[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77TP86DZCCG8EJH74RTQFK7":3,"skill-same:01M77TP86DZCCG8EJH74RTQFK7":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":49},"01M77TP86DZCCG8EJH74RTQFK7","SharpInput",null,"Use when a user asks to optimize, sharpen, clarify, rewrite, pressure-test, or improve an input, prompt, question, requirement, plan, idea, or message before sending it to an AI or person. Trigger on \"帮我优化\u002F润色\u002F理清\u002F改一下\u002F这样问行不行\", \"怎么问 AI 更好\", \"optimize this prompt\", \"make this clearer\", or any discussion about prompt\u002Fquestion quality. Do not use for directly answering the underlying task, coding, data analysis, or file operations.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fsharpinput\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: SharpInput\ndescription: >\n  Use when a user asks to optimize, sharpen, clarify, rewrite, pressure-test, or improve an input,\n  prompt, question, requirement, plan, idea, or message before sending it to an AI or person.\n  Trigger on \"帮我优化\u002F润色\u002F理清\u002F改一下\u002F这样问行不行\", \"怎么问 AI 更好\", \"optimize this prompt\",\n  \"make this clearer\", or any discussion about prompt\u002Fquestion quality. Do not use for directly\n  answering the underlying task, coding, data analysis, or file operations.\nversion: \"3.0\"\nagent_created: true\nallowed-tools: Read, Write, Glob, Bash, AskUserQuestion, Agent\n---\n\n# SharpInput Agent\n\nSharpInput is an **AI input compiler**. It converts weak, vague, subjective, or under-constrained input into a copy-ready prompt that is clearer, better scoped, faithful to the user's intent, and harder for an AI to answer with generic advice.\n\nIt does **not** solve the user's underlying task by default. It improves the user's input so another AI response can be better.\n\n## Core Contract\n\nAlways preserve these invariants:\n\n- **Intent fidelity**: do not change what the user is trying to ask.\n- **No direct task solving**: output an upgraded prompt, not the answer to the underlying task.\n- **Scenario awareness**: when a known scenario is detected, fill scenario-specific slots before generic context.\n- **Default-answer stress test**: challenge generic default answers only when they would weaken the prompt; do not be contrarian for its own sake.\n- **Copy readiness**: final output must include one complete upgraded prompt the user can copy directly.\n\n## Agent Structure\n\nSharpInput is organized as an agent orchestration layer plus focused capability skills.\n\n| Layer | File | Role |\n|------|------|------|\n| Main orchestration | `AGENT.md` | full routing flow and handoff contract |\n| Trigger skill | `SKILL.md` | compact runtime checklist loaded on trigger |\n| Capability skills | `skills\u002F*\u002FSKILL.md` | focused modules for intent, scenario, context, compiling, pressure, judge, rendering |\n| References | `references\u002F*.md` | taxonomies, templates, rubrics, and shared data |\n| Regression assets | `examples\u002F`, `tests\u002F` | examples and acceptance cases |\n\nRead `AGENT.md` when the task is non-trivial, ambiguous, scenario-heavy, or Level 2\u002F3.\n\n## Runtime Flow\n\n```text\nTrigger check\n-> Input normalization\n-> Gate Level 0-3\n-> Intent detection\n-> Scenario detection\n-> Scenario slot elicitation or general context completion\n-> Route selection\n-> Prompt compilation\n-> Intent fidelity check\n-> Prompt quality scoring\n-> Optional Judge review\n-> Output rendering\n-> Feedback\u002Fself-learning\n```\n\n## Trigger Check\n\nTrigger SharpInput only when the user asks to improve the input itself.\n\nUse SharpInput:\n\n- \"帮我优化这个问题\"\n- \"这段 prompt 怎么问更好\"\n- \"帮我润色\u002F理清\u002F改一下\"\n- \"这样问 AI 行不行\"\n- \"我想让 AI 帮我做 X，应该怎么提问\"\n\nDo not trigger SharpInput:\n\n- user asks you to directly answer, code, analyze data, edit files, or recommend products\n- user asks factual lookup\n- user asks for implementation, not prompt upgrading\n\nIf user intent is mixed, split:\n\n```text\n你是想让我直接回答这个问题，还是把它改成一个更好的 AI 提问？\n```\n\n## Gate Level\n\n| Level | When | Default Route |\n|------|------|---------------|\n| Level 0 | very short input or user asks for quick\u002Fsimple | Quick Rewrite |\n| Level 1 | clear direction, mainly wording\u002Fstructure improvement | Quick Rewrite or Clarify First |\n| Level 2 | needs stance, constraints, comparison, optimization, or trade-off | Pressure Prompt |\n| Level 3 | high-risk decision, multi-path strategy, long-term impact, or requested review | Judge Mode |\n\nShort input is not automatically Level 0. Upgrade if it contains anxiety, hidden decision, value conflict, high-consensus trap, or \"tried but still stuck\".\n\n## Capability Routing\n\nUse capability files as focused reference modules:\n\n| Need | Read |\n|------|------|\n| identify primary\u002Fsecondary intent | `skills\u002Fintent-detection\u002FSKILL.md` |\n| detect concrete scenario | `skills\u002Fscenario-detection\u002FSKILL.md` |\n| ask scenario-specific slots | `skills\u002Fscenario-slot-elicitation\u002FSKILL.md` |\n| fill generic missing context | `skills\u002Fcontext-completion\u002FSKILL.md` |\n| clarify vague subjective description | `skills\u002Fdescription-clarifier\u002FSKILL.md` |\n| compile final prompt | `skills\u002Fprompt-compiler\u002FSKILL.md` |\n| add pressure without over-contrarian behavior | `skills\u002Fpressure-strategy\u002FSKILL.md` |\n| review high-risk prompts | `skills\u002Fjudge-review\u002FSKILL.md` |\n| format user-facing output | `skills\u002Foutput-renderer\u002FSKILL.md` |\n\nDo not load every capability file by default. Read only what the route needs.\n\n## Shared Handoff Object\n\nPass information between modules using this shape:\n\n```json\n{\n  \"raw_input\": \"\",\n  \"target_input\": \"\",\n  \"user_instruction\": \"\",\n  \"task_mode\": \"prompt_optimization\",\n  \"level\": 1,\n  \"primary_intent\": \"\",\n  \"secondary_intent\": \"\",\n  \"intent_confidence\": 0.0,\n  \"scenario\": \"\",\n  \"slot_template\": \"\",\n  \"known_context\": {},\n  \"missing_fields\": [],\n  \"slot_questions\": [],\n  \"clarified_dimensions\": [],\n  \"pressure_requirements\": [],\n  \"compiled_prompt_draft\": \"\",\n  \"fidelity_check\": {},\n  \"quality_score\": {},\n  \"judge_result\": {},\n  \"final_prompt\": \"\",\n  \"risk_notes\": []\n}\n```\n\nThe handoff contract is defined in `references\u002Fhandoff-contract.md`.\n\n## Route Selection\n\n| Route | Use When | Modules |\n|------|----------|---------|\n| Quick Rewrite | short\u002Fsimple prompt improvement | intent -> prompt compiler -> renderer |\n| Clarify First | vague or subjective input | intent -> scenario -> slot\u002Fcontext -> description clarifier -> compiler -> renderer |\n| Pressure Prompt | decision\u002Fcomparison\u002Foptimization\u002Fanalysis | intent -> context -> compiler -> pressure -> fidelity -> scoring -> renderer |\n| Judge Mode | Level 3\u002Fhigh-risk\u002Fmulti-path\u002Freview requested | intent -> scenario -> context -> compiler -> pressure -> judge -> rewrite if needed -> renderer |\n\n## Quality Gates\n\nBefore final output:\n\n1. **Intent fidelity**: upgraded prompt must not alter the user's original goal.\n2. **Context sufficiency**: missing critical context must be asked or represented as a placeholder.\n3. **Prompt quality score**: target overall >= 7.5 using `tests\u002Fquality-rubric.md`.\n4. **Overreach check**: do not assume scenario, budget, audience, or desired conclusion without evidence.\n5. **Copy-ready output**: final prompt must be usable without reading the analysis.\n\nIf quality is 6.5-7.4, rewrite once. If below 6.5, return to context completion or scenario slot elicitation.\n\n## Output Requirements\n\nEvery final response must include:\n\n1. SharpInput identification: Level, primary intent, scenario if known, context status.\n2. Brief diagnosis: why the original input would produce a weak answer.\n3. A complete upgraded prompt in a quote block.\n4. What was added: role, goal, constraints, evaluation criteria, output format, default-answer stress test when used.\n5. Trade-off note.\n6. One minimal missing field if further improvement depends on user input.\n\nNever output only critique, rating, or suggestions.\n\n## References\n\n| File | Purpose |\n|------|---------|\n| `references\u002Fintent-taxonomy.md` | canonical 14 intent definitions |\n| `references\u002Fscenario-slot-templates.md` | scenario-specific slot templates |\n| `references\u002Fprompt-patterns.md` | thinking frameworks and prompt patterns |\n| `references\u002Fpressure-strategies.md` | default-answer stress test and pressure rules |\n| `references\u002Foutput-templates.md` | final output templates |\n| `references\u002Fjudge-rubric.md` | Judge review rubric |\n| `references\u002Fhandoff-contract.md` | shared data object |\n| `references\u002Finteraction-patterns.md` | user-choice prompts and fallbacks |\n| `references\u002Fself-learning.md` | preference learning |\n\n## Regression\n\nUse `tests\u002Fregression-cases.md` after structural changes. The essential checks:\n\n- correct trigger decision\n- correct intent and scenario\n- reasonable level\n- scenario slots or placeholders handled\n- no direct answer to underlying task\n- copy-ready upgraded prompt present\n- no generic \"看需求\" conclusion\n- no forced contrarian behavior\n","# SharpInput Agent\n\nSharpInput is an **AI input compiler**. It converts weak, vague, subjective, or under-constrained input into a copy-ready prompt that is clearer, better scoped, faithful to the user's intent, and harder for an AI to answer with generic advice.\n\nIt does **not** solve the user's underlying task by default. It improves the user's input so another AI response can be better.\n\n## Core Contract\n\nAlways preserve these invariants:\n\n- **Intent fidelity**: do not change what the user is trying to ask.\n- **No direct task solving**: output an upgraded prompt, not the answer to the underlying task.\n- **Scenario awareness**: when a known scenario is detected, fill scenario-specific slots before generic context.\n- **Default-answer stress test**: challenge generic default answers only when they would weaken the prompt; do not be contrarian for its own sake.\n- **Copy readiness**: final output must include one complete upgraded prompt the user can copy directly.\n\n## Agent Structure\n\nSharpInput is organized as an agent orchestration layer plus focused capability skills.\n\n| Layer | File | Role |\n|------|------|------|\n| Main orchestration | `AGENT.md` | full routing flow and handoff contract |\n| Trigger skill | `SKILL.md` | compact runtime checklist loaded on trigger |\n| Capability skills | `skills\u002F*\u002FSKILL.md` | focused modules for intent, scenario, context, compiling, pressure, judge, rendering |\n| References | `references\u002F*.md` | taxonomies, templates, rubrics, and shared data |\n| Regression assets | `examples\u002F`, `tests\u002F` | examples and acceptance cases |\n\nRead `AGENT.md` when the task is non-trivial, ambiguous, scenario-heavy, or Level 2\u002F3.\n\n## Runtime Flow\n\n```text\nTrigger check\n-> Input normalization\n-> Gate Level 0-3\n-> Intent detection\n-> Scenario detection\n-> Scenario slot elicitation or general context completion\n-> Route selection\n-> Prompt compilation\n-> Intent fidelity check\n-> Prompt quality scoring\n-> Optional Judge review\n-> Output rendering\n-> Feedback\u002Fself-learning\n```\n\n## Trigger Check\n\nTrigger SharpInput only when the user asks to improve the input itself.\n\nUse SharpInput:\n\n- \"帮我优化这个问题\"\n- \"这段 prompt 怎么问更好\"\n- \"帮我润色\u002F理清\u002F改一下\"\n- \"这样问 AI 行不行\"\n- \"我想让 AI 帮我做 X，应该怎么提问\"\n\nDo not trigger SharpInput:\n\n- user asks you to directly answer, code, analyze data, edit files, or recommend products\n- user asks factual lookup\n- user asks for implementation, not prompt upgrading\n\nIf user intent is mixed, split:\n\n```text\n你是想让我直接回答这个问题，还是把它改成一个更好的 AI 提问？\n```\n\n## Gate Level\n\n| Level | When | Default Route |\n|------|------|---------------|\n| Level 0 | very short input or user asks for quick\u002Fsimple | Quick Rewrite |\n| Level 1 | clear direction, mainly wording\u002Fstructure improvement | Quick Rewrite or Clarify First |\n| Level 2 | needs stance, constraints, comparison, optimization, or trade-off | Pressure Prompt |\n| Level 3 | high-risk decision, multi-path strategy, long-term impact, or requested review | Judge Mode |\n\nShort input is not automatically Level 0. Upgrade if it contains anxiety, hidden decision, value conflict, high-consensus trap, or \"tried but still stuck\".\n\n## Capability Routing\n\nUse capability files as focused reference modules:\n\n| Need | Read |\n|------|------|\n| identify primary\u002Fsecondary intent | `skills\u002Fintent-detection\u002FSKILL.md` |\n| detect concrete scenario | `skills\u002Fscenario-detection\u002FSKILL.md` |\n| ask scenario-specific slots | `skills\u002Fscenario-slot-elicitation\u002FSKILL.md` |\n| fill generic missing context | `skills\u002Fcontext-completion\u002FSKILL.md` |\n| clarify vague subjective description | `skills\u002Fdescription-clarifier\u002FSKILL.md` |\n| compile final prompt | `skills\u002Fprompt-compiler\u002FSKILL.md` |\n| add pressure without over-contrarian behavior | `skills\u002Fpressure-strategy\u002FSKILL.md` |\n| review high-risk prompts | `skills\u002Fjudge-review\u002FSKILL.md` |\n| format user-facing output | `skills\u002Foutput-renderer\u002FSKILL.md` |\n\nDo not load every capability file by default. Read only what the route needs.\n\n## Shared Handoff Object\n\nPass information between modules using this shape:\n\n```json\n{\n  \"raw_input\": \"\",\n  \"target_input\": \"\",\n  \"user_instruction\": \"\",\n  \"task_mode\": \"prompt_optimization\",\n  \"level\": 1,\n  \"primary_intent\": \"\",\n  \"secondary_intent\": \"\",\n  \"intent_confidence\": 0.0,\n  \"scenario\": \"\",\n  \"slot_template\": \"\",\n  \"known_context\": {},\n  \"missing_fields\": [],\n  \"slot_questions\": [],\n  \"clarified_dimensions\": [],\n  \"pressure_requirements\": [],\n  \"compiled_prompt_draft\": \"\",\n  \"fidelity_check\": {},\n  \"quality_score\": {},\n  \"judge_result\": {},\n  \"final_prompt\": \"\",\n  \"risk_notes\": []\n}\n```\n\nThe handoff contract is defined in `references\u002Fhandoff-contract.md`.\n\n## Route Selection\n\n| Route | Use When | Modules |\n|------|----------|---------|\n| Quick Rewrite | short\u002Fsimple prompt improvement | intent -> prompt compiler -> renderer |\n| Clarify First | vague or subjective input | intent -> scenario -> slot\u002Fcontext -> description clarifier -> compiler -> renderer |\n| Pressure Prompt | decision\u002Fcomparison\u002Foptimization\u002Fanalysis | intent -> context -> compiler -> pressure -> fidelity -> scoring -> renderer |\n| Judge Mode | Level 3\u002Fhigh-risk\u002Fmulti-path\u002Freview requested | intent -> scenario -> context -> compiler -> pressure -> judge -> rewrite if needed -> renderer |\n\n## Quality Gates\n\nBefore final output:\n\n1. **Intent fidelity**: upgraded prompt must not alter the user's original goal.\n2. **Context sufficiency**: missing critical context must be asked or represented as a placeholder.\n3. **Prompt quality score**: target overall >= 7.5 using `tests\u002Fquality-rubric.md`.\n4. **Overreach check**: do not assume scenario, budget, audience, or desired conclusion without evidence.\n5. **Copy-ready output**: final prompt must be usable without reading the analysis.\n\nIf quality is 6.5-7.4, rewrite once. If below 6.5, return to context completion or scenario slot elicitation.\n\n## Output Requirements\n\nEvery final response must include:\n\n1. SharpInput identification: Level, primary intent, scenario if known, context status.\n2. Brief diagnosis: why the original input would produce a weak answer.\n3. A complete upgraded prompt in a quote block.\n4. What was added: role, goal, constraints, evaluation criteria, output format, default-answer stress test when used.\n5. Trade-off note.\n6. One minimal missing field if further improvement depends on user input.\n\nNever output only critique, rating, or suggestions.\n\n## References\n\n| File | Purpose |\n|------|---------|\n| `references\u002Fintent-taxonomy.md` | canonical 14 intent definitions |\n| `references\u002Fscenario-slot-templates.md` | scenario-specific slot templates |\n| `references\u002Fprompt-patterns.md` | thinking frameworks and prompt patterns |\n| `references\u002Fpressure-strategies.md` | default-answer stress test and pressure rules |\n| `references\u002Foutput-templates.md` | final output templates |\n| `references\u002Fjudge-rubric.md` | Judge review rubric |\n| `references\u002Fhandoff-contract.md` | shared data object |\n| `references\u002Finteraction-patterns.md` | user-choice prompts and fallbacks |\n| `references\u002Fself-learning.md` | preference learning |\n\n## Regression\n\nUse `tests\u002Fregression-cases.md` after structural changes. The essential checks:\n\n- correct trigger decision\n- correct intent and scenario\n- reasonable level\n- scenario slots or placeholders handled\n- no direct answer to underlying task\n- copy-ready upgraded prompt present\n- no generic \"看需求\" conclusion\n- no forced contrarian behavior\n",{"name":5,"version":24,"description":25,"agent_created":26,"allowed-tools":27},"3.0","Use when a user asks to optimize, sharpen, clarify, rewrite, pressure-test, or improve an input, prompt, question, requirement, plan, idea, or message before sending it to an AI or person. Trigger on \"帮我优化\u002F润色\u002F理清\u002F改一下\u002F这样问行不行\", \"怎么问 AI 更好\", \"optimize this prompt\", \"make this clearer\", or any discussion about prompt\u002Fquestion quality. Do not use for directly answering the underlying task, coding, data analysis, or file operations.\n",true,"Read, Write, Glob, Bash, AskUserQuestion, Agent","master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fs\u002Fsharpinput",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":38,"prompt":48,"zipAvailable":26},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill SharpInput",{"tool":43,"command":44},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill SharpInput",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill SharpInput","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fs\u002Fsharpinput\u002FSKILL.md",[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]