agentleFS
ghvinashvilighvinashvili/specagent/.claude/skills/escalate/SKILL.md

escalate

Skill7 starsChanged 16 days agoApache-2.0View on GitHub

Ask the human in escalations/<NNN>.json and stop. Use when material conflicts or is missing, a tool fails twice or the brief is silent.

5 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

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

  • 0

    Common

    Most of the 5 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. Very specific:

    Write escalations/<NNN>.json following schemas/escalation.schema.json: stage, shard (from $HARNESS_SHARD, when set), question (one …

    line 10
  2. Distinctive:

    Stop. Do not continue on a guess.

    line 13

“Common” is measured: kept by at least 6 in 10 of the 5 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

Escalate

  1. Next id: ls $HARNESS_RUN_DIR/escalations, take the highest NNN and add one; start at 001. If $HARNESS_BLIND is 1 you cannot read or write that directory: write the same JSON as escalation.json in your stage directory ($HARNESS_STAGE_DIR) with "id": "000"; harness poll assigns the number and files it.
  2. Write escalations/<NNN>.json following schemas/escalation.schema.json: stage, shard (from $HARNESS_SHARD, when set), question (one sentence), context (where you saw it, with paths and quotes), options (two to four, each with its consequence), recommendation (or null), blocking: true, status: "open", answer: null.
  3. Rewrite result.json with status: "escalated" and the question in open_questions.
  4. Rewrite progress.md so that the step after the answer is explicit.
  5. Stop. Do not continue on a guess; the manager resumes you with the answer as your next message.

The Stop hook lets you stop when an escalation with status: open exists for your stage, or when result.json is valid and final (complete, escalated or failed); a partial result does not let you stop.

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.