agentleFS
fabian-von-tiedemannfabian-von-tiedemann/research-harness-template/.agents/skills/close-out/SKILL.md

close-out

Skill1 starsChanged 2 months agoMITView on GitHub

Run the close-out check when an investigation or a working session ends, and before anything is shared outside the repo. Ends with the feedback question about the template.

4 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions4 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 4

    1. shady2k/skills★ 6same name
    2. AcKeskin/contexture★ 2same name
    3. life-itself/skills★ 2same name
    4. MatthewDelprado/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository3 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Harness: Run, in order:

    line 14
  2. Distinctive:

    Stop and report if any fails.

    line 21
  3. Distinctive:

    Never file without the researcher seeing the text.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 4 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

Close-out

You run the five checks in method/README.md, section "Close-out check", in order, and report deviations together with what you corrected.

Steps

  1. Decisions. Read the investigation README and the git log since the investigation started. List every decision that changed the repo's direction, method, scope or what leaves the repo. For each, add an entry to DECISIONS.md under today's date: what, why, which files it landed in. If there are none, say so.
  2. Carrier documents. For each decision, open the file that carries the rule (method/README.md, method/templates.md, knowledge/README.md, a skill) and confirm the change is there. If a rule, template or format changed, confirm there is a line under [Unreleased] in CHANGELOG.md. Fix what is missing.
  3. Harness. Run, in order:
    python3 -m harness check
    python3 -m harness validate
    python3 -m harness index > knowledge/INDEX.md
    python3 -m unittest discover -s tests
    Stop and report if any fails. Do not mark the investigation closed with a failing validate.
  4. Investigation index. Compare the row in investigations/README.md with the investigation README: status, outcome. Fix the row.
  5. Feedback. Ask the researcher: "Did the method, a template or the harness get in the way anywhere in this investigation? A rule that did not fit, a template heading you skipped, a command that did the wrong thing?" If yes, draft an issue using .github/ISSUE_TEMPLATE/method-gap.md, show it, and if the researcher agrees offer:
    gh issue create -R fabian-von-tiedemann/research-harness-template --title "<title>" --body-file <draft>
    Never file without the researcher seeing the text. Never include subject content or personal data in the issue.

Report: decisions written, corrections made, test results, and whether feedback was sent.

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.