Agent skill · Documentation

spec-status

Show pipeline overview of all specifications with status counts and stale detection

majiayu000github.com/majiayu000GitHub ↗
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill spec-status --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Allowed tools: Bash(find:*)Bash(grep:*)Bash(stat:*)ReadGlob
Path: skills/analysis/spec-status/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Spec Status Skill Display a pipeline overview of all specifications in the repository. ## Usage ``` /spec-status ``` ## Output Format ``` Spec Pipeline: Draft: 2 001-valkey, 002-gpu-nodes Implementing: 1 003-queue Done: 15 (in docs/specs/done/) Stale (>14 days unchanged): 001-valkey (last modified: 2025-01-05) ``` ## Workflow ### 1. Find Active Specs ```bash # Find all spec.md files excluding done/ and templates/ find docs/specs -name "spec.md" \ -not -path "*/done/*" \ -not -path "*/templates/*" \ -type f 2>/dev/null ``` ### 2. Parse Status from Each Spec For each spec file found: ```bash # Extract status field from spec header grep -oP '\*\*Status\*\*:\s*\K[^\s|]+' "$SPEC_FILE" ``` Valid statuses: `draft`, `in-review`, `approved`, `implementing`, `done` ### 3. Count Done Specs ```bash # Count specs in done/ directory find docs/specs/done -name "spec.md" -type f 2>/dev/null | wc -l ``` ### 4. Detect Stale Specs ```bash # Find specs not modified in 14+ days find docs/specs -name "spec.md" \ -not -path "*/done/*" \ -not -path "*/templates/*" \ -mtime +14 \ -type f 2>/dev/null ``` ### 5. Format Output Group specs by status and display: - **Draft**: Specs with `draft` or `in-review`

What's inside
Steps it walks through
  1. Usage
  2. Output Format
  3. Workflow
  4. 1. Find Active Specs
  5. 2. Parse Status from Each Spec
  6. 3. Count Done Specs
  7. 4. Detect Stale Specs
  8. 5. Format Output
  9. Status Categories
  10. GitHub Issue Labels
  11. Example Output
  12. Related Skills
Ships with 1 file
  • metadata.json
Commands it runs
Find all spec.md files excluding done/ and templates/
find docs/specs -name "spec.md" \
Extract status field from spec header
grep -oP '\*\*Status\*\*:\s*\K[^\s|]+' "$SPEC_FILE"
Count specs in done/ directory
find docs/specs/done -name "spec.md" -type f 2>/dev/null | wc -l
Find specs not modified in 14+ days
List spec issues by label
gh issue list --label "spec:draft"
gh issue list --label "spec:implementing"
More from claude-skill-registry
All skills →
About this skill
What does the spec-status skill do?

Show pipeline overview of all specifications with status counts and stale detection

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill spec-status --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going