grafana-pathfinder-app

The full QC8 comment-quality catalog — eight bad comment shapes to delete with before/after examples, plus the keep-list of comments that earn their place. Load before writing or editing code comments, or when a review flags comment quality. AGENTS.md carries the one-line rule and the shape titles; this skill carries the worked examples.

Per-PR documentation-drift prevention. When a PR adds new code subsystems, scripts, skills, docs, plugin routes, feature flags, or changes architecture relationships, this skill produces the AGENTS.md, CLAUDE.md, and .cursor/rules/ updates needed in the same PR so agent guidance never falls behind the code. Use this on /review or directly before merge.

Security audit — frontend (F1-F6 rules from `.cursor/rules/frontend-security.mdc`), Go backend (URL allowlists, token handling, hardcoded secrets, unbounded reads), MCP HTTP transport (size / wallclock / concurrency caps, Zod-validated tool inputs), and dependency audit (`npm audit` high+critical, Go module advisories). Reports findings with concrete remediation per rule. Never edits source — the user applies fixes.

Routed PR review orchestrator. Load for `/review` command or any PR review task.

Generate a structured PR description from the current diff using `docs/design/CONCERNS.md` routing. Interviews the author for motivation before drafting. Produces canonical sections (Summary, What to look at, Why, How to verify, Breaking changes, Reversibility) tailored to change type. Outputs the draft for human review; can apply via `gh pr edit` after explicit confirmation. Pair with `/review` — this skill drafts, `/review` reviews.

Locate technical debt in a subsystem or architectural component of a codebase. Use when the user runs `/techdebt <subsystem>` or asks to audit a module for smells, duplication, prop drilling, dead code, or other debt patterns. Examples: "/techdebt src/auth", "find tech debt in components/docs-panel", "audit the interactive-engine for smells".

Orchestrate the pre-release flow for grafana-pathfinder-app — bump the version in package.json, draft a CHANGELOG entry (via the `changelog` skill), run `npm run check` and `npm run build`, then print the exact `git tag` command for the user to execute. Never creates or pushes the tag itself; tagging is a one-way door the user owns.

Draft a CHANGELOG.md entry from merged PRs since the last release tag. Categorizes by conventional-commit prefix (Added / Fixed / Chore / Security / Changed / Removed), rewrites PR titles into sentence-case narrative bullets with PR refs, and commits to the current branch without pushing. Use when preparing a release, or call this skill from `/release-prep`.

Detect translation gaps across the 21 locales under `src/locales/`. For keys present in `en-US` but missing from another locale, add the key with an empty string value (matching the runtime fallback to the en-US default). Emit a gap report (filled / empty / stale counts per locale + the list of newly stubbed keys). Never invents translations; translators fill the empty stubs later.

Fix a robustness bug from GitHub issues using worktrees, test-first development, and subagents.

Execute high-risk refactors of large or intertwined components per the High-Risk Refactor Guidelines wiki — investigation, phased planning, and atomic-commit execution with subagent fan-out and worktree isolation. Use when the user invokes /refactor-investigate, /refactor-plan, or /refactor-execute, or asks to refactor a large component, split a complex hook, decompose a singleton, extract from a monolith, or otherwise restructure intertwined code.

Optimise Grafana app plugin bundle size using React.lazy, Suspense, and webpack code splitting. Use when the user asks to reduce plugin bundle size, optimise module.js, add code splitting, improve initial plugin load performance, split plugin chunks, lazy load plugin pages, or help implement lazy loading in a Grafana app plugin. Triggers on phrases like "optimise plugin bundle size", "module.js is too large", "plugin is slow to load", "code split the plugin", "reduce initial JS payload", or "help me with Suspense in my plugin".

Periodic documentation maintenance audit. Finds orphaned docs, detects drift between .cursor/rules/ and docs/developer/, validates doc correctness against source code, tracks structural issues in a persistent backlog, and opens PRs to close highest-priority gaps per run. Use when the user asks to audit documentation, sync docs, or maintain the knowledge base.

Principal engineer level architecture design review and critique. Use when the user asks for design review, architecture feedback, design partnership, risk analysis of a design doc, or wants to drive ambiguity out of a plan. Never writes code; operates as a conversational design partner.

Run E2E CLI against a JSON guide to analyze edge cases and behavior. Use when the user wants to test a guide with the e2e CLI for learning purposes, study e2e failures, analyze screenshots, or investigate edge cases in the guide runner.