Skills that improve other skills — session reflection, friction logging, and HITL-gated SKILL.md evolution.
Read accumulated session logs for a skill, synthesize numbered improvement proposals with rationale and session evidence, collect conversational HITL approval, apply accepted changes to the SKILL.md, bump the patch version, and write a changelog entry. Use when you have enough session logs and are ready to improve a skill. Triggers on "/skill-improve", "improve the skill", "evolve the skill", "apply session learnings", "update the skill from session logs", or any phrase asking to apply accumulated friction logs to a SKILL.md.
Capture a friction log immediately after finishing a skill session — what was improvised, what the user corrected, what edge cases the skill missed, and what changes would help. Writes a structured session log to ~/.claude/skill-sessions/<plugin>/sessions/<skill-name>/ so it can be read by the evolver from the skills repo later. Works in any project, not just the skills repo. Use whenever you've just finished running a skill and want to capture what happened while the session is fresh. Triggers on "/skill-reflect", "reflect on this session", "log this session", "write a session log", "capture skill friction", or any phrase asking to record what happened during a skill run.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub mvdmakesthings/skills --plugin metaRefinement-time test planning: reads a Linear issue's acceptance criteria and the repo's test conventions, then drafts a layer-aware test plan — per-AC scenarios tagged with a test layer and an expected result, plus auth roles, fixtures, visual states, and regression watch areas — and after your approval attaches it to the ticket as <issue-id>-test-plan.md for the qa skill to execute against.
Domain-expert personas that drop into any project and work with its conventions: a Postgres-first DBA (/dba) for health audits, schema design, index/bloat cleanup, slow-query diagnosis, and live incident investigation.
Linear-driven planning→QA flow: PRDs, issue breakdown, plan grilling, design mockups, test planning, QA execution, and post-incident reports. Bundles the to-prd, to-issues, grill-with-docs, plan-design, plan-qa, qa, and pir skills.
Console-native billable hours tracker with git-versioned plaintext ledger.
Writing toolkit: humanize AI-sounding prose (/writing:human) and a storytelling coach for pitches, talks, and memos. Bundles the human-voice-writer and storyteller-guidance skills.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions
Marketing skills for AI agents — conversion optimization, copywriting, SEO, paid ads, ad creative, and growth
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.