[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MJVEXTMG6G9QPHNHNMPNAT":3,"skill-same:01M6MJVEXTMG6G9QPHNHNMPNAT":98},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":36,"publishedAt":57,"linkOnly":58,"markdownContent":59,"markdownBody":60,"frontMatter":61,"refName":78,"commitSha":79,"skillDirectory":80,"forksCount":13,"repositoryHtmlUrl":81,"repositoryHomepageUrl":6,"ownerHtmlUrl":82,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":83,"install":84,"resources":97},"01M6MJVEXTMG6G9QPHNHNMPNAT","product-skills",null,"Use when coordinating product work across the 12 bundled product sub-skills (RICE, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, SaaS scaffolding) or the 4 standalone product-team plugins (user stories, Apple HIG, code-to-PRD, research summarizer). Triggers on 'help me prioritize', 'plan a product experiment', 'we ship features nobody uses', 'run the discovery loop', 'is our OST sound'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a continuous-discovery loop (Torres cadence tracker + OST linter as machine gates) or a full goal→plan→execute→verify→close run through the repo-wide agent-harness. Distinct from project-management (how to deliver vs what to build), marketing\u002Flanding (from-scratch pages), and engineering\u002Fagent-harness (the generic loop engine this orchestrator plugs into).","JiayiV\u002Fquestion_mixing","JiayiV","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54466889?v=4","01M6JFJYYMRZ3QRGP9339JNQ2K","01M6JFJZ35KB0QVT50NAHPJA7G",0,"MIT","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-product-team-skills-product-skills-skill-093adf80\u002FSKILL.md",[17,22,25,30,33],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",{"categoryNo":31,"categoryName":32,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000032","设计师",{"categoryNo":34,"categoryName":35,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000033","数据分析师",[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56],"product","product skills","project-management","cadence","close","summarizer","teardown","project","digest","tracker","router","design","prioritize","plan","loop","how","team","run","analytics","experiments","2026-11-10 10:12:30",false,"---\nname: \"product-skills\"\ndescription: \"Use when coordinating product work across the 12 bundled product sub-skills (RICE, OKRs, UX research, design tokens, competitive teardown, analytics, experiments, discovery, roadmaps, spec-to-repo, landing pages, SaaS scaffolding) or the 4 standalone product-team plugins (user stories, Apple HIG, code-to-PRD, research summarizer). Triggers on 'help me prioritize', 'plan a product experiment', 'we ship features nobody uses', 'run the discovery loop', 'is our OST sound'. Forks context to route to one sub-skill via a deterministic signal router and returns a digest; can also drive a continuous-discovery loop (Torres cadence tracker + OST linter as machine gates) or a full goal→plan→execute→verify→close run through the repo-wide agent-harness. Distinct from project-management (how to deliver vs what to build), marketing\u002Flanding (from-scratch pages), and engineering\u002Fagent-harness (the generic loop engine this orchestrator plugs into).\"\ncontext: fork\nversion: 2.11.1\nauthor: Alireza Rezvani\nlicense: MIT\ntags: [product, product-management, orchestrator, discovery, ux, analytics, agent-harness]\ncompatible_tools: [claude-code, codex-cli, cursor, antigravity, opencode, gemini-cli]\n---\n\n# Product Team — Domain Orchestrator & Discovery Loop\n\nThis orchestrator does two jobs. **Routing:** fork context, classify a product inquiry\nwith `scripts\u002Fproduct_goal_router.py` across all 16 product-team lanes (12 bundled + 4\nstandalone plugins), run exactly one, return a digest. **Looping:** run product work as\nbounded agentic loops with machine-checkable gates — the continuous-discovery loop\n(weekly cadence scored by `discovery_cadence_tracker.py`, tree structure enforced by\n`ost_linter.py`) and goal-scale runs through the repo-wide agent-harness.\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Prioritize features \u002F RICE \u002F PRD\" | `product-manager-toolkit` |\n| \"OKRs, strategy cascade\" | `product-strategist` |\n| \"Personas, usability, research synthesis\" | `ux-researcher-designer` |\n| \"Design tokens, WCAG contrast\" | `ui-design-system` |\n| \"Competitor matrix, teardown\" | `competitive-teardown` |\n| \"Retention, cohorts, funnels, KPIs\" | `product-analytics` |\n| \"A\u002FB test, sample size, hypothesis\" | `experiment-designer` |\n| \"Discovery, assumptions, opportunity trees\" | `product-discovery` |\n| \"Roadmap comms, release notes, changelog\" | `roadmap-communicator` |\n| \"Spec → runnable repo\" | `spec-to-repo` |\n| \"Landing page (Next.js\u002FTailwind)\" | `landing-page-generator` |\n| \"SaaS boilerplate\" | `saas-scaffolder` |\n| \"User stories, sprint capacity\" | `agile-product-owner` (standalone) |\n| \"Apple HIG audit\" | `apple-hig-expert` (standalone) |\n| \"PRD from an existing codebase\" | `code-to-prd` (standalone) |\n| \"Summarize papers\u002Farticles\" | `research-summarizer` (standalone) |\n\n## Routing logic (deterministic)\n\n```bash\npython3 scripts\u002Fproduct_goal_router.py --text \"\u003Cthe goal>\" --output json\n```\n\nExit 0 → `route_to` names the skill (with `skill_path`, including the standalone\nplugins): load its SKILL.md and follow its workflow. Exit 2 → ask ONE clarifying question\nnaming the listed candidates, with a recommended answer. Exit 3 → no signal: ask the user\nto restate the goal with the deliverable named. Never guess silently; never silently\nchain — digest first, confirm, then chain.\n\n## The discovery loop (the domain's recurring agentic loop)\n\nModern discovery is a weekly habit, not a project phase (Torres). Run it as a bounded\nloop with two machine gates:\n\n1. **Observe** — maintain `discovery_log.json` (interviews, assumption tests; shape in\n   `assets\u002Fsample_discovery_log.json`) and score the cadence:\n   ```bash\n   python3 scripts\u002Fdiscovery_cadence_tracker.py --input discovery_log.json\n   ```\n   Refuses on \u003C 2 interviews (exit 5) — there is no cadence to measure yet. Output:\n   health 0–100, verdict HEALTHY\u002FAT-RISK\u002FDORMANT, named gaps, and `next_loop_action`.\n2. **Choose** — the tracker's `next_loop_action` IS the choice: book the touchpoint,\n   re-anchor the guide on the outcome, or test the top untested assumption (route to\n   `product-discovery`'s assumption_mapper for prioritization).\n3. **Act** — run the interview \u002F assumption test with the routed sub-skill's tools.\n4. **Verify** — keep the tree structurally sound before it may drive a roadmap:\n   ```bash\n   python3 scripts\u002Fost_linter.py --input ost.json    # exit 2 = NEEDS-REWORK, fix before citing the tree\n   ```\n   Rules: one measurable outcome root (O1), opportunities are needs not features (O2),\n   targeted opportunities compare ≥ 2 solutions (O3), every solution has an assumption\n   test (O4), no orphan solutions (O5 — the feature-factory tell).\n5. **Record \u002F Repeat-or-stop** — update the log, keep the weekly streak alive. Stop\n   states: HEALTHY + validated assumption → graduate to `experiment-designer` (build the\n   A\u002FB gate) or `product-manager-toolkit` (PRD); DORMANT for 4+ weeks → escalate to the\n   product lead by name — do not quietly let discovery die.\n\nFor build-scale goals (\"turn this validated spec into a repo and verify it\"), compile\nthrough the repo-wide harness instead:\n\n```bash\npython3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Fgoal_compiler.py \\\n  --goal \"\u003Cgoal>\" --manifest engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fassets\u002Fharnesses\u002Fproduct-team.json \\\n  --out .agent-harness\u002Fplan.json\n```\n\nThe domain's three strongest close-out gates plug in as task verifications:\n`..\u002Fspec-to-repo\u002Fscripts\u002Fvalidate_project.py` (exit 0), `code-to-prd`'s golden\n`expected_outputs\u002F`, and `research-summarizer`'s citation-count check.\n\n## Hard rules\n\n1. **Evidence before conviction**: no roadmap item cites the OST unless `ost_linter.py`\n   exits 0; no insight is asserted from a single participant (anecdote, not insight).\n2. **Outcome-first**: every loop hangs from one measurable outcome — the linter's O1 rule\n   is the intake gate.\n3. **Experiments are gated by math**: sample size from\n   `..\u002Fexperiment-designer\u002Fscripts\u002Fsample_size_calculator.py`, never gut feel; report the\n   MDE with the verdict.\n4. **Prioritization shows its framework**: RICE for steady-state, WSJF\u002Fcost-of-delay when\n   time sensitivity dominates, opportunity scoring for underserved needs — name which and\n   why (see [references\u002Fproduct_operating_model.md](references\u002Fproduct_operating_model.md)).\n5. **AI features ship with evals**: a golden set + rubric is the PRD's quality contract\n   for probabilistic features\n   ([references\u002Fai_product_evals.md](references\u002Fai_product_evals.md)).\n6. **Never modify a gate you are judged by**; exhausted budgets escalate to a named human,\n   never report as success.\n\n## Forcing-question library (grill-with-docs pattern)\n\nOne per turn, recommended answer, canon citation. Never run a sub-skill or start a loop\nuntil the lane-defining decision is locked:\n\n- **DISCOVERY lane**: \"What is the single outcome this discovery serves, stated with a\n  number? Recommended: write it as the OST root first — opportunities without an outcome\n  are a feature factory. Canon: Torres, *Continuous Discovery Habits*; opportunity\n  solution trees (producttalk.org).\"\n- **PRIORITIZE lane**: \"Does time sensitivity change this ranking — would delaying any\n  item a quarter erode its value? Recommended: if yes, run WSJF\u002Fcost-of-delay alongside\n  RICE and compare ranks; flag items whose rank flips on a one-step estimate change.\n  Canon: Reinertsen, *Principles of Product Development Flow*; SAFe WSJF false-precision\n  critique.\"\n- **EXPERIMENT lane**: \"What baseline rate and MDE justify this test's runtime?\n  Recommended: compute n first; if you can't reach it in 4 weeks, test a bigger lever.\n  Canon: statistical power analysis (experiment-designer).\"\n- **ANALYTICS lane**: \"Is your North Star a leading indicator of value exchange, or\n  revenue\u002Fvanity? Recommended: leading value metric with an input tree. Canon: Amplitude,\n  *The North Star Playbook*.\"\n- **STRATEGY lane**: \"Are these OKRs outcomes or shipping lists? Recommended: outcomes —\n  output OKRs are the #1 operating-model failure. Canon: Cagan, *Transformed* (SVPG,\n  2024).\"\n- **BUILD lanes (spec-to-repo \u002F saas-scaffolder)**: \"Which validated assumption says this\n  should be built at all? Recommended: link the OST test that survived; building is the\n  most expensive way to test an idea. Canon: Torres; Bland, *Testing Business Ideas*.\"\n\n## Assumptions\n\n1. The user owns (or advises the owner of) the product decision.\n2. Discovery data lives in the workspace as JSON logs — the loop is file-backed and\n   resumable; every tool ships `--sample` so the shape is visible first.\n3. The four standalone plugins are installed alongside the bundle (the router still\n   routes to them by path if not).\n\n## Non-goals\n\n- Not the delivery loop — sprint\u002Fflow\u002FJira work routes to `project-management`.\n- Not the generic loop engine — that is `engineering\u002Fagent-harness`; this orchestrator is\n  the product-domain adapter (router + discovery gates).\n- Not campaign marketing — `marketing\u002Flanding` builds from-scratch marketing pages;\n  `landing-page-generator` here scaffolds product Next.js\u002FTSX pages.\n\n## Output artifacts\n\n| Mode | Artifact |\n|---|---|\n| Route | Sub-skill's own artifact + ≤ 200-word digest with one canon-cited challenge |\n| Discovery loop | `discovery_log.json` + cadence report + linted `ost.json` |\n| Harness run | `.agent-harness\u002Fplan.json` + `state.json` + close handoff |\n\n## Anti-patterns (do not)\n\n- ❌ Run all 16 lanes \"to be thorough\" — route to one, digest, chain on confirmation\n- ❌ Cite an OST that fails the linter, or promote a single-participant anecdote to insight\n- ❌ Ship an AI feature whose PRD has no eval (golden set + rubric)\n- ❌ Let the discovery streak die silently — DORMANT escalates by name\n- ❌ Treat RICE as the only prioritization lens when deadlines dominate\n\n## References\n\n- [references\u002Fcontinuous_discovery_canon.md](references\u002Fcontinuous_discovery_canon.md) —\n  Torres, OST, assumption testing, JTBD switch interviews, story mapping\n- [references\u002Fproduct_operating_model.md](references\u002Fproduct_operating_model.md) — Cagan\n  *Transformed*, North Star framework, PLG benchmarks, WSJF\u002FODI vs RICE\n- [references\u002Fai_product_evals.md](references\u002Fai_product_evals.md) — evals-as-PRD, model\n  cards, evaluator-optimizer loops\n- Loop engine: `engineering\u002Fagent-harness` · Loop vocabulary: `loop-library`\n","# Product Team — Domain Orchestrator & Discovery Loop\n\nThis orchestrator does two jobs. **Routing:** fork context, classify a product inquiry\nwith `scripts\u002Fproduct_goal_router.py` across all 16 product-team lanes (12 bundled + 4\nstandalone plugins), run exactly one, return a digest. **Looping:** run product work as\nbounded agentic loops with machine-checkable gates — the continuous-discovery loop\n(weekly cadence scored by `discovery_cadence_tracker.py`, tree structure enforced by\n`ost_linter.py`) and goal-scale runs through the repo-wide agent-harness.\n\n## When to invoke\n\n| Symptom | Sub-skill |\n|---|---|\n| \"Prioritize features \u002F RICE \u002F PRD\" | `product-manager-toolkit` |\n| \"OKRs, strategy cascade\" | `product-strategist` |\n| \"Personas, usability, research synthesis\" | `ux-researcher-designer` |\n| \"Design tokens, WCAG contrast\" | `ui-design-system` |\n| \"Competitor matrix, teardown\" | `competitive-teardown` |\n| \"Retention, cohorts, funnels, KPIs\" | `product-analytics` |\n| \"A\u002FB test, sample size, hypothesis\" | `experiment-designer` |\n| \"Discovery, assumptions, opportunity trees\" | `product-discovery` |\n| \"Roadmap comms, release notes, changelog\" | `roadmap-communicator` |\n| \"Spec → runnable repo\" | `spec-to-repo` |\n| \"Landing page (Next.js\u002FTailwind)\" | `landing-page-generator` |\n| \"SaaS boilerplate\" | `saas-scaffolder` |\n| \"User stories, sprint capacity\" | `agile-product-owner` (standalone) |\n| \"Apple HIG audit\" | `apple-hig-expert` (standalone) |\n| \"PRD from an existing codebase\" | `code-to-prd` (standalone) |\n| \"Summarize papers\u002Farticles\" | `research-summarizer` (standalone) |\n\n## Routing logic (deterministic)\n\n```bash\npython3 scripts\u002Fproduct_goal_router.py --text \"\u003Cthe goal>\" --output json\n```\n\nExit 0 → `route_to` names the skill (with `skill_path`, including the standalone\nplugins): load its SKILL.md and follow its workflow. Exit 2 → ask ONE clarifying question\nnaming the listed candidates, with a recommended answer. Exit 3 → no signal: ask the user\nto restate the goal with the deliverable named. Never guess silently; never silently\nchain — digest first, confirm, then chain.\n\n## The discovery loop (the domain's recurring agentic loop)\n\nModern discovery is a weekly habit, not a project phase (Torres). Run it as a bounded\nloop with two machine gates:\n\n1. **Observe** — maintain `discovery_log.json` (interviews, assumption tests; shape in\n   `assets\u002Fsample_discovery_log.json`) and score the cadence:\n   ```bash\n   python3 scripts\u002Fdiscovery_cadence_tracker.py --input discovery_log.json\n   ```\n   Refuses on \u003C 2 interviews (exit 5) — there is no cadence to measure yet. Output:\n   health 0–100, verdict HEALTHY\u002FAT-RISK\u002FDORMANT, named gaps, and `next_loop_action`.\n2. **Choose** — the tracker's `next_loop_action` IS the choice: book the touchpoint,\n   re-anchor the guide on the outcome, or test the top untested assumption (route to\n   `product-discovery`'s assumption_mapper for prioritization).\n3. **Act** — run the interview \u002F assumption test with the routed sub-skill's tools.\n4. **Verify** — keep the tree structurally sound before it may drive a roadmap:\n   ```bash\n   python3 scripts\u002Fost_linter.py --input ost.json    # exit 2 = NEEDS-REWORK, fix before citing the tree\n   ```\n   Rules: one measurable outcome root (O1), opportunities are needs not features (O2),\n   targeted opportunities compare ≥ 2 solutions (O3), every solution has an assumption\n   test (O4), no orphan solutions (O5 — the feature-factory tell).\n5. **Record \u002F Repeat-or-stop** — update the log, keep the weekly streak alive. Stop\n   states: HEALTHY + validated assumption → graduate to `experiment-designer` (build the\n   A\u002FB gate) or `product-manager-toolkit` (PRD); DORMANT for 4+ weeks → escalate to the\n   product lead by name — do not quietly let discovery die.\n\nFor build-scale goals (\"turn this validated spec into a repo and verify it\"), compile\nthrough the repo-wide harness instead:\n\n```bash\npython3 engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fscripts\u002Fgoal_compiler.py \\\n  --goal \"\u003Cgoal>\" --manifest engineering\u002Fagent-harness\u002Fskills\u002Fagent-harness\u002Fassets\u002Fharnesses\u002Fproduct-team.json \\\n  --out .agent-harness\u002Fplan.json\n```\n\nThe domain's three strongest close-out gates plug in as task verifications:\n`..\u002Fspec-to-repo\u002Fscripts\u002Fvalidate_project.py` (exit 0), `code-to-prd`'s golden\n`expected_outputs\u002F`, and `research-summarizer`'s citation-count check.\n\n## Hard rules\n\n1. **Evidence before conviction**: no roadmap item cites the OST unless `ost_linter.py`\n   exits 0; no insight is asserted from a single participant (anecdote, not insight).\n2. **Outcome-first**: every loop hangs from one measurable outcome — the linter's O1 rule\n   is the intake gate.\n3. **Experiments are gated by math**: sample size from\n   `..\u002Fexperiment-designer\u002Fscripts\u002Fsample_size_calculator.py`, never gut feel; report the\n   MDE with the verdict.\n4. **Prioritization shows its framework**: RICE for steady-state, WSJF\u002Fcost-of-delay when\n   time sensitivity dominates, opportunity scoring for underserved needs — name which and\n   why (see [references\u002Fproduct_operating_model.md](references\u002Fproduct_operating_model.md)).\n5. **AI features ship with evals**: a golden set + rubric is the PRD's quality contract\n   for probabilistic features\n   ([references\u002Fai_product_evals.md](references\u002Fai_product_evals.md)).\n6. **Never modify a gate you are judged by**; exhausted budgets escalate to a named human,\n   never report as success.\n\n## Forcing-question library (grill-with-docs pattern)\n\nOne per turn, recommended answer, canon citation. Never run a sub-skill or start a loop\nuntil the lane-defining decision is locked:\n\n- **DISCOVERY lane**: \"What is the single outcome this discovery serves, stated with a\n  number? Recommended: write it as the OST root first — opportunities without an outcome\n  are a feature factory. Canon: Torres, *Continuous Discovery Habits*; opportunity\n  solution trees (producttalk.org).\"\n- **PRIORITIZE lane**: \"Does time sensitivity change this ranking — would delaying any\n  item a quarter erode its value? Recommended: if yes, run WSJF\u002Fcost-of-delay alongside\n  RICE and compare ranks; flag items whose rank flips on a one-step estimate change.\n  Canon: Reinertsen, *Principles of Product Development Flow*; SAFe WSJF false-precision\n  critique.\"\n- **EXPERIMENT lane**: \"What baseline rate and MDE justify this test's runtime?\n  Recommended: compute n first; if you can't reach it in 4 weeks, test a bigger lever.\n  Canon: statistical power analysis (experiment-designer).\"\n- **ANALYTICS lane**: \"Is your North Star a leading indicator of value exchange, or\n  revenue\u002Fvanity? Recommended: leading value metric with an input tree. Canon: Amplitude,\n  *The North Star Playbook*.\"\n- **STRATEGY lane**: \"Are these OKRs outcomes or shipping lists? Recommended: outcomes —\n  output OKRs are the #1 operating-model failure. Canon: Cagan, *Transformed* (SVPG,\n  2024).\"\n- **BUILD lanes (spec-to-repo \u002F saas-scaffolder)**: \"Which validated assumption says this\n  should be built at all? Recommended: link the OST test that survived; building is the\n  most expensive way to test an idea. Canon: Torres; Bland, *Testing Business Ideas*.\"\n\n## Assumptions\n\n1. The user owns (or advises the owner of) the product decision.\n2. Discovery data lives in the workspace as JSON logs — the loop is file-backed and\n   resumable; every tool ships `--sample` so the shape is visible first.\n3. The four standalone plugins are installed alongside the bundle (the router still\n   routes to them by path if not).\n\n## Non-goals\n\n- Not the delivery loop — sprint\u002Fflow\u002FJira work routes to `project-management`.\n- Not the generic loop engine — that is `engineering\u002Fagent-harness`; this orchestrator is\n  the product-domain adapter (router + discovery gates).\n- Not campaign marketing — `marketing\u002Flanding` builds from-scratch marketing pages;\n  `landing-page-generator` here scaffolds product Next.js\u002FTSX pages.\n\n## Output artifacts\n\n| Mode | Artifact |\n|---|---|\n| Route | Sub-skill's own artifact + ≤ 200-word digest with one canon-cited challenge |\n| Discovery loop | `discovery_log.json` + cadence report + linted `ost.json` |\n| Harness run | `.agent-harness\u002Fplan.json` + `state.json` + close handoff |\n\n## Anti-patterns (do not)\n\n- ❌ Run all 16 lanes \"to be thorough\" — route to one, digest, chain on confirmation\n- ❌ Cite an OST that fails the linter, or promote a single-participant anecdote to insight\n- ❌ Ship an AI feature whose PRD has no eval (golden set + rubric)\n- ❌ Let the discovery streak die silently — DORMANT escalates by name\n- ❌ Treat RICE as the only prioritization lens when deadlines dominate\n\n## References\n\n- [references\u002Fcontinuous_discovery_canon.md](references\u002Fcontinuous_discovery_canon.md) —\n  Torres, OST, assumption testing, JTBD switch interviews, story mapping\n- [references\u002Fproduct_operating_model.md](references\u002Fproduct_operating_model.md) — Cagan\n  *Transformed*, North Star framework, PLG benchmarks, WSJF\u002FODI vs RICE\n- [references\u002Fai_product_evals.md](references\u002Fai_product_evals.md) — evals-as-PRD, model\n  cards, evaluator-optimizer loops\n- Loop engine: `engineering\u002Fagent-harness` · Loop vocabulary: `loop-library`\n",{"name":5,"tags":62,"author":68,"context":69,"license":14,"version":70,"description":7,"compatible_tools":71},[37,63,64,65,66,55,67],"product-management","orchestrator","discovery","ux","agent-harness","Alireza Rezvani","fork","2.11.1",[72,73,74,75,76,77],"claude-code","codex-cli","cursor","antigravity","opencode","gemini-cli","main","068c2486ccc0f8d200a3db4d21ec137064eda3b4","skills\u002Fpublic-02-claude-skills-main-product-team-skills-product-skills-skill-093adf80","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing","https:\u002F\u002Fgithub.com\u002FJiayiV","2026-08-25 16:30:52",{"source":8,"skillName":5,"commands":85,"prompt":95,"zipAvailable":96},[86,89,92],{"tool":87,"command":88},"npx","npx skills add JiayiV\u002Fquestion_mixing --skill product-skills",{"tool":90,"command":91},"bunx","bunx skills add JiayiV\u002Fquestion_mixing --skill product-skills",{"tool":93,"command":94},"pnpm","pnpm dlx skills add JiayiV\u002Fquestion_mixing --skill product-skills","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fpublic-02-claude-skills-main-product-team-skills-product-skills-skill-093adf80\u002FSKILL.md",true,[],[99,125,152,181,209,242],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":57},"01M6NN9PJS9NHWPDG4QP93BP8F","webmcpify","Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for \"webmcpify\", \"add WebMCP\", or \"expose app actions to AI agents\".","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fwebmcpify\u002FSKILL.md",[],[101,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124],"github","ai agents","web","notes","code","browser","https","actions","manifest","inventory","verify","tool","use","ready","unrelated","app","scope","for","webmcp",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":129,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":57},"01M6NN6KZE5RBN6NGHN2WXV1RE","vardoger-analyze","Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~\u002F.copilot\u002Fsession-state\u002F`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~\u002F.copilot\u002Fcopilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fvardoger-analyze\u002FSKILL.md",[],[133,134,135,136,137,138,54,139,140,141,142,143,144,145,146,147,148,149,150,151],"vardoger analyze","analyze","directory","cli","github copilot","copilot","update","learn","network","my style","install","conversation","me","local","github copilot cli","pipx","my","at","copilot instructions",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":162,"publishedAt":57},"01M6NN3CZGQP3XAJ04BM1NNYGT","transloadit-media-processing","Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS\u002FMP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftransloadit-media-processing\u002FSKILL.md",[158,161],{"categoryNo":159,"categoryName":160,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[163,164,165,166,167,168,169,170,171,172,173,174,175,118,176,177,178,179,123,180],"transloadit media processing","Media","media processing","processing","MCP","mcp server","documents","subtitles","pipeline","ocr","Video","Audio","mp4","images","files","transformation","free","hls",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":190,"publishedAt":57},"01M6NN28E92F9GH4WFYQ2H1Y15","terraform-azurerm-set-diff-analyzer","Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fterraform-azurerm-set-diff-analyzer\u002FSKILL.md",[187],{"categoryNo":188,"categoryName":189,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[191,192,193,194,195,196,197,198,199,118,200,201,202,203,204,205,206,207,208,123],"terraform","SET","terraform azurerm set diff analyzer","diff","analyzer","diffs","azure","gateway","firewall","only","resource changes","provider","resources","load balancer","attributes","front","load","balancer",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":224,"publishedAt":57},"01M6NN1QMH2TDYWTH3XY3N5XPV","technical-job-search","Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV\u002Fresume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Ftechnical-job-search\u002FSKILL.md",[215,218,221],{"categoryNo":216,"categoryName":217,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":219,"categoryName":220,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000036","内容创作者",{"categoryNo":222,"categoryName":223,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000038","人力资源",[225,226,227,228,229,230,231,232,134,233,118,234,235,236,237,238,239,240,123,241],"search","Job Search","technical job search","technical","writing","tasks","email","parsing","interview","up","engineer","general","activate","do","task","cv","letter",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":248,"publishedAt":57},"01M6NMZFA67XYS1GS09WT42235","steno-mode","Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says \"steno mode\", \"shorthand mode\", \"compressed responses\", \"token reduction\", \"brief structured output\", or invokes \u002Fsteno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding\u002Ftutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.","https:\u002F\u002Fgithub.com\u002FJiayiV\u002Fquestion_mixing\u002Fblob\u002Fmain\u002Fskills\u002Fsteno-mode\u002FSKILL.md",[],[249,250,251,252,253,228,254,118,238,255,256,257,258,259,260,261,262,263,123,264],"steno mode","mode","customer","brief","first","tutorial","teaching","tokens","as","trigger","structured output","machine","output","court","requests","response compression"]