agentleFS
ai-analyst-labai-analyst-lab/ai-analyst/.claude/skills/resume-pipeline/SKILL.md

resume-pipeline

Skill304 starsChanged 2 months agoMITView on GitHub

Resume a specifically identified analysis using its verified run-local artifacts and controller state.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Resume the requested analysis

  1. Identify the exact run. Inspect question, inputs, plan and status. If several match, ask which one. A latest link does not select the user's intended work.
  2. Version 3 state uses helpers.pipeline.controller.Controller. Never overwrite or reinterpret legacy state as version 3. Offer a new run with explicitly selected, verified legacy artifacts while retaining the originals.
  3. For blocked approval gates, show evidence and request approval. Record it only after receiving it, with checkpoint, actor and reason. Local records are not authenticated identities.
  4. For failures, inspect the cause before retrying. Confirm an interrupted worker is no longer running. Never remove a lock while another controller is active.
  5. Run python -m helpers.pipeline.controller run EXACT_RUN_DIRECTORY, with --retry-failed only for an intentional retry. Code validates definition and artifact hashes and skips valid completed work. Changed definitions/artifacts require a new reviewed run; do not silently reuse stale work.
  6. Report the actual final status and outputs. Never manually change statuses or create a deck for a plan that did not request one.

Authentication, tool permissions and workflow approvals are separate requirements. See docs/PIPELINE-CONTROLLER.md for recovery and migration details.

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.