Repo proof
Skill Gary06868/repo-proof
Use this skill when a user needs to prove that a repository README or release instructions work from a fresh clone: audit install/run/test/demo steps, create cleanroom evidence, classify README/script/config/package failures, generate minimal fixes, or add a GitHub Action for README truth verification. Do not use for ordinary README writing, generic code review, broad QA checklists, or tasks that do not require repository-grounded fresh-clone evidence.From its SKILL.md
npx -y skills add Gary06868/repo-proofAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.0 KB, 345 tokens by cl100k_base, as published. Nobody here has run it
RepoProof
Prove the repository from the point of view of a new user. Treat the README as a contract, not a suggestion.
Default Workflow
- Run
node scripts/repoproof.mjs audit . --output repoproof-output. - Read
repoproof-output/repoproof-report.jsonbefore drawing conclusions. - If the user explicitly permits execution, run
node scripts/repoproof.mjs prove . --allow-exec --output repoproof-output. - If fixes are requested, run
node scripts/repoproof.mjs fix . --dry-run --output repoproof-outputand inspectrepoproof-fixes.patch. - Report only what the evidence supports. Mark unproven claims as unproven.
Safety Rules
- Audit mode is the default and must not execute repository code.
- Prove mode requires explicit user approval with
--allow-execor a CI runner. - Never publish, deploy, push, merge, or read user secrets.
- Never claim strong sandboxing without a real container, VM, or OS sandbox.
- Use deterministic scripts for evidence collection and redaction.
References
- Read
references/workflow.mdfor the full audit/prove/fix workflow. - Read
references/safety-model.mdbefore executing repository code. - Read
references/extraction-rules.mdwhen README step extraction is ambiguous. - Read
references/fix-policy.mdbefore proposing edits. - Read
references/evidence-schema.mdwhen interpreting reports. - Read
references/github-action.mdbefore adding CI. - Read
references/platform-notes.mdfor Windows, macOS, and Linux differences.
What ships with it: 114 files
319.2 KB alongside SKILL.md, 38 of them executable
action/
- action.yml1.1 KB
agents/
- openai.yaml273 B
assets/
- demo.gif237.4 KB
- demo-storyboard.svg1.5 KB
- logo.svg591 B
docs/
- adapter-authoring.md325 B
- demo-script.md1.2 KB
- fixture-authoring.md458 B
- release-checklist.md1.3 KB
- threat-model.md720 B
evals/
- baseline-comparison.md605 B
- behavior-evals.json457 B
- rubric.md219 B
- trigger-evals.jsonl986 B
fixtures/
- expected/01-wrong-package-manager.json94 B
- expected/02-missing-env.json98 B
- expected/03-wrong-port.json71 B
- expected/04-undeclared-global.json87 B
- expected/05-npm-pack-missing.json80 B
- expected/06-python-version.json116 B
- expected/07-windows-script.json83 B
- expected/08-missing-demo-file.json90 B
- expected/09-cache-only.json71 B
- expected/10-service-not-accessible.json84 B
- expected/11-python-build-import-fails.json85 B
- expected/12-demo-mismatch.json74 B
- node/cache-only/index.jsruns105 B
- node/cache-only/package.json97 B
- node/cache-only/README.md33 B
- node/dangerous-readme/index.jsruns31 B
- node/dangerous-readme/package.json131 B
- node/dangerous-readme/README.md87 B
- node/good-cli/cli.jsruns188 B
- node/good-cli/package.json98 B
- node/good-cli/README.md60 B
- AGENTS.md524 B
- CHANGELOG.md539 B
- CITATION.cff265 B
- CONTRIBUTING.md709 B
- .env.example162 B
74 more files not listed here. See all 114 in the repository.