agentleFS
rgoerwitrgoerwit/ai-investment-agent/.agents/skills/run-pipeline/SKILL.md

run-pipeline

Skill71 starsChanged 36 days agoMITView on GitHub

Run, resume, audit, or interpret the repository's two-stage equity-screening pipeline, including Stage-1 quick BUY lists, Stage-2 full reports, reuse, and failures.

6 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

4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    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:

    Read the relevant script paths first.

    line 12
  2. Very specific:

    Verify state from the dated BUY list, full reports (no _quick suffix), stage summary, and any failure/timeout records in scratch/.

    line 17
  3. Distinctive:

    Read the defaults from their owners, not copied values in guidance.

    line 26
  4. Distinctive:

    When changing this workflow, inspect reuse, completeness, watchdog, failure, and marker paths together, then run focused pipeline tests and …

    line 31

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

Run or interpret the screening pipeline

scripts/run_pipeline.sh owns the two stages: quick Stage 1 writes the dated BUY list; full Stage 2 consumes it. Same-mode reuse means quick reports never satisfy Stage 2, and reconciliation treats quick BUYs as non-investable.

  1. Read the relevant script paths first; confirm start stage, date, freshness, strictness, and forced reuse behavior.
  2. Report Stage-1 BUY-list count separately from Stage-2 attempted, reused, completed, and failed work. results/.pipeline_last_run.json records only the Stage-1 BUY-list count.
  3. Verify state from the dated BUY list, full reports (no _quick suffix), stage summary, and any failure/timeout records in scratch/.
  4. Require a current, publishable full report for a purchase. On interruption, state the verified status and resume the appropriate stage.

The per-ticker timeout settings feed scripts/pipeline_signals.sh, which passes an absolute epoch deadline to the child. src/llm_runtime/run_deadline.py translates it to a monotonic analysis deadline with a publication reserve; src/main.py binds it around analysis rather than final rendering, persistence or shutdown. Read the defaults from their owners, not copied values in guidance. Do not inject an artificial pipeline deadline into a manual run. Distinguish budget admission failure from watchdog signals and exit records; a truncated retry ladder is a bounded-work diagnostic, not a promise of completion or evidence of provider failure.

When changing this workflow, inspect reuse, completeness, watchdog, failure, and marker paths together, then run focused pipeline tests and static checks.

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.