ngmeyer-skills

Audit recent work in a folder and produce a forward-looking self-improvement report. Reviews files modified in the past week, git activity, file-type distribution, and recurring task patterns; writes a 5-section weekly-setup-improvements.md with concrete updates for context files, ideas for new skills, workflow gaps to close, files to clean up, and what's working well enough to leave alone. Cross-platform; safe to schedule weekly via /schedule. Use when: 'weekly review', 'weekly self audit', 'improve my setup', 'what should I clean up', 'suggest new skills', 'self improvement loop', 'weekly setup improvements', or before a planning week.

Single-critic adversarial stress test of a known artifact — a PR, draft, spec, plan, code file, or argument. The reviewer actively tries to break it: edge cases, hidden assumptions, failure modes, logical inconsistencies, security gaps, scalability cliffs, surprising user behavior, counter-examples. Distinct from /council-review, which is for OPEN questions and decisions; this skill is for stress-testing a finished thing. Use when: 'adversarial review', 'red team this', 'find what is wrong', 'tell me why this is wrong', 'pre-mortem this', 'attack this', 'stress test', 'devil's advocate', 'try to break this', or before shipping any artifact where a missed edge case is expensive.

All-in-one skill for CLAUDE.md files. Two modes: `audit` finds drift (claimed facts no longer matching code), leaked secrets, duplicates, instruction-budget bloat, and prescriptive-vs-descriptive imbalance across all CLAUDE.md files in your projects. `improve` measures one CLAUDE.md against Anthropic's official best practices (200-line budget, removability test, emphasis tuning, 3-tier hierarchy) plus community-validated guidance, then proposes concrete rewrite diffs applied only after user approval. Default behavior auto-detects: in a project with a CLAUDE.md → improve mode; otherwise → audit all. Use when: 'audit claude.md', 'check claude md drift', 'lint CLAUDE.md', 'claude md audit', 'refresh instructions', 'improve CLAUDE.md', 'restructure CLAUDE.md', 'tune CLAUDE.md', 'apply CLAUDE.md best practices', 'is my CLAUDE.md good', 'CLAUDE.md is too long', 'rebalance CLAUDE.md', or quarterly as a hygiene check.

Audit a web codebase for security, performance, correctness, and refactoring improvements WITHOUT changing any outward-facing behavior. Fans out parallel read-only reviewers, scores findings on two axes (severity × confidence), suppresses predictable false positives, validates survivors with an INDEPENDENT wave (not self-recheck), classifies safe vs. gated, and writes a report. Applies only behavior-preserving fixes, and only on request. Use when: 'rigorous review', 'hardening audit', 'security and performance audit', 'internal audit', 'harden the codebase', 'audit for security/perf/refactoring', 'tech-debt audit', 'review this codebase without changing behavior'.

Recover lost Claude Code session context by merging duplicate project directories. Finds session/memory dirs under ~/.claude/projects/ that point at the same logical project from different cwd-encoded paths (e.g. /mnt/work/foo vs ~/Projects/foo cwd produces two separate namespaces). Unifies memory into the canonical dir, archives orphaned jsonl transcripts, and captures the lesson as a feedback memory so the split doesn't repeat. Use when: 'merge sessions', 'recover lost context', 'fix duplicate session dirs', 'session memory split', 'memory dir is empty but I added things', 'two project dirs', 'recover legacy memories from before a folder move', 'stale orphan memory namespace', or any time you find a populated memory dir at the "wrong" path and an empty one at the canonical path.