Menu
Use when requirements are unclear, before planning - clarifies goals, constraints, and acceptance criteria through structured questioning
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use after implementation to run independent code review - dispatches reviewer agents based on task level, ensures author-reviewer separation
Use for the L2+ browser-QA gate. Real-browser mode (Playwright Chromium) is opt-in (--browse / SGC_QA_REAL=1); by default runs a stub returning concern (never rubber-stamps). Writes verdict + findings to reviews/{task}/qa/.
Use when starting any conversation - establishes SGC commands, routes tasks to appropriate skills, and enforces system invariants
Use to capture knowledge from solved problems - extracts structured solution documents via 4 specialized agents with dedup enforcement
Use when starting any non-trivial task - classifies task level (L0-L3), runs appropriate planning agents, produces intent document and execution plan
Use when ready to release - verifies all evidence, runs ship gate, handles deployment, triggers compound janitor
| name | discover |
| description | Use when requirements are unclear, before planning - clarifies goals, constraints, and acceptance criteria through structured questioning |
Take a vague topic; emit structured forcing-questions (goal / constraints / scope / edge cases / acceptance) plus a concrete sgc plan follow-up. The user answers the questions inline, then carries the consolidated answer into sgc plan --motivation.
Core principle: ambiguity in requirements multiplies into bugs in code. Eliminate it before writing a single line.
/plan when the task is L2+ and scope is unclear| Directory | Access |
|---|---|
| decisions | — |
| progress | R |
| solutions | — |
| reviews | — |
Plus spawn:clarifier.*. No writes — discover cannot mutate .sgc/ state beyond the spawn audit trail under progress/agent-prompts/ and agent-results/.
src/commands/discover.ts (runDiscover)src/dispatcher/agents/clarifier-discover.ts — heuristic stub keys off auth / data / ui / perf / api keywords to tune the question setclarifier.discover manifest in contracts/sgc-capabilities.yamlWhen this skill is invoked, dispatch to the sgc CLI:
bun src/sgc.ts discover "$ARGUMENTS"
Output is structured text with sections Goal / Constraints / Scope / Edge cases / Acceptance / Next. The last section contains the exact sgc plan ... command to run after answering.
For product-fuzzy requirements exploration beyond sgc's forcing questions:
gs:/office-hours — YC-style brainstorming for demand reality, wedge identification, and design docsIf an active task exists (progress/current-task.md), its id + level show up in the suggested-next hint as context.