create-prove
Skill785 starsChanged 12 days agoMITView on GitHub
Run a changed Aeon skill for real and attach SHA-bound behavioral evidence to its PR
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 26
Never prove create-prove by recursively dispatching itself.
- Very specific: line 31
Read the PR through gh api.
- Very specific: line 46
Wait up to 30 minutes. Require status=completed and conclusion=success.
- Distinctive: line 58
Never treat CI checks, source inspection, or the prior review receipt as behavioral evidence.
- Very specific: line 59
Never post a proven receipt for a failed, cancelled, timed-out, stale, empty-output, unsupported, or unsafe run.
- Distinctive: line 60
Do not merge, close, approve, or modify the target PR.
- Distinctive: line 61
Do not commit repository files.
- Very specific: line 65
Use gh for every GitHub read, dispatch, log fetch, and PR comment.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
${var} - Required immutable target in the form
owner/repo#pr@40-character-lowercase-sha.
Today is ${today}. Prove the behavior of one Aeon-shaped change by running the changed skill through the target repository's real aeon.yml workflow. A green diff review is not proof. A successful, correlated Actions run is proof.
Scope
This first implementation supports Aeon-shaped pull requests that change exactly one runnable skills/<slug>/SKILL.md. It does not launch conventional applications and it does not guess which skill represents a workflow-only or configuration-only change. Unsupported target shapes must fail closed without posting a proof receipt.
Never prove create-prove by recursively dispatching itself. Exit PROVE_UNSUPPORTED instead.
Steps
- Parse
${var}intotarget=owner/repo#prandexpected_sha. Reject any value outside the exact grammar above withPROVE_INVALID_TARGET. - Read the PR through
gh api. Require all of the following:- the PR is open;
- its current
head.shaequalsexpected_sha; - its head branch belongs to the same repository, because
gh workflow run --refcannot execute an untrusted fork branch in the base repository; - exactly one changed path matches
skills/<slug>/SKILL.md; - the slug is not
create-prove. Any mismatch exitsPROVE_UNSUPPORTEDorPROVE_STALEwithout a receipt.
- Inspect the changed skill's frontmatter and instructions. Choose the smallest real, non-destructive variable that exercises the changed behavior. If no safe real invocation exists, exit
PROVE_UNSAFErather than inventing evidence. Do not use synthetic credentials or a dry-run mode. - Dispatch the target branch's workflow by filename, with a unique correlation ID whose
dispatch_idmust start with the literal prefixprove-—.github/workflows/aeon.yml's commit-skip guard only recognizes that exact prefix to know this run is being proved, not a normal dispatch, and must not commit or push to the branch it's proving. Getting this prefix wrong silently defeats the immutable-head guarantee this whole skill exists to provide:
Discover the run only by the exact correlated run title, using the same rule asdispatch_id="prove-${pr_number}-$(date -u +%Y%m%dT%H%M%SZ)-${RANDOM}" gh workflow run aeon.yml --repo "$repo" --ref "$head_branch" \ -f skill="$skill" -f var="$proof_var" -f dispatch_id="$dispatch_id"chain-runner.yml. Never select merely the newest run for that skill. - Wait up to 30 minutes. Require
status=completedandconclusion=success. Fetch the run log and the captured skill output. Confirm the output is non-empty and does not contain_No output captured._. A successful Actions wrapper with no captured behavior isPROVE_MISSING_EVIDENCE. - Re-read the PR and require its head SHA still equals
expected_sha. - Post one PR comment containing a concise description of the exercised path, the run URL, a short output excerpt, and exactly one final machine receipt:
Construct the JSON with<!-- aeon-proof:{"schema":1,"target":"owner/repo#N","sha":"<sha>","kind":"aeon-skill","skill":"<slug>","evidence_run_id":123,"evidence_url":"https://github.com/owner/repo/actions/runs/123","verdict":"proven"} -->jq -cn, then render it on one line. Do not post the receipt until every gate above passes. - End with the target, skill, run ID, run URL, and
PROVE_VERDICT=provenin the captured output.
Constraints
- The proof run must execute the PR head branch, not
main. - Never treat CI checks, source inspection, or the prior review receipt as behavioral evidence.
- Never post a
provenreceipt for a failed, cancelled, timed-out, stale, empty-output, unsupported, or unsafe run. - Do not merge, close, approve, or modify the target PR.
- Do not commit repository files.
Network note
Use gh for every GitHub read, dispatch, log fetch, and PR comment. Authentication is provided by the workflow. Never print tokens or place secret values on a command line.
Log
Append the result to memory/logs/${today}.md under ### create-prove, including the target, SHA, selected skill, evidence run ID, and terminal verdict. The workflow may persist the captured output on your behalf.
Other versions3 projects use a version of this.
Word for word · 3
- aaronjmars/aeon★ 776100% same
- MiroShark/miroshark-aeon★ 19100% same
- aaronjmars/miroshark-aeon★ 18100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository90 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms.txtllms.txt
- aeonSkill
- action-converterSkill
- aeon-doctorSkill
- aeon-updateSkill
- anatomySkill
- arc-studioSkill
- articleSkill
- auto-mergeSkill
- autoresearchSkill
- auto-workflowSkill
- base-mcpSkill
- bd-radarSkill
- changelogSkill
- competitor-monitorSkill
- compute-resellSkill
- cortx-reliabilitySkill
- create-skillSkill
- defi-overviewSkill
- deploy-prototypeSkill
- deploy-uni-hookSkill
- digestSkill
- distribute-tokensSkill
- executor-mcpSkill
- featureSkill
- feedback-builderSkill
- fetch-tweetsSkill
- finance-district-mcpSkill
- fleet-controlSkill
- fork-fleetSkill
- github-filing-registrySkill
- github-monitorSkill
- github-trendingSkill
- glim-mcpSkill
- heartbeatSkill
- higgsfieldSkill
- hunter-22Skill
- idea-forgeSkill
- idea-pipelineSkill
- inbox-triageSkill
- install-skillSkill
- investigation-reportSkill
- last30Skill
- memory-flushSkill
- mention-radarSkill
- miroshark-matchdaySkill
- monitor-polymarketSkill
- narrative-convergenceSkill
- narrative-trackerSkill
- onchain-monitorSkill
- operator-scorecardSkill
- pack-submitSkill
- picks-trackerSkill
- pm-manipulationSkill
- posthog-errorsSkill
- price-alertSkill
- pr-reviewSkill
- pr-triageSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

