{
 "schema": "aiblocks-page/1",
 "id": "the-head-agent-strategic-oversight-implementation-planner",
 "type": "skill",
 "name": "Multi-agent findings brief builder",
 "summary": "Turn findings from several AI agents into one daily brief. Merge repeats, rank open issues and plan who handles each. Draft only.",
 "headline": "Multi-agent findings brief builder",
 "subhead": "Give it the findings your AI agents posted, each agent's job and who may hand work to whom. It merges repeats, ranks what is open and plans each handoff. You get a daily brief, a handoff plan and test cases. Nothing is sent or changed.",
 "job": {
  "id": "build-software",
  "name": "Build and ship software"
 },
 "level": "intermediate",
 "thinking": "medium",
 "tested": true,
 "updated": "2026-11-03",
 "first_published": "2026-10-25",
 "inputs": [
  {
   "type": "question",
   "required": true,
   "label": "Question",
   "what": "the problem, decision or piece of work you want help with, and what a good outcome looks like"
  },
  {
   "type": "codebase",
   "required": false,
   "label": "Codebase",
   "what": "a project's code, in a folder or repo the AI can open"
  }
 ],
 "outputs": [
  {
   "type": "plan",
   "required": true,
   "label": "Plan",
   "what": "a dated plan: what to do, in what order, with a decision rule for each step"
  },
  {
   "type": "code_change",
   "required": false,
   "label": "Code change",
   "what": "a change to the code, with what it fixes and how it was checked"
  }
 ],
 "you_give": [
  "The findings your agents posted, with agent name, date, client or team, severity, title and evidence",
  "Your agent list, with what each one handles",
  "The handoff rules, meaning which agent may give work to which, and the longest chain of handoffs allowed",
  "How you rank urgency, such as money at risk or customer impact (optional)",
  "Who makes the call on each kind of decision",
  "Your coordinator code and tables (optional)"
 ],
 "you_get": [
  "A daily brief with one top action, merged issues and a ranked open list",
  "Each disagreement shown with both views and what would settle it",
  "A handoff plan with an owner, a rule check and blockers for each task",
  "A list of decisions that need a named person",
  "A list of gaps in the starter code, and test cases on made-up findings"
 ],
 "use_when": [
  "Three agents flag the same client problem on the same morning and you want one clear item, not three.",
  "You want a short daily brief you can read in two minutes, with the first action on top.",
  "Agents disagree, such as one says pause and another says keep going, and you need both views side by side.",
  "You are about to let one agent hand tasks to others and want the rules checked first."
 ],
 "skip_when": [
  "You run one agent. Its own report is enough. A brief only pays off when several agents report.",
  "You want one person's daily summary of email and meetings. Use the Daily executive brief writer.",
  "You want the task table where agents claim work. Use the Agent task ownership workflow builder.",
  "You want rules for who must approve an action. Use the Agent approval workflow builder.",
  "You want it to post the brief or assign the tasks. It drafts the brief and the plan. You send them."
 ],
 "output_sample": {
  "input": [
   "The findings your agents posted",
   "Your agent list and what each one handles",
   "Your handoff rules and the longest chain allowed",
   "How you rank urgency (optional)"
  ],
  "prerequisites": [
   "Agents that already post findings somewhere you can copy from",
   "Your coordinator code, if you want the gaps listed (optional)"
  ],
  "output": [
   {
    "name": "Daily brief",
    "contains": "The date, the window and one top action, written in one sentence."
   },
   {
    "name": "Merged issues",
    "contains": "Findings that describe one problem, with who reported it and the evidence."
   },
   {
    "name": "Ranked open items",
    "contains": "What is still open, in order, with the reason for the rank and an owner."
   },
   {
    "name": "Disagreements",
    "contains": "Where two agents say different things, both views and what would settle it."
   },
   {
    "name": "Handoff plan",
    "contains": "Each task with its sender, receiver, the rule that allows it, and what blocks it."
   },
   {
    "name": "Escalations",
    "contains": "Decisions only a person can make, with the person named."
   },
   {
    "name": "Gaps in the starter",
    "contains": "What the starter code leaves out, and the fix for each gap."
   },
   {
    "name": "Test cases",
    "contains": "Made-up findings that check merging, ranking and the handoff rules."
   }
  ]
 },
 "output_shape": "BASIS\n<what was read; nothing was run>\nMISSING: <inputs and what each stops>\n\nDAILY BRIEF\n<date and window> | <scope>\nTOP ACTION: <one sentence>\n\nMERGED ISSUES\n<#> | <issue> | <scope> | <reported by> | <evidence> | <severity>\n\nRANKED OPEN ITEMS\n<rank> | <item> | <why it ranks here> | <owner>\n\nDISAGREEMENTS\n<issue> | <view A> | <view B> | <what would settle it>\n\nHANDOFF PLAN\n<task> | <from> | <to> | <rule that allows it> | <depth> | <blocked by>\n\nESCALATIONS\n<decision> | <person who decides> | <if no answer>\n\nGAPS IN THE STARTER\n<#> | <what is missing> | <fix>\n\nTEST CASES\n<name> | <set-up> | <expected result>\n\nNEXT STEP\n<one smallest useful step>",
 "how_to_use": [
  "Open the skill in your AI. A chat AI works if you paste your findings in. Claude Code or Codex works better if you want it to read your code.",
  "Paste the findings, your agent list and your handoff rules. Remove client names and keys first.",
  "Read MISSING first. It lists anything you left out and what that stops.",
  "Check MERGED ISSUES against the raw findings. Make sure no two different problems were joined.",
  "Check the HANDOFF PLAN. Each task needs a rule that allows it. Fix any that do not.",
  "Run the test cases on a copy of your system before it sends anything. Send the brief yourself."
 ],
 "checks": [],
 "next": [
  {
   "name": "Pull request writer",
   "url": "https://useaiblocks.com/skills/pull-request-writer",
   "why": "Build it"
  },
  {
   "name": "Git workflow helper",
   "url": "https://useaiblocks.com/skills/git-workflow-helper",
   "why": "Build it"
  }
 ],
 "source": null,
 "credits": [],
 "files": [
  "references/head-agent-starter.ts",
  "references/method-notes.md",
  "references/visual-reference-notes.md"
 ],
 "links": {
  "page": "https://useaiblocks.com/skills/the-head-agent-strategic-oversight-implementation-planner",
  "markdown": "https://useaiblocks.com/skills/the-head-agent-strategic-oversight-implementation-planner.md",
  "json": "https://useaiblocks.com/skills/the-head-agent-strategic-oversight-implementation-planner.json",
  "instructions": "https://useaiblocks.com/skills/the-head-agent-strategic-oversight-implementation-planner/SKILL.md",
  "download": "https://useaiblocks.com/skills/the-head-agent-strategic-oversight-implementation-planner.zip",
  "api_item": "https://useaiblocks.com/api/v1/items/the-head-agent-strategic-oversight-implementation-planner",
  "api_document": "https://useaiblocks.com/api/v1/documents/skill/the-head-agent-strategic-oversight-implementation-planner",
  "mcp": "https://useaiblocks.com/mcp"
 }
}