research-synthesize
Skill0 starsChanged 4 months agoMITView on GitHub
Phase 2 of 3 in the research chain (gather → synthesize → artifact). Compresses and dedupes the raw material gathered in Phase 1 into a structured synthesis — themes, findings, contradictions between sources, and open gaps. Trigger when the previous phase says "run research-synthesize next", or standalone via "research-synthesize", "phase 2 of research", "synthesize the research".
4 other projects use a version of this.
Adopted by
Most recently taken up by
- wrencanfly/research-loop-skillstheir own version, first seen Nov 15, 2026
- simota/research-skillstheir own version, first seen Oct 19, 2026
- jpoindexter/theft-kittheir own version, first seen May 20, 2026
- TorpedoD/claude-researchertheir own version, first seen Apr 27, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- wrencanfly/research-loop-skills★ 49same name
- TorpedoD/claude-researcher★ 2same name
- jpoindexter/theft-kit★ 1same name
- simota/research-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository21 other files it gives its agents.
- bughunt-diagnoseSkill
- bughunt-fixSkill
- bughunt-reproSkill
- bughunt-verifySkill
- feature-ship-buildSkill
- feature-ship-reviewSkill
- feature-ship-shipSkill
- feature-ship-specSkill
- migrate-inventorySkill
- migrate-transformSkill
- migrate-verifySkill
- onboard-deepenSkill
- onboard-digestSkill
- onboard-mapSkill
- release-bumpSkill
- release-changelogSkill
- release-publishSkill
- release-tagSkill
- release-verifySkill
- research-artifactSkill
- research-gatherSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 3 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
All chain state is managed by the chain tool: authoritative JSON at .pi/fairy-tales/chains/research/state.json with a human-readable …
- Very specific: line 31
Call the chain tool with action: "status", chain: "research" (a legacy .research-state.md from an older version is imported automatically):
- Very specific: line 34
If there is no run → abort: "No research run found.
- Very specific: line 35
If the run is not active with currentPhase: "synthesize" → abort: "Expected the run to be at phase synthesize but it is at …
- Very specific: line 38
If data.sources (or the gather phase summary) is missing → abort: "Phase pointer looks right but the Phase 1 output is missing.
- Very specific: line 41
If the tool reports the chain is locked by another session, abort.
- Very specific: line 48
Read every per-source note from data.sources.
- Distinctive: line 70
Call the chain tool:
- Distinctive: line 87
After completing this phase, output exactly:
- Distinctive: line 92
Do not start the next phase.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Research: Synthesize
Chain version: 2 (durable state contract — see docs/STATE-CONTRACT.md)
Phase 2 of 3: research-gather → research-synthesize → research-artifact
Overview
Takes the per-source notes, quotes, and links gathered in Phase 1 and compresses them into a structured synthesis: cross-source themes, the actual findings, where sources contradict each other, and what's still an open gap. Makes no report yet — that's Phase 3 — so this stays a focused analytical pass over already-gathered material.
All chain state is managed by the chain tool: authoritative JSON at
.pi/fairy-tales/chains/research/state.json with a human-readable state.md
projection beside it. Never create or edit state files by hand, and never create lock
files — the tool locks for you.
Load State
Call the chain tool with action: "status", chain: "research" (a legacy
.research-state.md from an older version is imported automatically):
- If there is no run → abort: "No research run found. Run
research-gatherfirst." - If the run is not
activewithcurrentPhase: "synthesize"→ abort: "Expected the run to be at phasesynthesizebut it is at<currentPhase/status>. Run that phase's skill instead." - If
data.sources(or the gather phase summary) is missing → abort: "Phase pointer looks right but the Phase 1 output is missing. Treat as corrupted — restart the chain or repair via chain action 'update'." - If the tool reports the chain is locked by another session, abort; a dead session's
lock can be cleared with
action: "unlock". Never create lock files yourself.
Workflow
Step 1 — Compress and dedupe
Read every per-source note from data.sources. Merge overlapping points across
sources, dedupe repeated quotes/claims, and drop material that turned out irrelevant
to the research question.
Step 2 — Extract themes and findings
Group the deduped material into cross-source themes. Under each theme, state the concrete findings, citing which source(s) support each one.
Step 3 — Surface contradictions
Explicitly call out anywhere two or more sources disagree — what each says, and (if determinable) which is more credible or current. Do not silently resolve a contradiction by picking a side without saying so.
Step 4 — Identify gaps
List open questions the gathered material doesn't answer — these become the "worth a follow-up round" notes that Phase 3 surfaces in the final report.
Step 5 — Complete the phase
Call the chain tool:
action: "complete-phase", chain: "research", phase: "synthesize",
summary: "N themes, M findings, K contradictions, J open gaps; judgment calls made while deduping or resolving overlaps",
data: {
"themes": [ { "theme": "<name>", "findings": ["<finding + citation>", "..."] } ],
"contradictions": ["<what each source says, and which is more credible/current>"],
"gaps": ["<open question>", "..."]
}The tool validates this is the current phase, advances the run to artifact, and
rewrites the JSON + markdown projection atomically.
Handoff
After completing this phase, output exactly:
Phase 2 complete. Chain state updated (
.pi/fairy-tales/chains/research/state.json). Run/research-artifactto begin Phase 3.
Do not start the next phase. Do not offer to continue. Output only the handoff line and stop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

