keel-research
Skill9 starsChanged 51 days agoMITView on GitHub
Opt-in external research — scan GitHub/articles/LinkedIn/HuggingFace/web and save cited findings per platform under research/.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sayeediftekhar/Keeltheir own version, first seen Nov 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- sayeediftekhar/Keel★ 0same 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 repository17 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- keel-adoptSkill
- keel-agent-team-createSkill
- keel-agent-team-startSkill
- keel-auditSkill
- keel-autopilotSkill
- keel-compactSkill
- keel-continueSkill
- keel-distillSkill
- keel-handoverSkill
- keel-phase-reviewSkill
- keel-pilotSkill
- keel-planSkill
- keel-statsSkill
- keel-teamSkill
- keel-tidySkill
- keel-updateSkill
The file
Files
/keel-research — structured, opt-in external research
HARD GATE: never run without the user's explicit opt-in in THIS session (rules.md §8.27). If the user hasn't opted in, stop and ask first. Produce a verified, cited evidence trail — never blind copy.
Workflow:
- Scope — confirm the question + which platforms to scan (
github,articles,linkedin,huggingface,web). Add/drop platforms to fit the question. - Fan out — one
researchersubagent (.claude/agents/researcher.md) per platform, in parallel. Each searches, reads real sources (not just snippets), and writesresearch/<platform>/findings.md. Large/raw artifacts go toresearch/<platform>/downloads/(git-ignored). - Cite + rate — every claim carries its source URL + a confidence note; flag low-signal/paywalled sources.
- Verify (rules.md §4) — as the main agent, don't accept sub-agent output blindly; sanity-check the load-bearing claims before they drive anything.
- Synthesize — a short cross-platform summary; conclusions that drive a decision go into an ADR
(
docs/adr/) ordocs/, not left buried underresearch/.
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.