learn
Skill1 starsChanged 7 months agoApache-2.0View on GitHub
Makes the setup remember. Captures durable, project-specific learnings — user preferences, stack facts, conventions, fixes, recurring gaps — so every future session starts smarter (they're injected at SessionStart). Use when you discover something about how THIS project or user works that should persist. Triggers: 'remember that…', 'from now on…', 'we always/never…', or right after you learn a non-obvious project fact.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- HughYau/AcademicForgetheir own version, first seen Nov 8, 2026
- dimsedra/skillstheir own version, first seen Nov 8, 2026
- rajanrx/skillstheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-anydoc, add-clidash and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TomGranotSkilladd-anydoc
Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
Also in 5 projects that use this
- TomGranotSkill
add-clidash
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Also in 5 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 11 projects that use this
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
MicrosoftSkilladd-codex
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
Also in 6 projects that use this
- MicrosoftSkill
add-deltachat
Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
Also in 6 projects that use this
- +5 more from TomGranot
- +1 more from microsoft
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- garrytan/gstack★ 141ksame name
- rohitg00/ai-engineering-from-scratch★ 78ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- tigerless-labs/autoharness★ 11ksame name
- tw93/claude-health★ 7.5ksame name
- tw93/Waza★ 7.5ksame name
- nykooi1/vibe-wise★ 3.5ksame name
- HughYau/AcademicForge★ 2.6ksame name
185 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analyze-repoSkill
- augmentSkill
- code-reviewSkill
- context-guardSkill
- dep-checkSkill
- doctorSkill
- forgeSkill
- git-workflowSkill
- onboardingSkill
- security-scanSkill
- self-updateSkill
- test-runnerSkill
- tipsSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 1 is distinctive, and 3 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
After augment/forge/doctor change the setup, record what changed.
- Very specific: line 20
Write a single, specific sentence.
- Very specific: line 46
Keep each learning atomic and durable — not transient task state (that belongs in SESSION_STATE.md).
- Distinctive: line 48
Never store secrets or credentials as learnings.
“Common” is measured: kept by at least 6 in 10 of the 170 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Purpose
Turn one-off discoveries into permanent context. Mirrors how a good teammate stops needing to be re-told things. Storage is local, validated, and bounded — never networked.
When to use this
- The user states a preference or rule ("deploy via Fly, not Vercel"; "never touch the legacy/ dir"; "we use pnpm").
- You uncover a non-obvious project fact, a convention, or a fix worth keeping.
- After
augment/forge/doctorchange the setup, record what changed.
Steps
1. Distill ONE atomic learning
Write a single, specific sentence. Pick a category:
preference · stack · convention · workflow · fix · gap · fact.
2. Persist it (validated before it becomes durable)
echo '{"category":"preference","text":"User prefers TypeScript strict mode everywhere","tags":["ts"]}' \
| python3 .claude/engine/learn.py addThe store rejects empty/oversized text or a bad category (the "heal-safely" gate) and
de-dupes identical entries. It auto-renders .claude/memory/learnings.md.
3. Review when useful
python3 .claude/engine/learn.py listHow it comes back
The SessionStart hook runs learn.py inject and feeds learnings.md to Claude as
additional context at the start of every session — so the project keeps its memory
across sessions and compactions, with zero effort from the user.
Output
A new entry in .claude/memory/learnings.json + the refreshed learnings.md, and a
one-line confirmation of what was remembered.
Guardrails
- Keep each learning atomic and durable — not transient task state (that belongs in SESSION_STATE.md). One fact per entry.
- Never store secrets or credentials as learnings.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.