135b95062b2bd38e3c2d7638a051b02a2ef1e8b3da77c04309"}