staruhub/ClaudeSkills / skills/Geek-skills-product-manager
product-manager
Verified资深产品经理助手,提供 PRD/MRD/BRD 创作与评审、产品策略、留存增长、竞品分析、功能优先级,以及 grill-me-to-doc 逐轮访谈。用户要求“逐个问我”“先把需求问清楚”“grill me”“把想法变成产品文档”时进入 grill-me-to-doc:先读仓库证据,每轮只问一个决策,给推荐答案与理由,记录决策和未决项,支持 resume,产出结构化 PRODUCT-DOC;文档完成且用户批准前硬停止,任何时候都不写实现代码。即使未提“产品”,讨论 App 功能、增长或商业模式也应触发。不用于:单纯代码实现、系统架构深设(用 solution-architect)、需多源引用的市场调研(用 deep-research)、纯营销文案。
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.4 KB |
| evals/routing-evals.json | config | 2.1 KB |
| references/GRILL-ME-TO-DOC.md | markdown | 6.0 KB |
| references/PM-BEST-PRACTICES.md | markdown | 16.7 KB |
| references/PRD-TEMPLATE.md | markdown | 11.6 KB |
| references/PRD-WRITING-GUIDE.md | markdown | 13.0 KB |
| references/PRODUCT-DOC-TEMPLATE.md | markdown | 1.6 KB |
| references/REVIEW-CHECKLIST.md | markdown | 12.8 KB |
| schemas/grill-state.schema.json | config | 5.0 KB |
| scripts/validate_grill_session.py | script | 12.3 KB |
schemas/grill-state.schema.json
View on GitHub{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://staruhub.github.io/ClaudeSkills/schemas/grill-state.schema.json",
"title": "Grill-me-to-doc session state",
"type": "object",
"additionalProperties": false,
"required": [
"schema_version",
"session_id",
"skill_version",
"mode",
"status",
"evidence",
"decision_log",
"unresolved_questions",
"completion_gate",
"product_doc",
"hard_stop"
],
"properties": {
"schema_version": {"const": "1.0.0"},
"session_id": {"type": "string", "pattern": "^[a-z0-9][a-z0-9-]{5,63}$"},
"skill_version": {"const": "1.2.0"},
"mode": {"const": "grill-me-to-doc"},
"status": {
"enum": [
"evidence-gathering",
"interviewing",
"ready-for-draft",
"awaiting-approval",
"approved",
"stopped"
]
},
"next_question_id": {"type": ["string", "null"]},
"evidence": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"additionalProperties": false,
"required": ["path", "sha256", "summary", "kind"],
"properties": {
"path": {"type": "string", "minLength": 1},
"sha256": {"type": "string", "pattern": "^[a-f0-9]{64}$"},
"summary": {"type": "string", "minLength": 1},
"kind": {"enum": ["fact", "constraint", "evidence_unavailable"]}
}
}
},
"decision_log": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["id", "decision", "rationale", "source", "status"],
"properties": {
"id": {"type": "string", "pattern": "^d-[a-z0-9-]+$"},
"question_id": {"type": ["string", "null"]},
"decision": {"type": "string", "minLength": 1},
"rationale": {"type": "string", "minLength": 1},
"source": {"enum": ["repository", "user", "inference"]},
"status": {"enum": ["accepted", "modified", "rejected"]}
}
}
},
"unresolved_questions": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": false,
"required": ["id", "question", "blocking"],
"properties": {
"id": {"type": "string", "pattern": "^q-[a-z0-9-]+$"},
"question": {"type": "string", "minLength": 1},
"blocking": {"type": "boolean"}
}
}
},
"completion_gate": {
"type": "object",
"additionalProperties": false,
"required": [
"problem",
"users_jtbd",
"evidence_assumptions",
"scope_non_goals",
"flows",
"requirements",
"success_metrics",
"risks",
"open_questions",
"acceptance_criteria"
],
"properties": {
"problem": {"type": "boolean"},
"users_jtbd": {"type": "boolean"},
"evidence_assumptions": {"type": "boolean"},
"scope_non_goals": {"type": "boolean"},
"flows": {"type": "boolean"},
"requirements": {"type": "boolean"},
"success_metrics": {"type": "boolean"},
"risks": {"type": "boolean"},
"open_questions": {"type": "boolean"},
"acceptance_criteria": {"type": "boolean"}
}
},
"product_doc": {
"type": "object",
"additionalProperties": false,
"required": ["draft_path", "final_path", "approved_by_user"],
"properties": {
"draft_path": {"type": ["string", "null"]},
"final_path": {"type": ["string", "null"]},
"approved_by_user": {"type": "boolean"},
"approved_at_event": {"type": ["integer", "null"], "minimum": 1}
}
},
"hard_stop": {
"type": "object",
"additionalProperties": false,
"required": ["implementation_allowed", "reason"],
"properties": {
"implementation_allowed": {"const": false},
"reason": {"type": "string", "minLength": 1}
}
}
},
"allOf": [
{
"if": {
"properties": {
"status": {"enum": ["ready-for-draft", "awaiting-approval", "approved", "stopped"]}
}
},
"then": {
"properties": {
"completion_gate": {
"properties": {
"problem": {"const": true},
"users_jtbd": {"const": true},
"evidence_assumptions": {"const": true},
"scope_non_goals": {"const": true},
"flows": {"const": true},
"requirements": {"const": true},
"success_metrics": {"const": true},
"risks": {"const": true},
"open_questions": {"const": true},
"acceptance_criteria": {"const": true}
}
}
}
}
},
{
"if": {"properties": {"status": {"enum": ["approved", "stopped"]}}},
"then": {
"properties": {
"product_doc": {
"properties": {
"approved_by_user": {"const": true},
"final_path": {"type": "string", "minLength": 1}
}
}
}
}
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |