원클릭으로
workflow-brainstorm-review
Review Smelter brainstorm artifacts for decision quality, risks, completeness, and implementation readiness.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Review Smelter brainstorm artifacts for decision quality, risks, completeness, and implementation readiness.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when: User wants to run a SUBSTANTIAL multi-step coding task as a workflow (fix/implement a whole issue or feature, comprehensive review), CREATE workflows or commands, set up workflow automation, or manage workflow configuration. Triggers (run): "use workflow to", "run workflow", "with workflow", "workflow to", "workflow run", "use a workflow to", "run a workflow", and generic task-completion intents that imply a full coding deliverable: "실행해줘", "돌려줘", "구현해줘", "고쳐줘", "이슈 고쳐줘", "PR 만들어줘", "implement this", "fix this issue", "build this feature", "ship this". Triggers (create): "create a workflow", "write a workflow", "make a command", "author a workflow", "new workflow", "new command", "workflow yaml". Triggers (setup): "set up workflows", "install workflow automation", "how to use workflows", "configure workflows", "workflow setup", "get started with workflows". Triggers (config): "change my workflow config", "modify workflow config", "workflow
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Smelter deep interview for planning-first requirement discovery before /brainstorm, /implement, or /fix execution
Create a release from dev branch. Generates changelog entries from commits, bumps version, and creates a PR to main. TRIGGERS - Use this skill when user says: - "/release" - create a patch release (default) - "/release minor" - create a minor release - "/release major" - create a major release - "make a release", "cut a release", "ship it", "release to main"
Replicate and validate a GitHub issue by spinning up Smelter, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Smelter, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /smelter or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
Autonomous rule adherence checker. Scans the codebase for rule violations, fixes the highest-impact ones in an isolated worktree, runs full validation, creates a PR. Uses memory to track progress across runs.
| name | workflow-brainstorm-review |
| description | Review Smelter brainstorm artifacts for decision quality, risks, completeness, and implementation readiness. |
| version | 0.55 |
| type | workflow |
| consumes | brainstorm.md |
| produces | brainstorm-review.md |
| default_pattern | B |
| default_agent | critic |
| supports_patterns | ["A","B"] |
| team_template | {"B":{"agents":["critic"],"mode":"adversarial_single"}} |
| result_types | ["pass","fail","reshape"] |
| min_verification_rounds | 2 |
| verification_rounds | [{"n":1,"focus":"omission","prompt_template":"templates/verification/round-1-omission.md"},{"n":2,"focus":"contradiction","prompt_template":"templates/verification/round-2-contradiction.md"}] |
| gate | {"postcondition":[{"file_exists":"brainstorm-review.md"},{"contains_decision":"pass|fail|reshape"}]} |
Reviews brainstorm.md from the critic's perspective. Surfaces ambiguity, contradictions, and omissions before any investigation or task-breakdown work consumes them.
Core principle: A design is not approved until both review rounds (omission, contradiction) return pass. Partial review is not review.
Violating the letter of this rule is violating the spirit of this rule.
Announce at start: "I'm using workflow-brainstorm-review to run 2-round verification on brainstorm.md."
NO DOWNSTREAM HANDOFF WITHOUT 2/2 REVIEW ROUNDS AT pass
Skill-level pass is declared only when completed_rounds === 2 && all rounds result === pass. Declaring pass with completed_rounds < 2 is blocked by hook.
brainstorm-review.md:
## Verdict — pass / fail / reshape## Issues Found — ambiguity, contradictions, missing perspectives## Suggestions — corrective directions (on fail/reshape)## Reshape Target — only when reshape (e.g., re-run workflow-brainstorm itself)| Thought | Reality |
|---|---|
| "Looks complete to me, skip round 2" | Multi-Pass 2-Round Enforcement is non-negotiable. Hook blocks sub-2 pass. |
| "The design is obviously fine" | Obviousness is rationalization. Round 1 = omission, round 2 = contradiction. Each catches different bugs. |
| "Round 1 passed, ship it" | Skill-level pass requires both rounds at pass. One round is not pass. |
| "Include prior round findings in the next round to save time" | Bias prevention: do NOT inject prior round conclusions into current round prompts. |
| "We already verified this last session" | Stage-completion is session-local. Re-verify on every run. Critic Watchdog blocks "already verified" skips. |
| Excuse | Reality |
|---|---|
| "No contradictions visible → skip round 2" | Invisibility is what round 2 reveals. Run it. |
| "Edge cases are for later" | Later = never. Capture them now or lose them. |
| "The critic agrees with the plan" | Agreement is not the verdict. pass vs. fail vs. reshape is. Record it. |
| "Just this once" | No exceptions. Every round every run. |
skill declarer allowed (Iron Law principle 3). The hook only checks for the postcondition file.pass) but may not declare "cannot do it".This skill runs 2 mandatory rounds before declaring pass. Each round has a distinct focus:
| Round | Focus | Question |
|---|---|---|
| 1 | Omission | Is anything required (scope, constraints, perspectives) missing? |
| 2 | Contradiction | Are there logical conflicts within the brainstorm or with prior artifacts? |
All rounds recorded in state.json.team_runtime.workflow-brainstorm-review.rounds[]. Skill-level pass is declared only when completed_rounds === 2 && all rounds result === pass.
fail → skill-level fail with cause: verification_failed, evidence: {round, focus, findings[]}workflow-brainstorm (the consumed artifact's producer)pass with completed_rounds < 2 is blocked by hookfail → re-run workflow-brainstorm (augment)reshape → re-run workflow-brainstorm (reset scope, evidence required)REQUIRED NEXT SKILL on pass: workflow-investigate
On fail or reshape: route back to workflow-brainstorm (producer chain).
Do NOT:
workflow-tasker, workflow-coding, or any execution skill