Turns work in Claude Code or GitHub Copilot CLI into reviewable learned-* skills or learning records. Opt-in hooks start a confined background review of redacted session transcripts on your own account, with staged file tools, a Learned notice and one-command undo. Off until .claude/learned-skills.json exists. Commits, a git sink and a disclosure filter are optional.
Plugin learned-skills from marketplace thornfield-plugins in karmaterminal/thornfield-plugins. Commands read from the repo's manifest — 3 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
learned-skillsUse when a "💾 Learned" notice arrives from the background skill review, when someone says undo after one, when enabling or tuning learned skills in Claude Code or GitHub Copilot CLI (.claude/learned-skills.json), when a learned-* skill misled you and needs a fix, or when deciding whether something
/learned-skills:learned-logLearned skills - show the last 40 lines of the background review log
/learned-skills:learned-reset-guardLearned skills - list open private-key guards, or clear one session's (logged)
/learned-skills:learned-review-nowLearned skills - run a background review now, in the foreground
/learned-skills:learned-statusLearned skills - show status (config, learned skills, next review)
/learned-skills:learned-undoLearned skills - undo the last learned change to one skill (learned-NAME)
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/on_stop.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/on_prompt.py"
Proves a bug's cause before you trust the fix. Claude pins the wanted behaviour in a failing test whose assertions never change, traces the code path and the git history (with git bisect where it can), applies the smallest fix, then shows that reverting only the fix brings the failure back. Instructions only: no hooks, servers or scripts, and it sends nothing anywhere.
1 skill
Lets an agent ask frond-alarm to phone figs, the Thornfield frond's human, and read what happened. A skill gives the one command for "I want figs here now", how to word the call, and the room @-mention for what can wait. A standard-library script files one request in the alarm's own format, with up to three questions for figs, and reads the outcome and figs's answers from what its worker wrote. The only credential is your GitHub token, and the alarm accepts only the callers it lists.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
6 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.