agentleFS
Sign inStart free
yiyaw-labyiyaw-lab/agent-armor/snip/SKILL.md

snip

Skill1 starsChanged 5 months agoMITView on GitHub

Save a code/md snippet as a build-in-public bundle — source + freeze PNG + draft post caption — under ~/build-in-public/snippets/, with a disclosure-boundary and secrets check first.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    If $ARGUMENTS gives a file path (optionally :<start>-<end> line range), read exactly that.

    line 12
  2. Distinctive:

    If it describes something from this session ("the freeze command", "that skill file"), extract it from context.

    line 13
  3. Distinctive:

    Check the snippet against the project's public-disclosure-boundary memory.

    line 17
  4. Very specific:

    Create ~/build-in-public/snippets/<YYYY-MM-DD>_<slug>/ (date from your context) containing:

    line 21
  5. Distinctive:

    Keep the caption in the user's voice: builder-casual, concrete numbers and filenames over adjectives, no emoji walls.

    line 37

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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
<!-- mirror:transform — intentional divergence: the disclosure-boundary memory reference is genericized (private copy names a specific project's boundary memory) -->

You are saving a snippet for one of the user's build-in-public X posts.

Step 1 — Resolve the snippet

  • If $ARGUMENTS gives a file path (optionally :<start>-<end> line range), read exactly that.
  • If it describes something from this session ("the freeze command", "that skill file"), extract it from context.
  • Pick a kebab-case slug (≤4 words) from $ARGUMENTS or the content.

Step 2 — Safety gate (do this BEFORE writing anything)

  • Check the snippet against the project's public-disclosure-boundary memory. If the snippet leaks private material, STOP and tell the user what specifically crosses the line.
  • Scan for secrets: API keys (sk-ant, sk-, AKIA), tokens, .env contents, absolute paths revealing private project structure, emails. Redact with <REDACTED> and note it, or stop if redaction would gut the snippet.

Step 3 — Write the bundle

Create ~/build-in-public/snippets/<YYYY-MM-DD>_<slug>/ (date from your context) containing:

  • snippet.<ext> — the exact source, original extension.
  • snippet.png — freeze render. Wrap prose first; use the house style:
    fold -s -w 80 snippet.<ext> | freeze --config full \
  --theme catppuccin-mocha --language <lang> -o snippet.png
    If the snippet is >30 lines, ALSO render a hero.png cropped for small-screen legibility: ≤15 lines, wrapped at fold -s -w 60 so the type renders larger. Pick the densest, most structural lines (headers, bullets, a key code block) and cut prose-heavy passages — fewer words beats more context here. Say which lines you chose.
  • post.md — a draft X post: hook line, 2–4 short lines of substance (what it does + the one non-obvious detail), no hashtag spam. Note the char count and whether it needs Premium long-post. End with a Status: draft line.

Step 4 — Index + open

  • Append to ~/build-in-public/snippets/INDEX.md (create with a # Snippets header if missing): - [ ] <YYYY-MM-DD> <slug> — <one-line what it is> (<source file>) (The checkbox tracks posted/not-posted; never check it yourself.)
  • open the PNG so the user can review, and print the bundle path + draft post.

Keep the caption in the user's voice: builder-casual, concrete numbers and filenames over adjectives, no emoji walls.

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.

Check your setup, free