agentleFS
Sign inStart free
AkkuAkku/stem/.claude/skills/alignment/SKILL.md

alignment

Skill1 starsChanged 14 days agoMITView on GitHub

Short, interruptible interview that builds a shared understanding before planning - one question at a time, each with a recommended answer, walking the open decisions in dependency order. Use for unclear or new features, before a large task, when output surprised the user, or optionally during setup.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. raphaelsalaja/skills★ 62same name
    2. baizhine999/leader-skills★ 8same name
    3. sanmidable/skills★ 2same 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 repository9 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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:

    Stop: when no open decision could change the plan materially, when the budget is used, or when the user says stop.

    line 13
  2. Very specific:

    If a step did not fit or you deviated from it: Learning: skill alignment: <what> -> <change> in the task notes (R-LEARNING).

    line 17

≈ “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

Design alignment ("grill", small and stoppable)

Rules: R-CONCEPT (product/UI direction), R-DESIGN, R-AUTONOMY (do not invent product decisions).

  1. Scope the budget first, tell the user: small change 2-4 questions; feature 5-12; new product 10-20 in rounds with a pause in between. Say "stop any time; for the rest I decide and write down my assumptions".
  2. Explore before asking: whatever the repository, vision doc, glossary (docs/GLOSSARY.md if it exists) or docs/ARCHITECTURE.md already answers, do not ask.
  3. One question at a time, in dependency order (a decision others depend on comes first). Each question: why it matters in one sentence, 2-3 options, your recommendation. Questions the user can hardly judge: decide yourself and record the assumption.
  4. Stop when no open decision could change the plan materially, when the budget is used, or when the user says stop. Then list the assumptions you made.
  5. Write the result down where it lives (one place): vision doc or PRD (backlog doc), or acceptance criteria in the tasks, with date; new domain terms into docs/GLOSSARY.md if the project has one. Only then plan and create tasks.
  6. Offer a batch if the resulting tasks are related (R-BATCHING).

If a step did not fit or you deviated from it: Learning: skill alignment: <what> -> <change> in the task notes (R-LEARNING).

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