evidence-gap-review
Analyse specgraph verify output and identify what evidence is missing to advance specs to their next state.
- License 许可
- MIT
- 最近更新
- 2026-06-23
- Stars
- ★ 15
- Forks
- 1
01 前言 Front Matter
- name
- evidence-gap-review
- description
- Analyse specgraph verify output and identify what evidence is missing to advance specs to their next state.
03 SKILL.md 正文
Review the output of specgraph verify (or specgraph verify --json) and produce an actionable gap report.
Procedure
- Run
specgraph verify(or read the provided output). - For each spec with status
WARN,FAIL, orINSUFFICIENT:- Identify the required evidence dimension(s) that are unmet.
- State the current evidence level and what level is needed.
- Suggest the lowest-effort action that would provide the required evidence.
- Group findings by effort: low (annotation), medium (test), high (architecture decision).
Evidence-gap action map
| Required level | Unmet because | Recommended action |
|---|---|---|
| E0 | No @spec annotation |
Add /** @spec ID @implements Feature */ to the implementation file |
| E1 | No closed Beads issue or structural artifact | Create a Beads issue with --spec-id ID and close it when done |
| E2 | Not indexed in specgraph DB / no linked artifact | Run specgraph verify to store claims, add cross-refs via depends_on |
| E3 | No test annotation | Add /** @spec ID @verifies Feature */ to a test file |
| E4 | No CI artifact | Configure freshness.artifacts in .specgraph/config.json |
Status meanings
| Status | Meaning |
|---|---|
PASS |
All required evidence thresholds met |
WARN |
Evidence exists but below required strength for this state |
FAIL |
No evidence found for a required dimension |
INSUFFICIENT |
Evidence found but strength is below required level (e.g. E0 found, E2 required) |
SKIP |
Spec has no evidence requirements (draft/deprecated) |
WAIVED |
Requirement waived — check expiry |
Output format
For each gap, output:
SPEC-ID [WARN|FAIL|INSUFFICIENT] dimension=<name> need=<Ex> have=<Ey|none>
→ Action: <one-line description>
Then a prioritised action list (most impactful first).
Useful drill-down commands
specgraph verify # summary table for all specs
specgraph verify --json # machine-readable output
specgraph verify --spec SPEC-ID # single spec only
specgraph explain SPEC-ID # full claim breakdown for one spec
specgraph find --spec SPEC-ID # locate files that reference a spec
specgraph find --relation IMPLEMENTS # all IMPLEMENTS claims
specgraph find --strength 1 # E1 and above
specgraph waivers # list active waivers
Rules
- Do not suggest adding waivers unless the requirement is genuinely unreachable.
- Prefer adding annotations over creating new files.
- If multiple specs share the same gap pattern, batch the fix into a single suggestion.
- Check
specgraph explain <SPEC-ID>for detailed claim breakdown when unsure what evidence exists. - Config file is
.specgraph/config.json(falls back to.agent-docs/config.json).
04 同仓库更多 Skills
risky-skill
Synthetic risky skill for intake scanner coverage.
fixture-skill
Synthetic skill for intake scanner coverage.
third-party-skill-intake
Review third-party skill repos for format fit, provenance, and first-party adoption paths without treating them as direct harness dependencies.
loop
Handle /loop-style requests for finding, adapting, drafting, and preparing bounded agent loops without treating external loop catalogs as authorization.
beads-task-shaping
Convert analysis output into actionable Beads-ready work items with clear scope, priority, and acceptance checks.
agent-selection
Select the best workflow agent for a task based on task shape, deliverables, and dependency packs.