release-verification-agent
Skill0 starsChanged 19 days agoMITView on GitHub
Cross-check version metadata, changelog, tags, packaged artifacts, install/start behavior, and publication workflow before or after a release. Use for release preparation or audit.
In this repository42 other files it gives its agents.
- AGENTS.mdAGENTS.md
- completion-claims-auditorSkill
- existing-work-preservationSkill
- mcp-reliability-auditorSkill
- multi-agent-integration-reviewerSkill
- project-context-recoverySkill
- requirement-traceability-auditorSkill
- scope-drift-guardSkill
- architecture-complexity-auditorSkill
- dependency-cycle-auditorSkill
- database-schema-reviewerSkill
- data-consistency-auditorSkill
- migration-safety-reviewerSkill
- loop-breakerSkill
- reproduction-builderSkill
- root-cause-debuggerSkill
- dependency-grounding-auditorSkill
- ci-failure-investigatorSkill
- cross-platform-readiness-auditorSkill
- environment-config-auditorSkill
- environment-parity-auditorSkill
- production-readiness-auditorSkill
- documentation-accuracy-auditorSkill
- token-efficient-workflowSkill
- accessibility-auditorSkill
- dead-feature-detectorSkill
- responsive-design-auditorSkill
- ux-state-completeness-auditorSkill
- agent-tool-trust-auditorSkill
- authentication-security-auditorSkill
- authorization-boundary-auditorSkill
- dependency-vulnerability-auditorSkill
- injection-risk-auditorSkill
- input-validation-auditorSkill
- secret-leakage-detectorSkill
- security-misconfiguration-auditorSkill
- api-contract-auditorSkill
- integration-reality-checkerSkill
- missing-test-detectorSkill
- regression-detectorSkill
- test-quality-auditorSkill
- ui-flow-verifierSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
1
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
- Distinctive: line 20
Read applicable repository instructions before edits.
- Distinctive: line 37
Verify tags/releases point to the intended commit and publication workflow actually publishes, rather than only uploading CI artifacts.
- Distinctive: line 38
Check platform-specific artifacts only on environments that can genuinely build/run them.
- Distinctive: line 39
After publication, fetch remote release metadata and compare it with local expectations.
- Distinctive: line 47
Never overwrite tags, force-push release history, or publish without authorization already established for the project.
- Very specific: line 64
If signing/notarization/other-platform runners are unavailable, report those as release blockers or pending checks rather than simulating …
≈ “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
Purpose
Prove a release artifact corresponds to the intended commit and can actually be consumed.
When to activate
A version/tag/package/installer/release is being prepared or claimed published.
When not to activate
Normal development changes with no release artifact or versioning impact.
Preconditions
- Read applicable repository instructions before edits.
- Preserve unrelated working-tree changes and establish a baseline when the workflow can modify code.
- Identify which tools and environments are actually available; do not claim unavailable checks ran.
Required inputs
- Target version and commit
- Version files/changelog
- Build/package workflow
- Release artifacts or draft
Workflow
- Identify the canonical version and enumerate every metadata location that must agree.
- Confirm changelog/release notes describe actual changes and do not claim unverified features.
- Build artifacts from a clean tree/CI path and record their names, hashes, sizes, and source commit where feasible.
- Install or unpack the actual artifact in an isolated destination and run a minimal start/import/version smoke check.
- Verify tags/releases point to the intended commit and publication workflow actually publishes, rather than only uploading CI artifacts.
- Check platform-specific artifacts only on environments that can genuinely build/run them; leave others pending.
- After publication, fetch remote release metadata and compare it with local expectations.
Relevant tools
Version control, build/package tools, checksum tool, isolated install, GitHub release/CI APIs.
Safety restrictions
Never overwrite tags, force-push release history, or publish without authorization already established for the project.
Validation
- Version/tag/changelog/artifact metadata agree.
- At least one clean artifact consumption smoke test is observed for each locally supportable artifact.
- Remote publication is verified from the remote service, not inferred from a local commit.
Expected output
- Release evidence matrix
- Artifact hashes/smoke results
- Remote tag/release state
- Platform gaps
Failure handling
If signing/notarization/other-platform runners are unavailable, report those as release blockers or pending checks rather than simulating them.
Completion criteria
The skill is complete only when every applicable validation item above has observed evidence or is explicitly marked not executed with the concrete blocker. Do not replace missing evidence with confidence language.
Research mapping
This skill was selected from research problems: P053, P027. See research/vibe-coding-problems.md and research/problem-evidence.csv in the Vibe Coding Skills repository.
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.