prompt-evaluation-runn…
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when preparing a versioned release and release metadata, validation, publish commands, and rollback plan must be checked before tagging.
$ npx -y skills add yeaight7/agent-powerups --skill release-readiness-protocol --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/release-readiness-protocolContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when preparing a versioned release and release metadata, validation, publish commands, and rollback plan must be checked before tagging.
name: release-readiness-protocol description: Use when preparing a versioned release and release metadata, validation, publish commands, and rollback plan must be checked before tagging.
Confirm a release is correct, documented, validated, publishable, and reversible before any external write such as a tag push, package publish, or GitHub release.
Read the current version from the relevant manifest and verify the target does not already exist:
npm view <pkg>@<version> version pip index versions <pkg> cargo search <pkg>
Confirm bump type:
git describe --tags --abbrev=0 git log <last-tag>..HEAD --oneline --no-merges git diff --stat <last-tag>..HEAD
Flag breaking changes, release-note gaps, and user-visible assets that changed.
For npm packages:
npm pack --dry-run
Run the full release suite for the project:
npm test npm run build python scripts/validate-skills.py python scripts/validate-catalog.py
If a repository has a release preflight command, prefer it:
npm run release:check
Write exact commands before executing them:
git tag vX.Y.Z -m "Release vX.Y.Z" git push origin vX.Y.Z npm publish --access public gh release create vX.Y.Z --verify-tag --title "vX.Y.Z" --notes-file <notes>
Wait for explicit approval before the first irreversible step.
| Step | Rollback | | --- | --- | | local tag | `git tag -d vX.Y.Z` | | pushed tag | `git push origin :refs/tags/vX.Y.Z` | | npm publish | `npm deprecate <pkg>@<ver> "released in error"` | | GitHub Release | `gh release delete vX.Y.Z --yes` |
RELEASE READINESS: go / no-go Version: X.Y.Z Compare range: <last-tag>..HEAD Changelog coverage: complete / gaps Breaking changes: yes / no Validation: <commands and result> Publish plan: <exact commands> Rollback plan: <exact commands> Blockers: <none or list>
Curated power-ups for coding agents: skills, slash commands, MCP configs, hooks, AGENTS.md templates, and workflows for serious software engineering. Claude Code, Codex, Antigravity CLI, Cursor and more
Repo: yeaight7/agent-powerups
Use when evaluating prompts, LLM outputs, red-team suites, or model behavior with local eval configs and safe provider/cost controls.
Use when creating or reviewing red-team eval plugins, attack templates, grader rubrics, safety fixtures, or model-risk test metadata.
Use when designing, running, debugging, or hardening deterministic eval suites for agent skills, prompts, tool workflows, or MCP-backed cases.
Use when designing tool definitions for a new agent or subagent, an agent shows high retry rates, ambiguous tool invocations, or silent failures, or an…
Use when routing a prompt to a local provider CLI for a second opinion, review, or plan -- you are about to call a provider directly, need the response saved…
Use when starting work in an unfamiliar area of a codebase, spawning a subagent that needs targeted file context, a first search pass missed the relevant file,…