agentleFS
deanmikandeanmikan/ai-native-company-starter/.agents/skills/record-decision/SKILL.md

record-decision

Skill0 starsChanged 2 months agoMITView on GitHub

Record an important company or workspace choice as a numbered decision in work/decisions/ and update the pages it affects. Use when a choice has been made (or is being proposed) that is expensive to rediscover, likely to be questioned, or changes what other pages mean.

11 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use verify and handoff.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 3 projects that use this

  • MicrosoftSkill

    handoff

    Compact the current conversation into a handoff document for another agent to pick up.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 0 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Read work/decisions/README.md and list the folder to find the next sequential number.

    line 20
  2. Very specific:

    Check whether an existing decision covers the same ground.

    line 22
  3. Very specific:

    Create work/decisions/NNNN-short-name.md from templates/decision.md.

    line 26
  4. Very specific:

    Update affected pages so the workspace is consistent: the company or area page whose meaning changed, work/now.md if it removes a "next …

    line 38
  5. Very specific:

    Add the decision to the index in work/decisions/README.md.

    line 41
  6. Very specific:

    Run python3 scripts/lint.py and review the diff.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 8 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

Record a decision

When a decision deserves a record

  • It would take more than a few minutes to reconstruct why it was made.
  • Someone new will plausibly ask "why do we do it this way?"
  • It changes the meaning of an approved company or area page.
  • It rules something out (a market, a vendor, a practice).

Small reversible choices do not need a record. Put them in the relevant page or a learning.

Steps

  1. Read work/decisions/README.md and list the folder to find the next sequential number.
  2. Check whether an existing decision covers the same ground. If so, this is a superseding decision: write the new one, then set the old one to status: superseded and add a "Superseded by" link at the top of its Summary. Never rewrite the old text.
  3. Create work/decisions/NNNN-short-name.md from templates/decision.md.
  4. Fill every section:
    • Summary: the choice in one or two sentences.
    • Context: what prompted it, with sources.
    • Decision: what is chosen, precisely enough to act on.
    • Alternatives considered: each with the reason it lost. Include "do nothing" when relevant.
    • Consequences: benefits, costs, risks, and how reversible it is.
    • Revisit when: the observable conditions that would reopen it.
  5. Set owner to the person accountable for the decision, status: draft unless that owner has explicitly approved it in this conversation, and review_by to when the "Revisit when" conditions should be checked.
  6. Update affected pages so the workspace is consistent: the company or area page whose meaning changed, work/now.md if it removes a "next decision", the project page that produced it.
  7. Add the decision to the index in work/decisions/README.md.
  8. Run python3 scripts/lint.py and review the diff.

Authority

An agent may draft any decision. Decisions about strategy, policy, legal or financial commitments, personnel, or customer promises are approved only by the accountable human. Say clearly in your report which state the record is in.

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.