agentleFS
serhiilenivserhiileniv/ccs/skills/learn/SKILL.md

learn

Skill0 starsChanged 10 days agoMITView on GitHub

Turn this session's lessons into edits to the ccs skills themselves, then commit on approval.

195 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • TomGranotSkill

    add-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

  • seek888Skill

    open-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-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-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

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 169 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If $ARGUMENTS is given, that is the lesson.

    line 11
  2. Very specific:

    Never write memory files, and never edit ~/.claude/CLAUDE.md.

    line 24
  3. Very specific:

    Never edit ~/.claude/plugins/cache — it is overwritten on update.

    line 36
  4. Very specific:

    Every skill carries the same ## Writing and ## Report blocks.

    line 47

“Common” is measured: kept by at least 6 in 10 of the 169 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/ccs:learn

The skills get better with use. This turns what a session taught into edits to them. If $ARGUMENTS is given, that is the lesson.

Step 1 — find lessons

A lesson is one of:

  • a user correction a ccs skill should have prevented
  • a step that was skipped or misread because its wording allowed it
  • a rule that proved wrong
  • a friction shared by ≥2 reports in .ccs/reports/ with learned: false, or one report plus a user correction. One-off friction is not a lesson.

Project facts and one-off preferences are not lessons — the harness memory holds those. Never write memory files, and never edit ~/.claude/CLAUDE.md.

Step 2 — map each to one skill

Each lesson goes to one skill in skills/. No skill fits → report it, don't edit, don't scaffold a new one.

Step 3 — locate the source

$CCS_REPO, else ~/Projects/ccsensei. It must be a git checkout whose origin is serhiileniv/ccsensei. Otherwise print the proposed diff and stop.

Never edit ~/.claude/plugins/cache — it is overwritten on update.

Step 4 — edit

  • Tree dirty → stop and say so.
  • Branch learn/<slug> off main.
  • Smallest change to that skill's SKILL.md or supporting file. Tighten an existing line before adding one.

Step 5 — drift

Every skill carries the same ## Writing and ## Report blocks. If any differs from the one in skills/spec/SKILL.md, make it match in the same diff.

Step 6 — gate

Show the diff, then one line per lesson: what happened → what changed. Stop.

On approval, commit on the branch, then set learned: <short sha> on the reports that fed it. Never delete reports. Never push or open a PR.

Nothing qualified → say so and change nothing. An empty run beats filler.

Writing

One line where one line does. Answer first. State the fact, not the story behind it — no narrating what was tried, no paragraph restating the line above. Two things always stay: why a non-obvious decision was made, and what a check cannot do. Caveats and risks still get said, one line each.

Outcome: success = edit committed · partial = edit shown, not approved · failed = nothing qualified.

Report

Last step, every run, whatever the outcome: write .ccs/reports/<skill>/<YYYY-MM-DD>-<slug>.md at the repo root, and add .ccs/ to .git/info/exclude if missing. One line per field, no secrets, tokens or customer data. Print the path.

---
skill: <skill>
date: <YYYY-MM-DD>
repo: <owner/name>
target: <argument, one line>
outcome: success | partial | failed
learned: false
---

Used: <tools, CLIs, MCPs, files that did the work>
Found: <the result, one or two lines>
Friction: <what slowed or blocked it; a user correction; "none">

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.