agentleFS
Sign inStart free
CipherNovaaCipherNovaa/agent-skills/skills/myos/scan/SKILL.md

scan

Skill0 starsChanged 12 days agoMITView on GitHub

Classify an image the user sends (handwritten notes / printed document / homework / a screenshot / a meme), confirm the read, then route it to the right place. Use for any photo/image, or the //scan command.

35 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use coverage, metrics and 9 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.
  • PydanticSkill

    coverage

    Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.

    Also in 4 projects that use this

  • GoogleSkill

    metrics

    Expertise in analyzing time-series repository health metrics, investigating root causes, and proposing proactive workflow improvements.

    Also in 3 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 5 projects that use this

  • anombyte93Skill

    discover

    Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.

    Also in 3 projects that use this

  • Google CloudSkill

    fix

    Plan a remediation strategy after a test failure.

    Also in 3 projects that use this

  • MicrosoftSkill

    init

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 32 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If you can't read it, or two types fit → ask, don't guess.

    line 28
  2. Very specific:

    Exactly ONE inbox: ALWAYS resolve it with python $MYOS_ENGINES/myos_paths.py get inbox — never hardcode, never invent Vault/Inbox or any …

    line 36

“Common” is measured: kept by at least 6 in 10 of the 32 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

scan

The single front door for an image. Classify → confirm → route. One image in, the right destination out — no wandering, no misfiling. Mirrors the bare-image behaviour in the agent's persona (when the user just drops a photo with no words), and is the //scan command.

Procedure

  1. Read the image (vision model) and classify it into ONE of:
    • handwritten notes / printed document / homework / curriculum → a clean note in the one Inbox (below).
    • a type with its own pipeline (a receipt, a book cover, …) → that pipeline's tool, if one is installed. If none is, treat it as a document.
    • a GIF / meme / reaction → it's a vibe, not a task. React in kind; don't file it.
  2. State your read and the action, and wait for a quick confirm ("Looks like lecture notes on recursion — transcribe to the Inbox? [y]"). Only act after the user confirms. If you can't read it, or two types fit → ask, don't guess.
  3. Route on confirm:
    • notes/doc/homework → OCR/transcribe it, lightly clean errors but keep the user's wording, then write to the inbox with write_file: <inbox>/<title>.md where <inbox> = python $MYOS_ENGINES/myos_paths.py get inbox.
  4. Verify the artifact exists and report the real path. Never say "filed" without it.

Pitfalls

  • Exactly ONE inbox. ALWAYS resolve it with python $MYOS_ENGINES/myos_paths.py get inbox — never hardcode, never invent Vault/Inbox or any other Inbox. Writing a second inbox is the exact bug this exists to prevent (and the janitor flags it as CRITICAL).
  • No Dataview / Templater in a filed note — knowledge notes must read fine as plain markdown (a small model writing query blocks it doesn't understand = an unreadable note).
  • Don't rewrite or "improve" the user's notes — transcribe + clean OCR only, preserve voice.
  • Confirm first. A wrong guess that acts is worse than a one-line "is this X?".

Verification

  • A new <inbox>/<title>.md exists (plain markdown, no Dataview), and the reply quotes its real path.
  • A routed type: the downstream tool's own ✅ line, relayed verbatim.

Cadence

On demand — any image the user sends, or //scan.

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