harden-task-file
Harden a manifest-dev task guidance file for one-shot quality — either /define''s quality-gate/Default set or figure-out''s probe set. Iterates: orthogonality…
Called by review-pr for each unresolved review thread it authored: judges from the thread, the author''s replies, and the current code whether the original concern is addressed, stale, or still standing, and returns exactly one disposition with a drafted reply where one is
$ npx -y skills add doodledood/manifest-dev --skill review-pr-thread-verify --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/review-pr-thread-verifyContext preview
The summary Claude sees to decide when to auto-load this skill.
Called by review-pr for each unresolved review thread it authored: judges from the thread, the author''s replies, and the current code whether the original concern is addressed, stale, or still standing, and returns exactly one disposition with a drafted reply where one is
name: review-pr-thread-verify description: 'Called by review-pr for each unresolved review thread it authored: judges from the thread, the author''s replies, and the current code whether the original concern is addressed, stale, or still standing, and returns exactly one disposition with a drafted reply where one is needed. Not for direct use.' user-invocable: false
Decide what has happened to one review finding since we posted it. The caller hands over everything; this skill judges and returns, and never posts, resolves, or edits anything itself.
**Receives.** The original finding (its anchor, body, the commit or head SHA it was reviewed at, and the concrete concern it raised); every author reply on the thread since our last message, plus every prior reply we posted there; the current code at the anchor with nearby context, and any commits since the original review that touched the relevant range; the full PR history (all comments, review threads, commit messages, the current PR description, our prior review and comment bodies); bundle context for each linked PR (diff, description, top-level conversation); and the caller's voice profile — its rules for how a posted comment reads — to apply to any reply drafted here.
**Judges.** Read the concrete concern first and hold it fixed: the question is whether *that* failure mode is gone, conceded, disproven, or still live — not whether the thread has been discussed. A code change counts only when it touches the relevant range and removes the failure mode; a reply counts only when a fair-minded human reviewer would concede it. Push back only on new signal — a new author reply or a code change — and stay on the specific point under contention; never repeat an argument already made on the thread.
**Returns exactly one disposition:**
**Return shape.** The disposition name, one short reason (the evidence: the commit, the reply, or the absence of either), and the drafted reply text when the disposition calls for one, written in the supplied voice profile.
Skills for agentic coding CLIs. They keep three things in your project instead of in your head: what it's becoming, what's worth doing next, and what done means here. The agent reads them, works against them, and checks the result before reporting it finished.
Harden a manifest-dev task guidance file for one-shot quality — either /define''s quality-gate/Default set or figure-out''s probe set. Iterates: orthogonality…
Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from…
Sync the prompt-engineering plugin from a local clone of claude-code-plugins into .claude/ so the repo is self-contained for isolated/web environments. Copies…
Regenerate the Codex distribution copy of the plugin skills and check it for drift. Run after changing anything under claude-plugins/*/skills. OpenCode and Pi…
Analyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project. Trigger terms: project overview, analyze…
Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR through CI, review threads, description…