agentleFS
mauricio-moralesmauricio-morales/llm-wiki/.claude/skills/speckit-clarify/SKILL.md

speckit-clarify

Skill0 starsChanged 8 days agoLicence not identifiedView on GitHub

Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.

133 other projects use a version of this, 123 of them edited; 99 of 123 edited versions we compared changed its rules; 9 new projects in the last 4 weeks, against 12 the 4 before.

How people change it

99 of 123 edited versions changed its rules, and some changes recur.

Of the 123 edited versions we compared: 11 keep every rule, 13 are an older text, 99 made changes of their own.

Not in older versions

  1. When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.missing from 12 of 13
  2. Write the updated spec back to FEATURE_SPEC.missing from 1 of 13
  3. If any Outstanding or Deferred remain, recommend whether to proceed to /speckit-plan or run /speckit-clarify again later post-plan.missing from 1 of 13
  4. Check if .specify/extensions.yml exists in the project root.missing from 1 of 13
  5. If it exists, read it and look for entries under the hooks.before_clarify keymissing from 1 of 13
  6. If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normallymissing from 1 of 13
  7. If the hook has no condition field, or it is null/empty, treat the hook as executablemissing from 1 of 13
  8. If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementationmissing from 1 of 13

Rules people drop

  1. If the YAML cannot be parsed or is invalid, skip hook checking silently and continue normallydropped by 36 of 99
  2. When constructing slash commands from hook command names, replace dots (.) with hyphens (-). For example, speckit.git.commit → /speckit-git-commit.dropped by 3 of 99
  3. Check if .specify/extensions.yml exists in the project root.dropped by 2 of 99
  4. If it exists, read it and look for entries under the hooks.before_clarify keydropped by 2 of 99
  5. If the hook has no condition field, or it is null/empty, treat the hook as executabledropped by 2 of 99
  6. If the hook defines a non-empty condition, skip the hook and leave condition evaluation to the HookExecutor implementationdropped by 2 of 99
  7. If no hooks are registered or .specify/extensions.yml does not exist, skip silentlydropped by 2 of 99

Rules people add

  1. Check if FEATURE_DIR/checklists/requirements.md exists.added by 96 of 99
  2. If it does NOT exist, skip this step silently.added by 96 of 99
  3. Read the checklist file.added by 96 of 99
  4. If the item now passes and was unchecked: change [ ] to [x].added by 96 of 99
  5. If the state is unchanged: leave the marker as-is (preserve existing case to avoid cosmetic diffs).added by 96 of 99
  6. NEVER use a topic label, section heading, or requirement id as the question itself. For example, Acceptance device/runtime matrix (FR-023) is INVALID — it is a label, not a question.added by 66 of 99
  7. After the ?, the only permitted suffix is an optional parenthesized requirement/question id. Exact format: **Question:** <interrogative>? or **Question:** <interrogative>? (FR-023). …added by 66 of 99
  8. Use everyday wording; introduce jargon only if defined in the same sentence. Self-check: a reader who does not know Spec Kit must be able to answer from the Question line alone. Terse is fine; cryptic labels are not.added by 66 of 99

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Cooling: 9 new projects took it in the last 4 weeks, 0.8× the 4 weeks before.

Week of Sep 20: 3 new projectsWeek of Sep 27: 3 new projectsWeek of Oct 4: 2 new projectsWeek of Oct 11: 4 new projectsWeek of Oct 18: 2 new projectsWeek of Oct 25: 2 new projectsWeek of Nov 1: 1 new projectWeek of Nov 8: 4 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read.

Most recently taken up by

Used with

Projects with it also use speckit-agent-context-update, speckit-baseline and 5 more.

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

    speckit-agent-context-update

    Refresh the managed Spec Kit section in coding agent context file(s)

    Also in 13 projects that use this

  • patterson-agentsSkill

    speckit-baseline

    Generate feature specifications by analyzing existing source code.

    Also in 3 projects that use this

  • patterson-agentsSkill

    claude-command-converter

    Convert Claude Code commands (.claude/commands/*.md) to standard Agent Skills (skills/*/SKILL.md). Use when migrating slash commands to portable skill format, creating skills from existing commands, or standardizing command definitions across AI runtimes.

    Also in 3 projects that use this

  • arkanSkill

    review-animations

    Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    agentic-workflows

    Route gh-aw workflow design/create/debug/upgrade requests to the right prompts.

    Also in 3 projects that use this

  • VercelSkill

    emil-design-eng

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.

    Also in 3 projects that use this

The file

Show its rules and text

We split this skill into the rules it gives an agent

32 rules. 19 are common, 0 are distinctive, and 13 are very specific to this project.

  • 19

    Common

    Most of the 123 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 13

    Very specific

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

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 123 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.

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.