speckit-tdd-verify
Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- speckit-tdd-verify
- metadata
- { "author": "github-spec-kit", "source": "tdd:commands/speckit.tdd.verify.md" }
- description
- Audit TDD discipline by delegating to zfa tdd verify (mutation testing, evidence integrity); the LLM interprets the verdict and drives remediation
- compatibility
- Requires spec-kit project structure with .specify/ directory
03 SKILL.md 正文
TDD Verify (zfa-delegating)
Audit the feature's TDD discipline and test strength. When this project is
zuraffa-wired, the audit is deterministic — dispatch to zfa tdd verify.
User Input
$ARGUMENTS
Accept: --no-tasks (don't append remediation tasks on FAIL).
Step 0 — Engine detection
zfa --version 2>/dev/null && test -f .zfa.json && echo "ZFA_OK" || echo "ZFA_MISSING"
ZFA_OK→ Step 1ZFA_MISSING→ fall back to the original LLM-guided audit
Step 1 — Resolve the feature
Standard resolution: input → .specify/feature.json → prerequisites script.
Step 2 — Dispatch to zfa
zfa tdd verify --feature "$FEATURE_SLUG" 2>&1
Step 3 — Interpret the verdict
zfa writes FEATURE_DIR/tdd/verification.md with a gate verdict.
Gate passed (exit 0)
Report: killed/survived/timed_out mutant counts, restoration verified, the verification path. Feature's TDD discipline is proven.
Gate preflight_red (non-zero)
The suite is red — verify refuses to audit a red suite (correct gate).
Report the failing tests, send the user back to /speckit.tdd.run.
Mutation survived (exit 1)
At least one mutant survived — a test is weak. Report the per-mutant table
from verification.md with the --> fix: pointer to the weak test. Unless
--no-tasks, append remediation tasks to tasks.md (one per surviving
mutant: "strengthen <test> to kill <mutant>").
Exit 2 or 3
Grammar or contract drift. Report verbatim.
Step 4 — Remediation loop (when FAIL)
- Append remediation tasks to
tasks.md(one per finding). - Drive them through
/speckit.tdd.run(they pick up as new behaviors). - Re-run this command.
- Cap: 3 remediation passes; report the verdict each pass.
Fallback Path (non-zuraffa projects)
Run the original LLM-guided audit: check test-first evidence in git history, red-phase evidence in cycle-log, test-smell rubric, mutation testing on changed files, acceptance-criteria coverage; write verification.md with verdict and remediation tasks.
04 同仓库更多 Skills
speckit-tdd-setup
Detect the test stack and write .specify/memory/tdd-profile.md; zuraffa-wired projects record zfa commands as the engine
speckit-tdd-run
Drive the red-green-refactor loop by delegating to zfa tdd run (deterministic engine); the LLM handles only honest stops — fixing genuine reds and remediation — never re-driving what zfa drives
speckit-tdd-plan
Derive the feature's test list by delegating to zfa tdd plan (deterministic engine); falls back to LLM-guided derivation only when zfa is unavailable
speckit-spec-stats-runs
On-demand execution — reads verified suite command from .specify/memory/tdd-profile.md, runs it for selected specs (--all, spec id/slug, or default active feature), captures pass/fail + duration + tail, appends run record to .specify/stats/runs.json, refreshes dashboard health column
speckit-spec-stats-report
Main generator — scans all specs/*/, derives per-feature stage, task progress, health, last updated; when the TDD extension is installed, adds a deep TDD table (acceptance/unit/characterization counts, DONE, loop mode, tasks.md state); renders dashboard to configurable output path and writes .specify/stats/stats.json snapshot
speckit-spec-stats-reconcile
Reconcile tasks.md checkboxes against actual implementation — cross-references TDD test-list.md DONE behaviors and file existence to mark tasks that were implemented but never checked