agentleFS
felipefontourafelipefontoura/pi-sdd-kit/skills/sdd-status/SKILL.md

sdd-status

Skill36 starsChanged 6 months agoMITView on GitHub

Explicit command-style skill for inspecting .ai/sdd state and recommending the next safe action. Use only when the user explicitly asks for SDD status, progress, blockers, readiness, or next action. Do not auto-load for general SDD work; do not create specs or implement code.

We split this skill into the rules it gives an agent

16 rules. About 0 are common, 7 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

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

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

    Use package-level templates/sdd-index.md as the dashboard reference when useful.

    line 19
  2. Very specific:

    Treat .ai/strategy/handoff/strategy-brief.md as optional upstream context and .ai/sdd/handoff/sdd-brief.md as optional downstream handoff …

    line 21
  3. Very specific:

    Check whether .ai/sdd/ exists.

    line 24
  4. Very specific:

    Check .ai/sdd/INDEX.md if present.

    line 25
  5. Very specific:

    Check .ai/strategy/handoff/strategy-brief.md if present and report it as an available upstream handoff.

    line 27
  6. Very specific:

    Check .ai/sdd/handoff/sdd-brief.md if present and report its readiness/status summary.

    line 28
  7. Distinctive:

    Do not modify files.

    line 48
  8. Distinctive:

    If an index or status appears stale, recommend an update instead of editing it.

    line 50
  9. Distinctive:

    Prefer short dashboards over long commentary.

    line 92
  10. Very specific:

    Do not infer approvals from file existence.

    line 93
  11. Very specific:

    When a strategy handoff exists but no SDD artifacts exist, recommend /skill:sdd-plan or /skill:sdd-prd depending on scope.

    line 96
  12. Very specific:

    When tasks are approved but sdd-brief.md is missing or stale, recommend refreshing the SDD handoff.

    line 97
  13. Distinctive:

    Do not create, edit, or delete files in this skill.

    line 101
  14. Distinctive:

    Do not approve drafts.

    line 102
  15. Distinctive:

    Do not implement code.

    line 103
  16. Distinctive:

    Do not run expensive verification commands unless the user explicitly asks for a health check.

    line 104

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

SDD Status

Inspect the SDD workspace and report current progress, blockers, and next actions.

Purpose

STATUS gives operational visibility across .ai/sdd/ without changing artifacts. It helps the user understand what exists, what is approved, what is still draft, what is blocked, and what the next safe SDD step should be. Treat it as an explicit utility command, not as a semantic auto-loaded skill for ordinary SDD authoring.

Workflow

  1. Load the SDD reference.
    • Read ../_shared/references/sdd-practical.md.
    • Apply the Language Policy: respond and write artifacts in the user's initial chat language while keeping skill instructions and templates in EN-US.
    • Use package-level templates/sdd-index.md as the dashboard reference when useful.
    • Load relevant .ai/steering/*.md files only if they help explain project context; do not summarize steering unless useful.
    • Treat .ai/strategy/handoff/strategy-brief.md as optional upstream context and .ai/sdd/handoff/sdd-brief.md as optional downstream handoff output.
  2. Inspect the workspace.
    • Check whether .ai/sdd/ exists.
    • Check .ai/sdd/INDEX.md if present.
    • Check .ai/sdd/PLAN.md if present.
    • Check .ai/strategy/handoff/strategy-brief.md if present and report it as an available upstream handoff.
    • Check .ai/sdd/handoff/sdd-brief.md if present and report its readiness/status summary.
    • List .ai/sdd/ideas/*.md if present.
    • List .ai/sdd/specs/*/ directories.
    • For each spec directory, read .status when present.
    • For each spec directory, note presence of requirements.md, design.md, tasks.md, review.md, and decisions.md.
    • Compute the next feature ID from actual spec directories using the shared Feature Workspace Identity algorithm; report it as informational only.
    • Flag duplicate numeric prefixes, non-canonical spec directory names, missing .status, and invalid .status values.
  3. Assess gates.
    • Identify specs that are ready for PRD, SPEC, TASKS, EXEC, or REVIEW.
    • Identify specs blocked by missing artifacts, draft statuses, or missing approvals.
    • Identify implementation specs with incomplete tasks when tasks.md exists.
    • Identify specs whose .status conflicts with existing artifacts.
  4. Produce a concise dashboard.
    • Group by Upstream Handoffs, Plan, Ideas, Specs, Handoff Output, In Progress, Review Ready, and Blocked.
    • Include exact paths for important artifacts.
    • Include the current .status value for each spec.
    • Recommend one or more next commands such as /skill:sdd-prd, /skill:sdd-spec, /skill:sdd-tasks, /skill:sdd-exec, or /skill:sdd-review.
  5. Do not modify files.
    • STATUS is read-only.
    • If an index or status appears stale, recommend an update instead of editing it.

Output Format

SDD STATUS

Workspace: .ai/sdd
Steering: .ai/steering present/missing

Upstream Handoffs:
- .ai/strategy/handoff/strategy-brief.md: present/missing

Plan:
- [missing/draft/approved] .ai/sdd/PLAN.md

Ideas:
- 001-name — idea:captured — .ai/sdd/ideas/001-name.md

Specs:
- 001-feature — requirements:approved
  Artifacts: requirements.md yes, design.md no, tasks.md no, review.md no
  Next: /skill:sdd-spec

Feature Workspace:
- Next feature ID: 002
- Numbering source: filesystem `.ai/sdd/specs/*/`
- Issues: none / [duplicate prefix, invalid status, non-canonical directory]

Handoff Output:
- .ai/sdd/handoff/sdd-brief.md: present/missing/readiness

Blocked / Attention:
- [Path] [problem]

Recommended next action:
- [Specific next step]

Quality Bar

  • Be accurate and path-specific.
  • Prefer short dashboards over long commentary.
  • Do not infer approvals from file existence; use .status and artifact headers when available.
  • Flag missing or inconsistent status instead of silently normalizing it.
  • Compute numbering from actual directories, never from memory or INDEX.md.
  • When a strategy handoff exists but no SDD artifacts exist, recommend /skill:sdd-plan or /skill:sdd-prd depending on scope.
  • When tasks are approved but sdd-brief.md is missing or stale, recommend refreshing the SDD handoff.

Critical Rules

  • Do not create, edit, or delete files in this skill.
  • Do not approve drafts.
  • Do not implement code.
  • Do not run expensive verification commands unless the user explicitly asks for a health check.

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.