self-critique
Skill22 starsChanged 3 months agoMITView on GitHub
Adversarially critique your own last substantial answer before the user has to. Spawn a critic agent that verifies every claim against live sources, checks similar and related issues, finds patterns, and addresses comments directly to you. Loop (revise, re-score) until satisfied, then report where you were wrong, iterations-to-satisfy, the numeric improvement, and a final score. Use when the user asks you to criticize, challenge, stress-test, or red-team your own answer, or accepts a "critical-thinking review" offer.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- Fili999/ai-hubtheir own version, first seen Nov 15, 2026
- goolars/Claude-Code-Stoptheir own version, first seen Oct 25, 2026
- jfkconstruct/claude-skillstheir own version, first seen Oct 11, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- goolars/Claude-Code-Stop★ 4same name
- Fili999/ai-hub★ 2same name
- jfkconstruct/claude-skills★ 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 repository194 other files it gives its agents.
- 0-templateSkill
- ab-test-analyzerSkill
- academy-guideSkill
- add-to-my-skillsSkill
- adr-authorSkill
- ai-tools-setupSkill
- algorithmic-artSkill
- api-and-interface-designSkill
- api-designerSkill
- api-docs-writerSkill
- apple-store-submitSkill
- aws-cost-optimizerSkill
- bash-script-hardeningSkill
- blog-post-writerSkill
- book-summarizerSkill
- branch-cleanupSkill
- brand-copy-landingSkill
- brand-copySkill
- brand-designSkill
- brand-guidelinesSkill
- browser-testing-with-devtoolsSkill
- canvas-designSkill
- changelog-generatorSkill
- changelog-keeperSkill
- chart-chooserSkill
- ci-cd-and-automationSkill
- ci-fix-loopSkill
- claude-apiSkill
- cloudflare-block-countriesSkill
- coderabbitloopSkill
- code-review-and-qualitySkill
- code-reviewerSkill
- code-simplificationSkill
- codexloopSkill
- comms-notionSkill
- comms-slackSkill
- comms-whatsappSkill
- competitive-analysisSkill
- concept-explainerSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- context-repoSkill
- cover-letter-writerSkill
- crash-courseSkill
- cron-schedulerSkill
- data-digestSkill
- data-pipeline-architectSkill
- debug-detectiveSkill
- debugging-and-error-recoverySkill
- decision-matrixSkill
- dependabot-triageSkill
- dependency-upgraderSkill
- deprecation-and-migrationSkill
- dev-instantdbSkill
- discernment-nudgeSkill
- doc-coauthoringSkill
- dockerfile-proSkill
- docs-index-keeperSkill
- documentation-and-adrsSkill
- docxSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Run an adversarial review of your own previous answer and report the result in numbers.
- Distinctive: line 38
Do not use for trivial one-shot replies or simple chat.
- Very specific: line 52
Decide and loop: Stop if score >= 90 OR no actionable fixes remain.
- Very specific: line 62
If only one round ran, state no revision needed.
“Common” is measured: kept by at least 6 in 10 of the 3 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
Self-critique
Run an adversarial review of your own previous answer and report the result in numbers.
Overview
A confident answer is not a verified one. This skill turns your last substantial reply into the subject of a hostile review: a separate critic agent tries to refute it against live sources, hunts for the related issue or pattern you missed, and scores it. You then revise and re-score until the score stops moving, and report the outcome honestly, including where you were wrong.
The point is to surface error before the user does, and to make "is this actually right?" a measured quantity instead of a vibe.
When to Use
- The user asks you to criticize, challenge, stress-test, red-team, or "poke holes in" your own answer.
- The user accepts a "critical-thinking review" offer.
- You have just produced a substantial analysis, recommendation, or investigation and want a confidence number before the user acts on it.
Do not use for trivial one-shot replies or simple chat. The overhead only pays off on load-bearing answers.
Procedure
- Snapshot the target. Capture your last substantial answer verbatim, plus the concrete claims
it makes and the source each claim rests on. This is
v1. - Spawn the critic. Launch one independent agent with live-source access (issue tracker, code
host, error monitor, the repo). Use the prompt template below. The critic must return:
score(0-100),verdict(AGREE / AGREE-WITH-CAVEATS / DISAGREE),where_wrong(list),missed(related issues or patterns you failed to surface),unverifiable(claims it could not confirm), andfixes(ranked, actionable). - Decide and loop. Stop if
score >= 90OR no actionablefixesremain. Otherwise revise the answer using the fixes to producev2, then re-spawn the critic to scorev2. Repeat. Hard cap: 3 critic rounds. (A known ceiling: raise it only if a round is still finding real, fixable defects.) - Report, always, even after a single round:
- Where you were wrong - consolidated, each item with the receipt the critic cited.
- Iterations to satisfy - how many critic rounds it took to reach the stop condition (1 means it was solid on the first pass).
- Improvement in numbers - the score trajectory, for example
72 -> 88 -> 94 (+22 pts, +31%). If only one round ran, stateno revision needed. - Final score - the critic's last score and verdict.
- Unverifiable - anything you should not present as fact.
Critic prompt template
Pass this to the critic agent, filling in the two placeholders. It is deliberately adversarial: the default stance is that the answer is wrong until a live source proves otherwise.
You are an adversarial reviewer. Your job is to verify and, where possible, refute the answer below. Default to skepticism: assume a claim is wrong until a live source proves it. Address every comment directly to the author ("You claimed X; the source says Y").
The answer under review (verbatim): {{ANSWER}}
Its claims and the source each rests on: {{CLAIMS_AND_SOURCES}}
Do this:
- Re-verify every claim against the live source (issue tracker / code host / error monitor / the repo) - never trust the answer's own summary. Quote the field, line, PR body, or issue you checked.
- Check similar and related issues, and find patterns. Is this part of a cluster? Is there a closer sibling, parent epic, or duplicate the answer should have surfaced but did not? Name it with its ID and the shared signal (same error, same code path, same root cause).
- Stress-test the strongest load-bearing claim and the answer's biggest blind spot specifically. Where is it over-confident? Where is symptom-level reasoning passing itself off as a proven root cause?
- List exactly where the author was wrong or imprecise, and what they missed.
- Flag any claim you could not verify so it is not presented as fact.
Output, terse, with a receipt for every line:
verdict: AGREE | AGREE-WITH-CAVEATS | DISAGREEscore: 0-100 (rubric: 100 = every claim verified, nothing missed, confidence correctly calibrated; subtract for each unverified claim, each missed sibling or pattern, and each over- or under-statement)where_wrong: bullet list, each with its source receiptmissed: related issues or patterns the author failed to surface, with IDsunverifiable: claims that need a source you do not havefixes: ranked, actionable - what to change to raise the score
Optional: auto-offer via a Claude Code Stop hook
A hook is a shell command, so it cannot run this loop itself. What it can do is nudge: after a substantial answer, it offers the review and you run the skill only if the user says yes.
The hook ships with this skill at scripts/critique-nudge.mjs. Register it as a Stop hook in your
Claude Code settings (.claude/settings.json for a team, .claude/settings.local.json for
yourself):
{
"hooks": {
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "node \"$CLAUDE_PROJECT_DIR/.claude/hooks/critique-nudge.mjs\"",
"timeout": 15
}
]
}
]
}
}Copy scripts/critique-nudge.mjs to .claude/hooks/critique-nudge.mjs (or point the command at
wherever you keep it). After an answer whose final prose is at least 1500 characters, the hook blocks
the turn once and instructs the agent to append a one-line "critical-thinking review" offer, then
stop. Two loop guards keep it from firing forever: it does nothing when stop_hook_active is set, and
nothing when the answer already contains the offer phrase. On any malformed input it exits silently
and never blocks the user.
The 1500-character threshold is a heuristic with a known ceiling: it misses short but dense tool-heavy turns. If that matters, extend the script to also count tool calls since the last user message.
Notes
- One critic round is fine and common. If the answer was already solid, report
iterations: 1, no revision neededand the single score rather than forcing a revision. - Diversity beats redundancy: if a claim can fail in more than one way, give the critic distinct lenses (correctness, completeness, does-it-reproduce) instead of repeating the same check.
- The critic verifies against live sources; it does not rewrite the answer. You revise; it re-scores.
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.

