attunehq/nudge/nudge-learnings
Claude Code and agent skill by attunehq/nudge
- community
Checking that the SKILL.md file is still in the repository.
Use during repo debugging to search `.nudge/learned` before investigating, apply relevant notes, and record durable fixes with `nudge learn add`.
Install
npx vskill@latest install attunehq/nudge/nudge-learningsSKILL.md
Nudge Learnings
Purpose
Nudge learnings are repo-local debugging memory, not broad agent memory. They live in Git with the repo, so each branch or worktree only sees the notes present in that checkout. Use this skill proactively when a repo-specific failure might already have a recorded fix, and after solving a durable repo-specific issue that future agents should not rediscover.
When to use
- You are debugging a failing command, test, build, integration, dependency,
local environment, or toolchain behavior in a repo with .nudge/learned.
- Nudge surfaces learned repo context.
- The user asks to search, list, record, or update Nudge learnings.
- You fixed a repo-specific issue that another agent could plausibly hit again.
Do not record generic programming advice, broad personal preferences, secrets, credentials, or one-off observations that are unlikely to recur.
Workflow
- If
.nudge/learnedexists, search before deep investigation:
- Use concrete symptoms, command names, package names, paths, tools, and
copied error fragments.
- Prefer several focused searches over one vague query.
- If no learning matches, continue normal debugging.
- If Nudge already surfaced a note, read the cited
.nudge/learned/*.mdfile. - Apply a note only when its symptoms, environment, and fix match the current
task. If it does not match, say why and keep investigating.
- After fixing a durable repo-specific issue, record a concise note with
nudge learn add and verify it with nudge learn search or nudge learn list.
Commands
Note Shape
References
references/learnings.md: choosing retrieval mode and recording notes.references/learnings-bm25.md: BM25 search behavior and search phrasing.references/learnings-embeddings.md: hybrid local embedding behavior.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/nudge/skills/nudge-learnings/SKILL.md
Popularity
- Repository stars
- 83
- Repository forks
- 5
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 8 Nov 2026, 1 h ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/attunehq/nudge/nudge-learnings)