agentleFS
Sign inStart free
ryanmacleanryanmaclean/skills/paperclip/SKILL.md

paperclip

Skill1 starsChanged 52 days agoMITView on GitHub

Operate Paperclip companies and agents safely and deterministically. Use when assigning work, unblocking heartbeat loops, repairing stale in_progress issues, and standardizing API command patterns.

  • Reads credentials

12 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 5

    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. Distinctive:

    Use this skill for Paperclip operations work.

    line 8
  2. Very specific:

    Prefer wrapper script when available: $AGENT_HOME/scripts/paperclip_api.sh.

    line 12
  3. Very specific:

    When issues stay in_progress without active runs:

    line 25
  4. Very specific:

    If no active run and no recent progress, patch to blocked or todo with reason.

    line 28
  5. Distinctive:

    Add exact unblock action (command, credential, or acceptance criteria).

    line 29
  6. Distinctive:

    Do not start interactive auth inside agent heartbeats.

    line 33
  7. Very specific:

    Prefer preflight checks and deterministic env injection (adapterConfig.env).

    line 34
  8. Distinctive:

    If credentials are missing, fail fast with a clear blocked update.

    line 35
  9. Distinctive:

    Every run update should include:

    line 39

“Common” is measured: kept by at least 6 in 10 of the 11 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

paperclip

Use this skill for Paperclip operations work.

API command discipline

  • Prefer wrapper script when available: $AGENT_HOME/scripts/paperclip_api.sh.
  • For mutating requests, include X-Paperclip-Run-Id when run context exists.
  • Build JSON with jq -n; avoid hand-built JSON strings.

Heartbeat-safe task handling

  1. Get assigned issues (todo,in_progress,blocked) for current agent.
  2. Checkout issue once; if HTTP 409, do not retry.
  3. Work only assigned scope.
  4. Patch issue status with concise evidence comment.

Stale in_progress recovery

When issues stay in_progress without active runs:

  1. Query recent runs for assignee.
  2. If no active run and no recent progress, patch to blocked or todo with reason.
  3. Add exact unblock action (command, credential, or acceptance criteria).

Auth + Paperclip interaction

  • Do not start interactive auth inside agent heartbeats.
  • Prefer preflight checks and deterministic env injection (adapterConfig.env).
  • If credentials are missing, fail fast with a clear blocked update.

Comment quality

Every run update should include:

  • status line (done, blocked, or in_progress)
  • what was executed
  • concrete evidence (IDs, command result summary)
  • next action if blocked

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