knowledge-review
Skill14 starsChanged 3 months agoMITView on GitHub
Audit the authority, freshness, and uncertainty of the sources and claims behind a decision, and reconcile conflicting evidence. Use for research synthesis, factual-claim checks, or reframing a recommendation built on weak sourcing. This is knowledge review, never code review.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- agno-agi/contexttheir own version, first seen Nov 8, 2026
- librocat/librocattheir own version, first seen Aug 23, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- agno-agi/context★ 16same name
- librocat/librocat★ 2same 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 repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brief-creativeSkill
- brief-product-uiSkill
- conquistadorSkill
- create-brandSkill
- create-paid-campaignSkill
- create-shortformSkill
- debate-agentsSkill
- improve-conversionSkill
- map-user-flowSkill
- measure-growthSkill
- model-growth-funnelSkill
- optimize-searchSkill
- plan-campaignSkill
- polish-vietnameseSkill
- research-channelSkill
- research-positioningSkill
- write-copySkill
- write-longformSkill
- write-outreachSkill
- write-socialSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Check that a decision rests on credible, current, and honestly uncertain evidence.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Knowledge review
Check that a decision rests on credible, current, and honestly uncertain evidence.
Clarify what is being claimed
State the factual claim or decision the review must support. Enumerate the sources and data the work currently leans on. Distinguish observed evidence, reasonable inference, and assumption before judging any of them.
Assess each source
For every source and claim, record:
- authority: primary or secondary, provenance, perspective, and known bias;
- freshness: an explicit date or how current this category of claim is;
- uncertainty: confidence, sample, and what could change the finding.
Build the contradiction matrix
For each key claim, put sources as rows and record what each asserts, its authority, date, and uncertainty. Mark every direct contradiction explicitly so conflicts are visible rather than merged.
Resolve
Reconcile conflicts by weighing authority, recency, and causal plausibility—not by counting or averaging sources. Label the resolved position and why the competing evidence lost.
Surviving unknowns and recheck trigger
List what remains unknown and set a recheck trigger: a date, event, or condition when the claim must be verified again. Do not let an unknown silently age into a fact.
Scope
This reviews knowledge, sources, and factual claims—not code. Do not use it to review an implementation, a diff, or a codebase; use a code-review path for that. Keep the review proportional to the decision and never fabricate or pad sources.
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.

