菜单
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Plan-then-execute implementation against SPEC.md. Native single-thread loop, no sub-agents. On test or build failure, auto-invokes the backprop skill before retrying — a failed verification always considers whether a new §V invariant would prevent recurrence. Triggers when the user asks to build, implement, execute the spec, or tackle a specific §T task (`build §T.3`, `build --next`, `implement next task`, `run the build`). Expects SPEC.md to exist; if not, defers to the spec skill.
Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec. Phrasings: "check drift", "audit the spec", "does the code still match §V", "check invariants", "spec vs code".
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent rewrites. Triggers when the user says "deepen this", "improve the design", "this module feels shallow", "pull complexity down", "use spare budget on the codebase", or invokes /ck:deepen. Leans on the codebase-design skill's deep-module vocabulary when present.
Calibrated interrogation of a fuzzy idea before it becomes a spec. Asks one question at a time, recommends an answer, and lands each answer in §G (goal) or §C (constraints) — unknowns parked as `?` items, never guessed. The cheapest place to kill a bad idea is before §T exists. Triggers when the user has a vague idea, says "grill me", "stress-test this", "challenge my plan", "interview me before I spec", or invokes /ck:grill. Defers the actual write to the spec skill.
Gather external knowledge the spec needs and distill it into §R — the durable research log — so build grounds in facts instead of hallucinating library behavior. Each finding cites a source; unsourced claims are flagged, never written as fact. Triggers when a spec decision hinges on a library/API/best practice the agent is unsure of, when the user says "research this", "what's the best lib for…", "check current best practice", or invokes /ck:research. Defers the §R write to the spec skill.
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged. Survivors harden §V; the run ends in an explicit go / no-go gate. Triggers before building anything high-blast-radius, when the user says "review the spec", "red-team this", "is this plan sound", "senior review", or invokes /ck:review.
| name | backprop |
| description | Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask. |
Plan-then-execute fixes the code & forgets. SDD fixes the code AND edits spec so recurrence is impossible. That edit is backprop.
/build verification./check flags VIOLATE with root cause found.Read failure output / bug report. Find exact file:line of wrong behavior. Name root cause in one caveman sentence.
Ask three questions:
Draft the spec change. Never skip §B; §V/§I/§T are case-by-case.
Template:
§B row: B<next>|<date>|<root cause>|V<N>
§V line: V<next>: <testable rule that would have caught it>
Example:
§B row: B3|2026-04-20|refund job ran twice on retry|V7
§V line: V7: ∀ refund → idempotency key check before charge reversal
New invariant without test = lie. Add failing test first.
Name test so it cites the invariant: TestV7_RefundIdempotent.
Fix code. Run test. Must pass. Run full suite. Must not regress.
Commit spec edit + test + code fix together.
Commit msg: backprop §B.<n> + §V.<N>: <one-line cause>.
! hold over ⊥ forbid).Bad: V8: code should be correct. Good: V8: ∀ pg_query ! params interpolated via driver, ⊥ string concat.
i++ vs i-- in throwaway).Still append §B entry — record that this failure mode was considered. Future bug with same smell → §B search shows precedent.
Every backprop run produces:
No dashboards. No log files. SPEC.md + git is the full history.