--- title: "Layered research handover builder" type: "skill" url: "https://useaiblocks.com/skills/layered-research-handover-builder" updated: "2026-10-28" first_published: "2026-10-25" job: "Write down how work gets done" tested: true licence: "MIT" source: "https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/artifact-pyramids" instructions: "https://useaiblocks.com/skills/layered-research-handover-builder/SKILL.md" --- # Layered research handover builder > Turn your research notes and sources into a layered research handover: a short summary that links to deeper analysis and evidence files. Share your research question, notes, sources, and who will read the work. It separates the main findings from deeper analysis and source records. You get a linked research folder so readers can start with the summary and inspect the evidence when needed. Free skill for the job "Write down how work gets done" · Level: intermediate · Thinking: high · Safety checked · Updated 2026-10-28 ## Links - Page: https://useaiblocks.com/skills/layered-research-handover-builder - Instructions (SKILL.md): https://useaiblocks.com/skills/layered-research-handover-builder/SKILL.md - All files (zip): https://useaiblocks.com/skills/layered-research-handover-builder.zip - JSON version: https://useaiblocks.com/skills/layered-research-handover-builder.json - In your AI: connect https://useaiblocks.com/mcp and ask "Use AI Blocks to get layered-research-handover-builder" ## What you give it - A research question, audience, notes, source evidence, and a destination folder. ## What you get - A research index, findings summary, topic analyses, evidence records, and coverage notes. ## Example: what goes in and what comes out ### What goes in - Your research question - Your notes and source material - Who will read the work - A folder to save the files in ### Before you start - An AI that can read the skill's reference files - An AI that can create files in a folder, or you copy the text out yourself - Python 3.9 and a shell only if you want the optional checker script ### What comes out - **00-index.md**: A map of the project that helps readers find files, with no findings in it. - **01-summary/**: One file with the research question, key findings and main implications, linking to the analysis files. - **02-analysis/**: One file per topic, such as market or risk, each readable alone and linking to evidence. - **03-dossiers/**: A flat set of files with source excerpts, raw data, transcripts and method notes. - **SOURCES section**: A closing list in every file of the paths below it and what you will find there. - **artifact-inventory.md**: A tracker of which files exist at each layer, so gaps are easy to spot. ## Skip it when - You only need a quick answer to one question: ask your AI directly, no folder needed. - You have a one-off lookup or calculation: just run it and keep the answer, no handover needed. - Your source material is already the final product and needs no summary: share it as it is. ## How to use it 1. Before you start, gather: your research question, your notes and source files (text, links, data), who will read the work, and a folder to save into. 2. Download the skill folder. In Claude, open Customize → Skills, then choose + → Create skill → Upload a skill. In ChatGPT, add the files to a project's Sources. In Gemini, make a Gem and paste the instructions. Or paste the instructions into a chat. The skill reads four reference files in its folder, so keep the folder together. 3. Give your AI your research question, your notes and sources, who will read the work, and a folder to save into. 4. Ask your AI to follow this skill. It drafts the one-file summary first, links it to one file per topic, and links each topic file to evidence files (source excerpts, data, method notes). It repeats until no gaps are left. 5. Open 00-index.md and the summary first. Click through to a topic file and an evidence file to check the links work and each file makes sense alone. 6. Read the coverage notes for gaps. Fill them, then ask your AI to update the links. 7. Share the index and the summary with readers first. Send the evidence files only to people who want to check the sources. 8. Where this copy comes from. We imported it from magnus919/agent-skills at commit 92c327e. The skill file's own metadata names an earlier home, magnus919/hermes-profiles, by the same author. ## What to do next - [Handover note writer](https://useaiblocks.com/prompts/handover-note-writer): Handover note writer - [Analysis assumptions logger](https://useaiblocks.com/skills/analysis-assumptions-logger): Analysis assumptions logger ## Sources and credits - From Magnus Hedemark: https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/artifact-pyramids, shared under the MIT licence (original name: artifact-pyramids). - [artifact-pyramids skill](https://github.com/magnus919/agent-skills/tree/92c327e525da69c9ad3812fd223a1770e977c2e3/artifact-pyramids), Magnus Hedemark: Copied under the MIT licence. We gave it a plain name. We added Before you start and After this sections that link to other AI Blocks steps. We refreshed those generated sections from the catalogue inputs and next-step links. - [Original author](https://github.com/magnus919/agent-skills/blob/main/artifact-pyramids/LICENSE), Groktopus: Wrote the skill; Magnus Hedemark shared it in their collection. ## Instructions (SKILL.md) ## Artifact Pyramids for Agentic AI Research Progressive disclosure governs how we feed agents context: metadata at startup, instructions on activation, resources on demand. **The Artifact Pyramid applies the same principle to what agents produce.** Three layers of increasing depth, each independently consumable, each linking down to the next. ### Before you start Use the material below to do this job. If facts or tool access are missing, explain what you can finish and what must wait. **What you need** (use your own material or the linked skill): - **Your question** (yours): the decision or problem, and what a good outcome looks like. **Makes it better (optional):** - **Source text** (yours): a long source in full: an article, a video or talk transcript, or notes from a book, with its title, author and link. How to start: 1. **Look first.** Use what they've already attached, pasted or put in their about-me note. In a coding assistant with file access, look in the project too for these by name. 2. **Check what's missing.** Look for your question, source text. They can attach files, paste the details, or share a file path your assistant can read. Ask only for missing facts that change the result. If they ask you to start with what they have, complete the parts you can and mark the gaps. 3. **Do the job.** Follow the skill below with the facts and tools you have. Mark each gap with `MISSING:` where it belongs and never invent a fact to fill it. **Tools that do this best:** - **A chat AI that can read the bundled reference files:** Use the supplied references and templates for the chosen task. Scripts are optional unless that task specifically needs them. ### Loading Guidance **When producing an artifact pyramid, load these references as a required set (not piecemeal):** | Reference | File | |-----------|------| | Pipeline Stages — layer definitions, navigation format, production flow | `references/pipeline-stages.md` | | Output Classification Framework — role-agnostic content contracts, 00-index/L1 boundary | `references/output-classification-framework.md` | | Quality Gates — verification checklists per layer | `references/quality-gates.md` | | Delegation Context Template — exact text for subagent output mandates | `references/delegation-context-template.md` | These four define complementary aspects of the spec that the others assume. Loading only a subset risks violating content contracts (e.g., putting findings in 00-index) or skipping required navigation affordances. Load the full set before writing any pyramid files. The reference table below describes *when* to load each file; the four above are **always required** for pyramid production. The remaining references (framework, worked example, canonical article, intellectual lineage, provenance, composite synthesis) are supplementary — load when the task calls for conceptual depth or a worked pattern. ### The Pyramid ``` ┌──────────────┐ │ L1 SUMMARY │ One file: research question, key findings, │ 🎯 │ most important implications. Links to L2 files. └──────┬───────┘ ┌──────┴───────┐ │ L2 ANALYSIS │ Per-dimension files: market, competitive, │ COLLECTION │ technical feasibility, risk. Self-contained, │ 🧩 │ each links to L3 dossiers. └──────┬───────┘ ┌──────┴───────┐ │ L3 DOSSIERS │ Source excerpts, raw data tables, interview │ 📦 │ transcripts, methodology notes. Reference └──────────────┘ library, pulled on demand. ``` The pyramid is consumed top-down but produced via recursive gap analysis: start with the summary, embed links to analysis files, write analysis files that link to dossiers, and evaluate after each round whether gaps remain. **Layer numbering is top-down** — L1 is the most distilled layer (the entry point), L3 is the most detailed (pulled on demand). This mirrors the Agent Skills input model: metadata (L1) → instructions (L2) → resources (L3). ### The Navigation Mechanism Every file at every layer carries, at the bottom, an explicit `SOURCES` section with absolute path references and descriptions: ``` SOURCES (LAYER 2 NAVIGATION) research/analysis/market-position.md -> Competitor mapping and market share analysis supporting Section 2 research/analysis/technical-feasibility.md -> Architecture evaluation supporting Section 3 research/dossiers/competitor-profiles.md -> Raw competitor data dossiers ``` These aren't footnotes. They are **navigation affordances** for agent consumers. Each description answers the question the consuming agent asks before loading: *what will I find if I go deeper?* ### Reference Files | Reference | Load when | File | |-----------|-----------|------| | Framework & Symmetry | You need the full conceptual foundation — the asymmetry problem, multi-agent routing, DIKW relationship | `references/artifact-pyramid-framework.md` | | Pipeline Stages | You're building or auditing a pyramid — detailed definitions per layer, navigation format, production flow | `references/pipeline-stages.md` | | Quality Gates | You need to verify an artifact meets the standard for its layer | `references/quality-gates.md` | | Worked Example | You want to see a complete synthetic walkthrough of all three layers | `references/synthetic-example.md` | | Intellectual Lineage | How software architecture documentation (4+1 Views, C4, arc42, ADRs) independently discovered progressive disclosure under different names — and what the Artifact Pyramid generalizes beyond them | `references/intellectual-lineage.md` | | Methodology-to-Pyramid Mapping | How specialist profiles map domain-specific methodologies into the universal pyramid structure, with dimension boundary rules | `references/methodology-to-pyramid-mapping.md` | | Output Classification Framework | **Role-agnostic** — three questions any specialist can ask to map their outputs into the correct layer: who consumes it, how often, what question it answers. Includes per-layer content contracts to eliminate duplication between 00-index and L1 files. | `references/output-classification-framework.md` | | Composite Pyramid Synthesis | How to merge multiple subagent pyramids into a root-level composite pyramid — orchestrator flow, SOURCES convention, worked example from jobs-finder pipeline | `references/composite-pyramid-synthesis.md` | | Delegation Context Template | You're delegating research to subagents and need the exact text to include in context strings to ensure artifact-pyramid output | `references/delegation-context-template.md` | | Flat-to-Pyramid Migration | You're converting existing flat JSON outputs to artifact-pyramid format — the pattern for L1/L2/L3 structure, 00-index rules, and downstream consumer fallback reads | `references/flat-to-pyramid-migration.md` | | Nested Pyramid Pattern | You're designing a single system that produces multiple artifact streams over time (multi-phase, multi-epoch) — avoid scatter, nest epochs under a single root pyramid | `references/nested-pyramid-pattern.md` | ### Scripts | Script | Load when | File | |--------|-----------|------| | pyramid-status | You want to audit an existing research directory for structural coverage | `scripts/pyramid-status.sh` | | extract-atoms | You have raw source text and need candidate atomic claims | `scripts/extract-atoms.py` | ### Templates | Template | Load when | File | |----------|-----------|------| | Project Scaffold | You're starting a new research project and need the index skeleton | `assets/pyramid-template.md` | | Artifact Inventory | You need to track what exists at each layer across a project | `assets/artifact-inventory.md` | ### Quick Start ```bash # Scaffold a new research project with all three layer directories mkdir -p my-project/{01-summary,02-analysis,03-dossiers} cp assets/pyramid-template.md ./my-project/00-index.md # Check structural coverage of an existing project scripts/pyramid-status.sh ./my-project # Extract candidate atoms from source text scripts/extract-atoms.py ./my-project/03-dossiers/source-1.txt ``` ### Project Structure ``` my-project/ ├── 00-index.md # Project scaffold (from template) ├── 01-summary/ # L1: one file — key findings, implications, links to L2 ├── 02-analysis/ # L2: per-dimension files (market, competitive, technical) ├── 03-dossiers/ # L3: source excerpts, transcripts, raw data, methodology └── artifact-inventory.md # Cross-layer tracking (from template) ``` The numbered prefixes mirror the pyramid's top-to-bottom orientation: 01 is most consumed, 03 is pulled on demand. ### Key Principles 1. **Progressive disclosure is symmetric.** The same three-tier model governs what agents consume (metadata → instructions → resources) and what they produce (summary → analysis → dossiers). 2. **Each layer is independently consumable.** A product-manager agent reads only the L1 summary. A data-scientist agent reads a single L2 analysis file. A verifier reads L3 dossiers. 3. **Navigation is explicit.** Every file carries a `SOURCES` section with absolute paths and descriptions — not footnotes, but agent navigation affordances answering *what will I find if I go deeper?* 4. **Depth varies by mission complexity.** A simple brief may produce only L1 + 2 analysis files. A competitive landscape may need all three layers with multiple files per layer. 5. **Quality gates are directional.** Material moves from L3 (sources) toward L1 (summary) only when it meets the gate for the target layer. 6. **03-dossiers/ is flat — no subdirectories.** The dossier layer is a flat reference library. Organize with epoch-prefixed or category-prefixed filenames (`epoch-1-validation-edit-3.json`), not nested directories. Subdirectories inside 03-dossiers/ violate the flat-file contract and break the SOURCES navigation path. 7. **Root-level files are amended; lower-level files are fixed.** In multi-epoch or multi-phase systems, `00-index.md`, `01-summary/findings.md`, and `02-analysis/` trajectory files grow as new data arrives. They are rewritten to reflect the current state. Files in `03-dossiers/` and per-category analysis files below `02-analysis/` are created once and never modified — they represent a fixed point in time. ### Validation Script Pitfall `scripts/pyramid-status.sh` currently discovers layers by matching **file names**, not canonical directory names. A compliant tree such as `01-summary/findings.md`, `02-analysis/topic.md`, and `03-dossiers/source.md` can therefore be falsely reported as missing L1/L2 when the nested file names do not themselves match the script's layer patterns. It also reports missing YAML frontmatter as a quality issue even though frontmatter is not required by the layer contracts above. Treat this script as a heuristic only; verify canonical directories, one L1 file, per-dimension L2 files, flat L3 files, final `## SOURCES` sections, and link resolution independently. ### When NOT to use - Single-turn Q&A with no research artifacts to preserve - Tasks producing only ephemeral output (one-off calculations, quick lookups) - Workflows where the source material IS the final output (no synthesis needed) ### Portability This skill is intentionally host-neutral. Use your agent's normal mechanisms to load the references, templates, and scripts listed here. Do not assume a particular profile system, task orchestrator, memory service, or response-handoff format. ### After this When you've handed it back, suggest what they could do next in one short question. It's a suggestion: if they're done, that's fine. Offer these, and say they can type their own: - The [Handover note writer](https://useaiblocks.com/prompts/handover-note-writer). It takes the document. - The [Analysis assumptions logger](https://useaiblocks.com/skills/analysis-assumptions-logger). It takes the document. If they pick one and that skill is added here, carry straight on with what you just made. If not, give the link and say what to bring.