agentleFS
qyndexqyndex/claude-init/.claude/skills/analyze/SKILL.md

analyze

Skill2 starsChanged 5 months agoMITView on GitHub

Cross-check spec, plan, and tasks for consistency. Phase 4.5 of the eight-phase workflow. Catches scope drift, missing acceptance criteria, dependency cycles. Modeled on github/spec-kit /speckit.analyze. Run after /tasks, before /implement.

70 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use revise, write and 7 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.
  • stormlightlabsSkill

    revise

    Address review comments on an open pull request and push the fixes. Use for /edit, /revise, or when asked to respond to review feedback on a PR number.

    Also in 3 projects that use this

  • DockerSkill

    write

    Write or edit reader-facing technical prose for immediate comprehension. Use for documentation, PR titles and descriptions, release notes, design documents, user-facing explanations, and substantive comments. Also use when asked to make writing clearer, more natural, less AI-generated, or easier to read. For documentation fixes, handles edits, formatting, self-review, and commits after research identifies what to change. Do not use for code-only tasks with no prose deliverable.

    Also in 6 projects that use this

  • H-mmerSkill

    submit

    Draft and submit a vulnerability report to the bug bounty platform. Reads scope.yaml for platform/program, uses brain + findings for content. Always drafts first for review.

    Also in 3 projects that use this

  • GoogleSkill

    quality

    Evaluates whether a GitHub issue is spam, empty, needs more information, or is OK to proceed.

    Also in 3 projects that use this

  • ArvorCoSkill

    checklist

    Generate quality validation checklist from spec, plan, and tasks. Use after creating tasks. Triggers on: create checklist, quality checklist, validation checklist.

    Also in 3 projects that use this

  • JosBen74Skill

    osint

    OSINT-sökning och informationsinhämtning från öppna källor för Länsstyrelsen VG

    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, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 60 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

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

    Read the spec (specs/active/<id>-<slug>.md).

    line 16
  2. Very specific:

    Read the plan (plans/active/<id>-<slug>.md).

    line 17
  3. Very specific:

    Read the tasks in tasks/TASKS.md filtered by spec:<id>.

    line 18
  4. Distinctive:

    Run the consistency checklist (below).

    line 19
  5. Very specific:

    Write .claude/state/analyze-<id>.json with exactly:

    line 23
  6. Distinctive:

    After save: post the summary to the user.

    line 67

“Common” is measured: kept by at least 6 in 10 of the 60 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

Analyze

Cross-artifact consistency check. Catch drift before it becomes code.

Process

  1. Read the spec (specs/active/<id>-<slug>.md).
  2. Read the plan (plans/active/<id>-<slug>.md).
  3. Read the tasks in tasks/TASKS.md filtered by spec:<id>.
  4. Run the consistency checklist (below).
  5. Report findings, severity-tagged.
  6. Write the machine marker (e2e-audit spec-pipeline-1 — this is what makes the gate real; without it next-task.sh/workflow-state.sh see the spec as unanalyzed): Write .claude/state/analyze-<id>.json with exactly:
    {"verdict": "PASS|BLOCK", "blockers": ["<each BLOCKER finding>"], "date": "<ISO>"}
    <id> is the numeric spec id (e.g. analyze-042.json). Re-running /analyze overwrites the marker — verdict reflects the LATEST run.
  7. Block /implement if any blockers — the marker's verdict: BLOCK is enforced by next-task.sh --require-analyze (loop path), not just by this prose.

Consistency checks

  • Every spec acceptance criterion has at least one task that exercises it.
  • Every plan component is implemented by at least one task.
  • No task references a file outside the plan's scope.
  • No cyclic dependencies in the task DAG.
  • Every task's accept: command is syntactically valid (no obvious typos).
  • All declared dependencies (packages, services, MCP servers) appear in install/setup tasks.
  • Spec, plan, and tasks share the same id namespace.
  • No open [OQ] items in the spec.
  • Phase boundaries align — every plan phase has tasks; no orphan tasks.
  • Risks in the plan have mitigation tasks or explicit acceptance of the risk.
  • Backwards-compat constraints from the spec appear as tests.

Output

# Analysis — feature <id> — <date>

## Coverage
- Spec criteria with tasks: 8/8 ✓
- Plan components with tasks: 6/6 ✓
- Tasks with accept commands: 12/12 ✓

## Gaps
- BLOCKER: Acceptance criterion "rate limit 100 req/min" has no task.
- HIGH: Plan mentions `redis-rate-limiter` but no install task.

## Cycles
- None ✓

## Verdict
BLOCK — 1 blocker, 1 high. Address before /implement.

After save: post the summary to the user. If green, "Ready for /implement." If red, list the gaps.

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.