paladini

Audit pull requests and release readiness across correctness, tests, architecture, security, vendor documentation and version compatibility, repository docs, websites, changelogs, changesets, release notes, and explicit contributor attribution. Use when…

Use when the user asks to release, publish, or version-bump harness-score — covers the npm package, the Cursor plugin, and the docs, in the right order.

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

Use when the user asks to improve, fix, or build their repository's AI harness — AGENTS.md, rules, skills, commands, hooks, guardrails, CI sensors — or to act on harness-score audit findings and raise their maturity level.

Use when the user asks to deploy or release the sample app to production; covers the full checklist from tag to smoke test.

Generate CHANGELOG.md entries from git history using a deterministic script, then rewrite them into human release notes. Use when preparing a release, writing release notes, updating a changelog, or when the user mentions changelog, release notes, or "what's…

Write git commit messages from staged changes following Conventional Commits. Use when the user asks to commit, asks for a commit message, wants to fix or improve a commit message, or mentions conventional commits, semantic commits, or squash/reword.

Record and recall durable project lessons across agent sessions using a versioned lessons file. Use when finishing a task that revealed a surprise, workaround, or user correction worth remembering, when starting non-trivial work to recall relevant lessons, or…

TODO — What this skill does + when to use it, with the trigger keywords a user would actually type. Required: max 1024 characters, third person. Example: "Generate API client stubs from an OpenAPI spec. Use when the user mentions OpenAPI, swagger, API…

Orchestrate multi-channel publication: write with mcp-me voice, publish dev.to via MCP, cross-post Medium via medium-publisher CLI. Use for release announcements, cross-posting, or "publish everywhere" requests.

End-to-end DEV.to to Medium cross-post: verify session, import draft, review formatting against source markdown, apply fixes, security checks, confirm save, and publish only when the draft is fully corrected. Use when the user wants a complete corrected…

Publish or cross-post to Medium via the medium-publisher CLI (Playwright). Use when the user asks to publish on Medium, cross-post from dev.to/TabNews, import a story URL, or run medium-publisher login/session-check/import/publish.

Review and fix Medium drafts after DEV.to import. Compare source markdown with extracted Medium editor outline, fix formatting (code blocks, headings), confirm autosave. Use after medium_import or when import formatting looks broken.

Use the mcp-me MCP server to access the user's personal profile — identity, career, skills, projects, and more. Invoke when any task benefits from knowing who the user is.

Initialize and populate a mcp-me personal profile from public APIs. Use when the user needs to set up, generate, or refresh their mcp-me profile.

Use when asked to check, measure, rate, or compare the AI-harness maturity of any repository, project, or codebase not already in the corpus — clones or reads it, scans it with the exact pinned harness-score version this study uses, and reports the level,…

Use when adding a new repository to the study corpus — pins it to an exact commit, scans it, and regenerates results/ the same reproducible way every existing entry was added.

Use when adding or changing a Meeting Cost calculation rule, validation edge case, or domain formula in src/meeting-cost.js.

Map local dev topology before hardcoding localhost URLs or debugging API connectivity. Use when starting dev servers, configuring env vars, or when the agent assumes port 3000.

Run the unhappypath CLI to find missing loading, empty, error, and retry UI states, then fix findings and re-run until the score target is met.

Use when preparing or validating the live Harness Score presentation before speaking to an audience.

Research, write, optimize, validate, and publish specialist technical articles for DEV Community with exactly four relevant tags and a draft-first safety workflow. Use when creating, rewriting, reviewing, scheduling, or publishing DEV.to tutorials, project…