show-your-work
Skill1 starsChanged 23 days agoMITView on GitHub
Publish the evidence, rejected alternatives, and open uncertainties behind a non-obvious decision without exposing private reasoning. Use when explaining a decision or defending a result.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- schmug/clodcasttheir own version, first seen Nov 15, 2026
- dheerajjha/show-your-worktheir own version, first seen Oct 11, 2026
- quatico-solutions/agent-skillstheir own version, first seen Jul 2, 2026
- ahirmaan/show-your-worktheir own version, first seen Jun 25, 2026
- muyuhill/100books-to-skillstheir own version, first seen Jun 11, 2026
- ChewbaccaRoars/pathfinder-skillstheir own version, first seen Mar 22, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- muyuhill/100books-to-skills★ 14same name
- dheerajjha/show-your-work★ 4same name
- ahirmaan/show-your-work★ 2same name
- ChewbaccaRoars/pathfinder-skills★ 2same name
- quatico-solutions/agent-skills★ 2same name
- schmug/clodcast★ 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 repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .codex/AGENTS.mdAGENTS.md
- .gemini/AGENTS.mdAGENTS.md
- .cursor/rules/agent-foundry-orchestrator.mdcCursor rule
- .cursor/rules/agent-foundry-skills.mdcCursor rule
- web/llms.txtllms.txt
- anti-slopSkill
- api-designSkill
- automation-pickSkill
- bottleneck-gatingSkill
- budget-guardSkill
- cache-identitySkill
- constraint-then-solveSkill
- context-optimizationSkill
- cron-troubleshootSkill
- e2e-test-strategySkill
- engram-routingSkill
- execution-observabilitySkill
- fallback-model-routingSkill
- feedback-loopSkill
- judge-integritySkill
- knowledge-extractSkill
- landscape-firstSkill
- measure-firstSkill
- plan-before-codeSkill
- plan-then-actSkill
- prompt-disciplineSkill
- pushback-when-wrongSkill
- quality-protocolSkill
- read-before-buildSkill
- re-verify-findingsSkill
- session-closeoutSkill
- session-distillSkill
- structured-output-contractSkill
- verify-firstSkill
- workflow-decomposeSkill
- agent-memory-vaultSkill
- agent-team-standardsSkill
- autonomous-briefingSkill
- book-to-skillSkill
- chrome-devtools-mcp-bridgeSkill
- design-languageSkill
- funnel-pr-guardSkill
- persistent-memorySkill
- sql-migration-trioSkill
- token-compressionSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
Distinctive
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 19
After a complex audit, plan, redesign, or investigation, add a compact
- Distinctive: line 39
Keep the record short enough to read before the deliverable.
- Distinctive: line 43
Do not publish hidden chain-of-thought, scratch deliberations, or requests for the model to reveal internal reasoning.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Show Your Work
A decision is easier to trust when the evidence is visible. Publish a decision record, not a transcript of private thought.
What to publish
After a complex audit, plan, redesign, or investigation, add a compact Decision record beside the deliverable with these sections:
- Evidence used. The files, commands, or sources that support the result. Cite exact locations. Label anything inferred.
- Alternatives rejected. Options considered and why each lost. This answers "why didn't you do X?" without forcing the reader to ask.
- Uncertainty. What was not checked, what is stale, and what would change the conclusion.
- Pivot, if any. The finding that changed the approach, stated as a fact rather than a story.
- Next verification. The cheapest check that would falsify the result.
Procedure
- State the decision in one sentence.
- Attach the evidence for that sentence, closest source first.
- List the alternatives that a reasonable reviewer might expect.
- Mark each unresolved item as unknown or deferred; never fill a gap with confident wording.
- Keep the record short enough to read before the deliverable.
Private reasoning stays private
Do not publish hidden chain-of-thought, scratch deliberations, or requests for the model to reveal internal reasoning. Publish conclusions, evidence, and uncertainty instead. A reviewer needs reproducibility, not a monologue.
Good evidence
file:linefor a code claim- command output with the command shown
- source title and date for an external claim
- "inference" when no direct source exists
Worked example
A compact decision record with evidence, a rejected alternative, and an unknown.
Decision: move retries out of the executor into the provider client.
Evidence: executor.py:412-460 (retry loop), provider.py:88 (single attempt), issue #214.
Rejected: keep retries in the executor; it couples budget accounting to transport.
Unknown: whether the provider retries idempotent POSTs; owner asked to confirm.Anti-patterns
- A confident narrative with no citations.
- Listing alternatives nobody would have chosen, to look thorough.
- Performing certainty where the evidence is partial.
- Publishing private deliberation instead of a decision record.
- Generic praise ("did great work") in place of method.
Verification Checklist
- The decision is stated in one sentence. (step 1)
- Every factual claim has a citation or an inference label. (step 2)
- At least one rejected alternative is named with a reason. (step 3)
- Remaining uncertainty is explicit. (step 4)
- The record contains no request for hidden reasoning. (step 5)
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.

