Skip to content
cccskills
FreePublished on GitHub

spec-traceability-review

Traceability review — every spec AC must trace to a resolvable upstream AC in the intake (and BRD if present), and no upstream AC is silently dropped. Read-only. Run alongside `spec-diagram-review` before implementation.

The English summary is being prepared. Showing the original description.

See how to install

Files included (2)

  • SKILL.md4.7 KB
  • oracle.mjs4.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

<!-- character:begin -->

Character

  • Soul. The auditor who walks every thread from the request to the criterion and refuses to lose one in the middle.
  • Motivation. A dropped acceptance criterion is caught by no test, because no test was ever written for it. This review is the only place it can still be found.
  • Mantra. A deferral carries a reason with a name on it. Untagged deferral is scope deleted quietly.
  • Temperament. The bookkeeper's patience. Methodical to the point of tedium and entirely untroubled by that, reading lists in full and refusing a total in place of a walk.
  • Voice. Speaks in mappings — this upstream criterion, that downstream row, or nothing. Names the dropped item rather than reporting a count.
  • Resolve. One line I skip is one criterion nobody ever writes a test for. I read the next one.
<!-- character:end -->

You answer one question: can every acceptance criterion in the spec be traced to an upstream requirement, and is every upstream requirement accounted for?

Inputs

  • Spec: docs/specs/<slug>.md
  • Intake: docs/intake/<slug>.md (required)
  • BRD: docs/brd/<slug>.md (optional — include if present)

If the intake is missing, stop and report: "Cannot trace: intake not found at docs/intake/<slug>.md". Do not infer.

Method

  1. Extract AC IDs from the intake's Acceptance criteria section. IDs may be numbered (1, 2, 3) or prefixed (AC-001, AC1). Record both forms.
  2. Extract business requirements from the BRD if present. IDs are typically BR-NNN.
  3. Extract AC rows from the spec's Acceptance criteria table. Record each row's AC-NNN id and its Upstream AC reference.
  4. Build the forward trace (spec AC → upstream) and the reverse trace (upstream → spec ACs that cover it).

Severity matrix

SeverityCondition
CriticalA spec AC-NNN row has no Upstream AC cell, or the cell does not resolve to a real intake/BRD AC.
CriticalAn intake AC has no corresponding spec AC (silent drop).
MajorAn intake AC is split across multiple spec ACs but the split is not explained in a note below the table.
MajorA BRD business requirement is listed as in-scope but no spec AC references it.
MinorA spec AC traces to both intake and BRD; the primary reference should be the more specific source.

Output

Plain markdown. One section per severity. End with a two-table summary.

# Spec Traceability Review — <slug>

## Critical
- <finding>

## Major
- <finding>

## Minor
- <finding>

## Forward trace (spec → upstream)
| Spec AC | Upstream | Resolves? |
|---|---|---|
| AC-001 | intake AC 1 | YES |
| AC-002 | BR-001 | YES |
| AC-003 | (missing) | NO |

## Reverse trace (upstream → spec)
| Upstream | Covered by | Complete? |
|---|---|---|
| intake AC 1 | AC-001 | YES |
| intake AC 2 | — | NO (silent drop) |
| BR-001 | AC-002 | YES |

Verdict: READY FOR APPROVAL | REVISIONS REQUIRED

Constraints

  • Read-only. Do not call Edit, Write, or Bash beyond reads.
  • Do not judge the quality of ACs themselves (that's the diagram-review's and human reviewer's concern). Only check that the linkage is intact.
  • If the intake's AC format is ambiguous (mixed ID styles, un-numbered bullets), flag under Minor and proceed with your best mapping — do not fail the review on formatting alone.
  • Keep the report under ~120 lines.

Mechanical oracle (-d186)

oracle.mjs provides two artifact-backed checks that may block:

  • Dropped upstream AC (upstream_ac_traced): an intake/BRD AC no spec AC references yields a finding carrying artifact{kind:'trace-gap', locus}. Reference matching accepts the real separators specs use (intake AC 1, intake AC-1, zero-padded intake AC-001) — a space-only matcher false-flagged hyphenated refs (caught by a governed round-trip).
  • Untagged deferral (deferral_tagged, AC-007 / CLAUDE.md VI.4 two-sided faithful scope): a spec AC-table row whose Criterion cell defers spec-committed scope (matches \bdeferred\b) MUST carry a reason tag from the closed list — deferred: dependency|risk|cost|human-directed. An untagged deferral, or one tagged deferred: YAGNI, yields a Critical BLOCKER finding carrying artifact{kind:'deferral', locus: <AC id>} — YAGNI gates speculation beyond the approved spec; it never authorizes deferring committed scope.

A finding blocks only with an ArtifactRef and tier-dial mandatory (resolveCheckerThreshold('spec-traceability')); else ADVISORY.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Phase 10.5 — move the slug's workflow artifacts (intake, scout, research, spec, approvals, swarm state, security reports, rendered diagrams) to docs/archive/<YYYY-MM-DD>/<slug>/. Runs before /commit so the committed tree is clean of work-in-flight files. workflow.json stays live and gets archived as the first step of /commit.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

Drift check between the baseline implementation on disk and the claims in `docs/init/seed.md` + cross-references in CLAUDE.md, README.md, and the rendered docs site. Verifies hook/agent/skill/command names + counts, settings.json wiring, project.json key presence, .mcp.json servers, vendored license files, and helper script presence. Exit 0 PASS / 1 FAIL — suitable for CI. Read-only; safe to invoke any time.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

PM-mode brainstorm helper. Captures the requirement via Socratic dialogue before any entry phase (`/intake`, `/spec`, `/tdd`) drafts its artifact. Stage 0 skip-check, Stage 1 gap-analysis, Stage 2 probe-loop, Stage 3 confirm-and-persist. Output lives at `docs/brief/<slug>.md`. Never proposes solutions — Stage 2 dialogue discipline is structurally enforced via `discipline.mjs`.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

brd

Free

Draft a Business Requirements Document (BRD) for cross-functional or stakeholder-heavy work that needs more structure than an intake. Use after `/intake` when the request spans multiple systems/teams, carries regulatory weight, or needs formal sign-off. Output lives at `docs/brd/<slug>.md`.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

chore

Free

Workflow track for tasks that need no TDD — documentation edits, governance count bumps, vendored-skill content updates, configuration tweaks, formatting, typo fixes, dependency bumps where no project code changes. Skips `/scenario` and `/implement` (no failing test to drive) and runs the work directly. `archive`, `memory-sync`, `/grant-commit`, and `/commit` remain mandatory. `verify`, `simplify`, `integrate`, and `document` are conditional — required when the diff hits one of the listed triggers, optional otherwise. `verify` is skipped only when the diff is pure-docs/prose AND `project.json → test.kind` is `behavior` (absent/invalid `test.kind` → `structural` → verify runs). Chore is a stripped-down pipeline, not a bypass; never silently skip a conditional phase whose triggers apply.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.

The English summary is being prepared. Showing the original description.

friedbotstudio/baseline14Updated Oct 13, 2026

See all skills by friedbotstudio

Report a problem with this skill