Claude Skills by philoserf

Reviews Claude Code release notes and recommends config updates. Use when a new Claude Code version is released, after running /release-notes, after upgrading Claude Code, when asking "what changed", "what should I update", "review the changelog", "version bump", or "review the latest release". Covers settings.json, hooks, permissions, rules, skills, and CLAUDE.md.

Audits Claude Code skills, hooks, agents, and rules in a single pass — structural lint, quality scoring (1-5 across 6 weighted dimensions), and prioritized improvement recommendations. Use when reviewing, auditing, scoring, linting, improving, or validating any customization. Produces one sectioned report with pass/fail checks, per-dimension scores, weighted total, quality tier, and P1-P5 action items.

Audits and improves CLAUDE.md files by scanning repositories. Use when maintaining CLAUDE.md files, optimizing project instructions, or reviewing what project instructions should contain. Evaluates quality against templates, outputs scored reports, and applies targeted updates.

Reviews a codebase for bugs, design issues, and code cleanliness problems with specific file paths and line numbers. Use when auditing code quality, finding bugs, doing a code review, finding problems, or reviewing a project for issues. Creates issue files in `.issues/` directory.

Audits project dependencies for vulnerabilities, outdated packages, and license issues. Use when checking dependency health, running security audits, or reviewing package versions. Covers native audit tools, version freshness, and license compliance.

Runs an iterative review-and-fix loop on a git diff. Use when reviewing a staged or branch diff and fixing findings in place — presents findings by severity, lets you choose which to fix, applies fixes, and re-reviews. Max 3 iterations.

Copy edits prose while preserving voice and register. Use when asked to edit, copy edit, line edit, proofread, revise, polish, tighten, rewrite, or clean up essays, articles, drafts, or fiction. Flags wordiness, passive voice, clichés, hedging, and nominalizations with bracket markup or clean rewrites.

Publishes and manages Flowershow sites with the `fl` CLI (the Go-based successor to the deprecated `@flowershow/publish` npm package). Use when publishing a note or folder to Flowershow, syncing updates to an existing site, managing auth, listing or deleting sites, or installing/upgrading the CLI.

Runs Go code quality checks. Use when checking Go code quality, linting, running checks, validating Go code, or running go checks. Covers formatting with gofumpt, static analysis with go vet, and test execution with go test.

Interacts with Obsidian vaults via the Obsidian CLI to read, create, and manage notes, tasks, properties, tags, bookmarks, and templates. Use when working with an Obsidian vault from the command line, adding to daily notes, querying by tag or link, checking sync status, or developing and debugging Obsidian plugins and themes.

Validates an Obsidian plugin is ready to tag and ship. Use when tagging a release, cutting a version, publishing or shipping a plugin, running a pre-release check, or asking "are we ready to release?" Checks repo hygiene, CI status, docs, version sync, and build verification.

Executes the final release workflow for Obsidian plugins after obsidian-release-check passes. Use when tagging a release, publishing a version, or shipping an Obsidian plugin. Uses the prep-PR pattern — version bump, CHANGELOG, and walkthrough land in one reviewable PR; tag is applied to the merged commit.

Wraps up a session with two outputs — a sweep into the auto-memory system to preserve reusable insights for future Claude sessions, and a human-readable recap saved to the Obsidian notes vault. Use for retrospectives, debriefs, post-mortems, or end-of-session reflection.

Audits ~/.claude/skills/ for unused entries, duplicate names, missing descriptions, and the longest descriptions. Use when trimming the user-level skill set, asking which skills are unused, finding duplicates, or auditing skill hygiene.

Identifies, classifies, and prioritizes technical debt. Use when auditing technical debt, assessing code quality, analyzing maintenance burden, or asking what's slowing us down. Produces categorized inventory with severity rankings, remediation roadmap, and fix recommendations.

Runs TypeScript/JavaScript code quality checks. Use when checking TypeScript or JavaScript quality, linting, running tests, validating TypeScript code, or running TS/JS checks. Covers formatting and linting with biome, type checking with tsc, and test execution with bun test.

Reads source code and produces a linear, executable walkthrough document. Use when explaining how code works, creating code walkthroughs, onboarding to a project, or giving a code tour. Generates structured showboat documents with annotated code paths.