agentleFS
Sign inStart free
TheAstroByteTheAstroByte/astrobyte-agent-skills/skills/astrobyte-show-work/SKILL.md

astrobyte-show-work

Skill1 starsChanged 14 days agoMITView on GitHub

Keep a compact, reviewable decision trail for experiments, unattended runs, migrations, evaluations, or multi-phase work. Use when a reviewer will need to understand what changed, why, what evidence was observed, and what was accepted or rejected.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Create .astrobyte/decisions.tsv unless the project defines another location.

    line 10
  2. Very specific:

    Use accepted, rejected, inconclusive, or blocked as status.

    line 20
  3. Distinctive:

    Keep secrets, tokens, personal data, and raw sensitive inputs out of the log.

    line 22
  4. Distinctive:

    Commit the trail only when it is part of the review or reproducibility contract.

    line 23
  5. Distinctive:

    Before ending, ensure the final row identifies the current state and next safe action.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Astrobyte show work

Create .astrobyte/decisions.tsv unless the project defines another location. Use one row per decision:

timestamp\tphase\thypothesis_or_choice\tevidence\taction\tresult\tstatus\tartifact

Rules:

  • Record decisions, not routine commands.
  • Link to configs, commits, runs, traces, metrics, tests, or screenshots instead of pasting bulk output.
  • Use accepted, rejected, inconclusive, or blocked as status.
  • Record failed and rejected work when it prevents repetition.
  • Keep secrets, tokens, personal data, and raw sensitive inputs out of the log.
  • Commit the trail only when it is part of the review or reproducibility contract.

Before ending, ensure the final row identifies the current state and next safe action. The trail is complete when another agent can explain the decision sequence without reading the full transcript.

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