agentleFS
Luis85Luis85/agentic-workflow/.claude/skills/quality-metrics/SKILL.md

quality-metrics

Skill0 starsChanged 6 months agoMITView on GitHub

Report deterministic quality KPIs — deliverables, traceability, QA checklists, blockers, maturity, trends. Triggers "quality status", "project KPIs", "quality metrics", "quality trend".

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    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:

    Use this skill when the user asks for the current quality status or KPIs of a project built from this template.

    line 9
  2. Distinctive:

    Run the repository metrics command:

    line 13
  3. Very specific:

    Use docs/quality-metrics.md when explaining what a metric means, what action it supports, and what it must not be used to infer.

    line 70
  4. Distinctive:

    Do not call the KPI score an ISO 9001 certification result.

    line 83
  5. Distinctive:

    Do not hide blockers or gaps because the overall score is high.

    line 84
  6. Distinctive:

    Do not mark quality gates complete based only on this script.

    line 85

“Common” is measured: kept by at least 6 in 10 of the 3 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

Quality Metrics

Use this skill when the user asks for the current quality status or KPIs of a project built from this template. It reports deterministic signals from repository artifacts; it does not replace the judgment-based Quality Assurance Track.

Command

Run the repository metrics command:

specorator quality:metrics

For one feature:

specorator quality:metrics -- --feature <feature-slug>

For machine-readable output:

specorator quality:metrics -- --json

For a trend baseline or comparison:

specorator quality:metrics -- --save
specorator quality:metrics -- --compare

The slash-command entry point is:

/quality:status [--feature <feature-slug>] [--compare] [--save] [--json]

What It Measures

  • Workflow deliverable completion from specs/*/workflow-state.md and examples/*/workflow-state.md.
  • Required artifact presence for the Specorator lifecycle.
  • Frontmatter coverage on workflow artifacts and Markdown files that require metadata.
  • Requirement downstream coverage through spec items, tasks, and tests.
  • EARS coverage for functional requirements.
  • Open blockers and clarifications in workflow state.
  • QA checklist volume and gap/nonconformity counts under quality/.
  • Stage-aware score so future lifecycle evidence is not treated as a defect while work is still in progress.
  • Evidence-backed maturity level with evidence, gaps, and next-step guidance.
  • Optional saved trend snapshots under quality/metrics/ for score, maturity, blocker, clarification, frontmatter, and QA-gap deltas.

Reporting

Summarize:

  • overall workflow score and stage-aware score,
  • maturity level, evidence, gaps, and next step,
  • lowest-scoring workflow KPIs,
  • active blockers and open clarifications,
  • missing frontmatter or documentation hygiene signals,
  • QA checklist gaps and nonconformities,
  • trend deltas when --compare is used,
  • whether the result is a deterministic KPI snapshot or a full QA readiness review.

Use docs/quality-metrics.md when explaining what a metric means, what action it supports, and what it must not be used to infer.

Agent Hooks

  • orchestrator: use /quality:status or this skill when the user asks "what's next?" and quality status would affect the recommendation.
  • qa: run feature-scoped metrics before finalizing test-plan.md or test-report.md; include blockers, clarifications, and traceability/test gaps as testing risks.
  • reviewer: run feature-scoped JSON metrics as deterministic evidence before writing the review verdict; do not let a high score replace review judgment.
  • release-manager: run --feature <slug> --compare before release readiness when a saved baseline exists; otherwise run --feature <slug> and disclose that no trend baseline exists.
  • retrospective: run --feature <slug> --save after learning-stage conclusions so future work can compare quality drift.
  • project-manager, portfolio-manager, and roadmap-manager: prefer --json when folding quality status into reports or dashboards.

Do Not

  • Do not call the KPI score an ISO 9001 certification result.
  • Do not hide blockers or gaps because the overall score is high.
  • Do not mark quality gates complete based only on this script; use the relevant workflow gate and critic review.

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.