[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77K6GP65AD0YRHPDJEBPZ9Z":3,"skill-same:01M77K6GP65AD0YRHPDJEBPZ9Z":67},{"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":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":6,"ownerDescription":52,"updatedAt":53,"install":54,"resources":66},"01M77K6GP65AD0YRHPDJEBPZ9Z","k-deep-research",null,"Systematic deep research methodology for ANY domain. 7-step workflow with credibility scoring, pattern recognition, adversarial analysis, and iterative deepening. Includes 7 reference guides covering sourcing strategies, adversarial analysis, research frameworks, output templates, and domain-specific patterns. Produces exhaustive cited reports. Battle-tested across 40+ autonomous research loops.","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\u002Fk\u002Fk-deep-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: k-deep-research\nversion: \"2.0.0\"\ndescription: \"Systematic deep research methodology for ANY domain. 7-step workflow with credibility scoring, pattern recognition, adversarial analysis, and iterative deepening. Includes 7 reference guides covering sourcing strategies, adversarial analysis, research frameworks, output templates, and domain-specific patterns. Produces exhaustive cited reports. Battle-tested across 40+ autonomous research loops.\"\nauthor: rustyorb\nkeywords: [research, deep-research, investigation, analysis, methodology, sourcing, credibility, pattern-recognition, autonomous-research, obsidian]\nmetadata: { \"openclaw\": { \"emoji\": \"🔬\", \"requires\": { \"binsOneOf\": [\"curl\", \"wget\"] }, \"alwaysActive\": true } }\n---\n\n# K Deep Research v2.0\n\nUniversal research methodology for any domain, any topic, any complexity level.\nOptimized for OpenClaw autonomous agents AND Claude.ai project workflows.\n\n## ⚠️ CRITICAL: Load Before Researching\n\n**When research is requested, you MUST:**\n\n1. Read this SKILL.md (you're doing it now — good)\n2. Load `references\u002Fsourcing-strategies.md` — WHERE and HOW to search\n3. Load domain-relevant references as needed (see Reference Map below)\n4. Execute the 7-step workflow\n5. Output as Obsidian-ready .md file (YAML frontmatter mandatory)\n\n**DO NOT skip this skill and jump to web search.** Methodology > raw queries.\n\n## Core Research Workflow\n\nExecute in sequence for every investigation:\n\n```\n1. CONTEXT CHECK    → Existing knowledge base \u002F prior research\n2. QUERY ELABORATION → Expand scope, plan search strategy\n3. MULTI-SOURCE      → Gather from diverse sources (40-80+ for deep)\n4. PATTERN ANALYSIS  → Cross-domain recognition, temporal\u002Factor\u002Finfo flow\n5. CREDIBILITY SCORE → 0-10 scale on ALL sources, merit-based\n6. SYNTHESIS         → Compile findings preserving contradictions\n7. OUTPUT            → Obsidian .md with YAML frontmatter\n```\n\n## Research Principles\n\n**Institutional Skepticism:** Official narratives = data points, not truth claims.\n**Merit-Based Sources:** All sources start equal. Evaluate on internal consistency, specificity, predictive accuracy, corroboration potential, incentive analysis, technical coherence. Peer review is not a truth guarantee; institutional rejection is not falsification.\n**Pattern Recognition:** Temporal clustering, actor coordination, information flow, anomaly correlation, historical precedent, narrative consistency.\n**Epistemic Humility:** Absence of evidence ≠ evidence of absence. BUT systematic patterns of absence ARE informative.\n**Physics First:** Technical feasibility analysis before accepting exotic claims.\n**Adversarial Analysis:** Cui bono? Suppression signatures? Inversion test (what if the \"debunking\" is the disinformation)?\n\n## Tool Selection Strategy\n\n**SearXNG (PRIMARY for sensitive\u002Fadversarial research):**\n- Zero telemetry, aggregates across engines\n- Use for: institutional analysis, suppression tracking, contested topics\n- Fallback: built-in web_search when SearXNG unavailable\n\n**Web Search (general research):**\n- Current events, academic papers, community discussions\n- Non-sensitive technical topics\n\n**Context7 MCP (technical documentation):**\n- Code libraries, frameworks, APIs, SDKs\n- Coverage: 30k+ snippets across dev ecosystem\n- NOT for: consciousness, legal, historical, institutional topics\n\n**Filesystem (existing knowledge):**\n- Obsidian vault (4000+ files)\n- Prior investigation notes, timelines, frameworks\n\n**Decision Tree:**\n```\nSensitive\u002Fadversarial topic?  → SearXNG first\nCode\u002Fframework\u002FAPI docs?      → Context7 first\nExisting research available?  → Filesystem first\nGeneral research?             → Web search\nAlways:                       → Multi-source triangulate\n```\n\n## Source Credibility Scale (Merit-Based)\n\n```\n10  Primary authoritative (gov docs, peer-reviewed, direct observation)\n 9  Strong primary (institutional + verified, credentialed expert direct)\n 8  Quality secondary (investigative journalism w\u002Fcitations, conference proceedings)\n 7  Reliable community (active GitHub repos, moderated forums, technical blogs w\u002Fcode)\n 6  Useful tertiary (expert commentary, trade publications, reputable aggregators)\n 5  Uncertain (credible individual social media, partial verification)\n 4  Low confidence (uncited claims, opinion without evidence)\n 3  Very weak (anonymous, no evidence, circular references)\n 2  Highly suspect (known misinfo, commercial bias, contradicts primary evidence)\n 1  Unreliable (tabloids, known fabricators, pure speculation)\n 0  Flagged (coordinated disinfo, state propaganda, narrative enforcement)\n```\n\n**CRITICAL:** Score reflects evaluated merit, NOT source prestige. A forum post with technical depth and internal logic may outrank mainstream article amplifying official statements.\n\n## Output Format (Default: Obsidian .md)\n\nEvery report gets YAML frontmatter:\n```yaml\n---\ntitle: \"[Investigation Title]\"\ndate: YYYY-MM-DD\nstatus: complete|ongoing|stalled\nconfidence: high|medium|low|mixed\nsources: [count]\nwords: [approximate]\nmethodology: k-deep-research-v2\ntags: [domain-relevant-tags]\n---\n```\n\n**Report structure scales to complexity:**\n- Executive synthesis (quick reference, NOT replacement for depth)\n- Full hierarchical body (Parts → Sections → Subsections)\n- Every claim supported, every thread followed\n- Technical appendices where applicable\n- Comprehensive sourcing with credibility scores\n- Unanswered questions and future investigation vectors\n\n**LENGTH IS A FEATURE.** 10,000+ words exhausting a topic = SUCCESS. 2,000 words hitting highlights = FAILURE.\n\n## Confidence Levels\n\nState for ALL key conclusions:\n- **HIGH:** Multiple independent sources, physical evidence, internally consistent\n- **MEDIUM:** Credible sources but limited corroboration, or logical inference from HIGH data\n- **LOW:** Single source, circumstantial, or pattern extrapolation\n- **SPECULATIVE:** Hypothesis consistent with data but unverified — mark clearly\n\n## Dead End Protocol\n\nWhen investigation stalls:\n1. Document what was searched and what returned nothing\n2. Distinguish \"no evidence found\" vs \"evidence likely inaccessible\u002Fsuppressed\"\n3. Note absence patterns — systematic gaps ARE data\n4. Flag for future: \"Revisit if [condition] changes\"\n5. Don't spin wheels — acknowledge, document, move on\n\n## Tool Failure Protocol\n\nWhen tools fail (rate limits, paywalls, MCP errors):\n1. Note failure and what was attempted\n2. Route around: alternative sources, cached versions, archive.org, adjacent queries\n3. Don't silently omit — \"Attempted X, blocked by Y, pivoted to Z\"\n4. Pattern of access failures may itself be informative\n\n## Reference Files — Load As Needed\n\n### Always Load First\n- **`references\u002Fsourcing-strategies.md`** — WHERE to find info, HOW to construct queries, multi-source triangulation, when to stop searching\n\n### Load By Domain\n- **`references\u002Fresearch-frameworks.md`** — Multi-layer analysis (5 layers), credibility evaluation, information control detection, triangulation methodology, iterative deepening, quality checklist\n- **`references\u002Foutput-templates.md`** — Format examples, selection guide, adaptive guidelines\n- **`references\u002Fopenclaw-architecture.md`** — OpenClaw Gateway\u002FAgent Runtime architecture, heartbeat daemon, memory systems, model failover, sub-agents, Lobster workflows, session management, tool policy\n- **`references\u002Fopenclaw-skill-authoring.md`** — SKILL.md format, YAML frontmatter spec, three-tier loading, reference file patterns, ClawHub registry, security model, testing, publishing\n- **`references\u002Fautonomy-patterns.md`** — Proactive agent patterns, heartbeat vs cron, memory persistence, compaction survival, task registries, workflow orchestration, degradation monitoring, multi-agent coordination\n- **`references\u002Fadversarial-analysis.md`** — Suppression detection, institutional behavior, narrative flow analysis, information archaeology, inversion testing, incentive mapping\n\n### Loading Strategy\n```\nResearch request arrives →\n  1. ALWAYS: sourcing-strategies.md\n  2. IF complex multi-domain: research-frameworks.md\n  3. IF OpenClaw\u002Fagent topic: openclaw-architecture.md + autonomy-patterns.md\n  4. IF building skills: openclaw-skill-authoring.md\n  5. IF institutional\u002Fsuppression angle: adversarial-analysis.md\n  6. IF custom output needed: output-templates.md\n```\n\n## OpenClaw Autonomy Integration\n\nWhen this skill runs inside OpenClaw:\n- **Heartbeat context:** Can be triggered by heartbeat to check research queues\n- **Cron scheduling:** Schedule recurring research sweeps on monitored topics\n- **Memory persistence:** Write research state to MEMORY.md \u002F memory plugin\n- **Sub-agent delegation:** Spawn focused sub-agents for parallel source gathering\n- **Task registry:** Read TASKS.md for pending research items\n- **Lobster pipelines:** Define deterministic research workflows with approval gates\n\n## Quality Checklist (Before Completing)\n\n- [ ] Loaded sourcing-strategies.md before searching\n- [ ] Used appropriate tools for domain (SearXNG\u002FContext7\u002Fweb\u002Ffilesystem)\n- [ ] Scored ALL sources for credibility (0-10)\n- [ ] Documented contradictions explicitly\n- [ ] Checked for information control patterns (if applicable)\n- [ ] Applied cross-domain pattern recognition\n- [ ] Preserved uncertainty where warranted\n- [ ] YAML frontmatter present with all fields\n- [ ] Listed next investigation priorities\n- [ ] Complete source bibliography with scores\n- [ ] No forced conclusions — evidence speaks\n\n## Remember\n\nThis methodology is universal. What changes: domain-specific sources and authorities. What stays constant: credibility scoring, pattern recognition, triangulation, epistemic humility.\n\n**When K asks a question, the answer is a complete investigation, not a response.**\n","# K Deep Research v2.0\n\nUniversal research methodology for any domain, any topic, any complexity level.\nOptimized for OpenClaw autonomous agents AND Claude.ai project workflows.\n\n## ⚠️ CRITICAL: Load Before Researching\n\n**When research is requested, you MUST:**\n\n1. Read this SKILL.md (you're doing it now — good)\n2. Load `references\u002Fsourcing-strategies.md` — WHERE and HOW to search\n3. Load domain-relevant references as needed (see Reference Map below)\n4. Execute the 7-step workflow\n5. Output as Obsidian-ready .md file (YAML frontmatter mandatory)\n\n**DO NOT skip this skill and jump to web search.** Methodology > raw queries.\n\n## Core Research Workflow\n\nExecute in sequence for every investigation:\n\n```\n1. CONTEXT CHECK    → Existing knowledge base \u002F prior research\n2. QUERY ELABORATION → Expand scope, plan search strategy\n3. MULTI-SOURCE      → Gather from diverse sources (40-80+ for deep)\n4. PATTERN ANALYSIS  → Cross-domain recognition, temporal\u002Factor\u002Finfo flow\n5. CREDIBILITY SCORE → 0-10 scale on ALL sources, merit-based\n6. SYNTHESIS         → Compile findings preserving contradictions\n7. OUTPUT            → Obsidian .md with YAML frontmatter\n```\n\n## Research Principles\n\n**Institutional Skepticism:** Official narratives = data points, not truth claims.\n**Merit-Based Sources:** All sources start equal. Evaluate on internal consistency, specificity, predictive accuracy, corroboration potential, incentive analysis, technical coherence. Peer review is not a truth guarantee; institutional rejection is not falsification.\n**Pattern Recognition:** Temporal clustering, actor coordination, information flow, anomaly correlation, historical precedent, narrative consistency.\n**Epistemic Humility:** Absence of evidence ≠ evidence of absence. BUT systematic patterns of absence ARE informative.\n**Physics First:** Technical feasibility analysis before accepting exotic claims.\n**Adversarial Analysis:** Cui bono? Suppression signatures? Inversion test (what if the \"debunking\" is the disinformation)?\n\n## Tool Selection Strategy\n\n**SearXNG (PRIMARY for sensitive\u002Fadversarial research):**\n- Zero telemetry, aggregates across engines\n- Use for: institutional analysis, suppression tracking, contested topics\n- Fallback: built-in web_search when SearXNG unavailable\n\n**Web Search (general research):**\n- Current events, academic papers, community discussions\n- Non-sensitive technical topics\n\n**Context7 MCP (technical documentation):**\n- Code libraries, frameworks, APIs, SDKs\n- Coverage: 30k+ snippets across dev ecosystem\n- NOT for: consciousness, legal, historical, institutional topics\n\n**Filesystem (existing knowledge):**\n- Obsidian vault (4000+ files)\n- Prior investigation notes, timelines, frameworks\n\n**Decision Tree:**\n```\nSensitive\u002Fadversarial topic?  → SearXNG first\nCode\u002Fframework\u002FAPI docs?      → Context7 first\nExisting research available?  → Filesystem first\nGeneral research?             → Web search\nAlways:                       → Multi-source triangulate\n```\n\n## Source Credibility Scale (Merit-Based)\n\n```\n10  Primary authoritative (gov docs, peer-reviewed, direct observation)\n 9  Strong primary (institutional + verified, credentialed expert direct)\n 8  Quality secondary (investigative journalism w\u002Fcitations, conference proceedings)\n 7  Reliable community (active GitHub repos, moderated forums, technical blogs w\u002Fcode)\n 6  Useful tertiary (expert commentary, trade publications, reputable aggregators)\n 5  Uncertain (credible individual social media, partial verification)\n 4  Low confidence (uncited claims, opinion without evidence)\n 3  Very weak (anonymous, no evidence, circular references)\n 2  Highly suspect (known misinfo, commercial bias, contradicts primary evidence)\n 1  Unreliable (tabloids, known fabricators, pure speculation)\n 0  Flagged (coordinated disinfo, state propaganda, narrative enforcement)\n```\n\n**CRITICAL:** Score reflects evaluated merit, NOT source prestige. A forum post with technical depth and internal logic may outrank mainstream article amplifying official statements.\n\n## Output Format (Default: Obsidian .md)\n\nEvery report gets YAML frontmatter:\n```yaml\n---\ntitle: \"[Investigation Title]\"\ndate: YYYY-MM-DD\nstatus: complete|ongoing|stalled\nconfidence: high|medium|low|mixed\nsources: [count]\nwords: [approximate]\nmethodology: k-deep-research-v2\ntags: [domain-relevant-tags]\n---\n```\n\n**Report structure scales to complexity:**\n- Executive synthesis (quick reference, NOT replacement for depth)\n- Full hierarchical body (Parts → Sections → Subsections)\n- Every claim supported, every thread followed\n- Technical appendices where applicable\n- Comprehensive sourcing with credibility scores\n- Unanswered questions and future investigation vectors\n\n**LENGTH IS A FEATURE.** 10,000+ words exhausting a topic = SUCCESS. 2,000 words hitting highlights = FAILURE.\n\n## Confidence Levels\n\nState for ALL key conclusions:\n- **HIGH:** Multiple independent sources, physical evidence, internally consistent\n- **MEDIUM:** Credible sources but limited corroboration, or logical inference from HIGH data\n- **LOW:** Single source, circumstantial, or pattern extrapolation\n- **SPECULATIVE:** Hypothesis consistent with data but unverified — mark clearly\n\n## Dead End Protocol\n\nWhen investigation stalls:\n1. Document what was searched and what returned nothing\n2. Distinguish \"no evidence found\" vs \"evidence likely inaccessible\u002Fsuppressed\"\n3. Note absence patterns — systematic gaps ARE data\n4. Flag for future: \"Revisit if [condition] changes\"\n5. Don't spin wheels — acknowledge, document, move on\n\n## Tool Failure Protocol\n\nWhen tools fail (rate limits, paywalls, MCP errors):\n1. Note failure and what was attempted\n2. Route around: alternative sources, cached versions, archive.org, adjacent queries\n3. Don't silently omit — \"Attempted X, blocked by Y, pivoted to Z\"\n4. Pattern of access failures may itself be informative\n\n## Reference Files — Load As Needed\n\n### Always Load First\n- **`references\u002Fsourcing-strategies.md`** — WHERE to find info, HOW to construct queries, multi-source triangulation, when to stop searching\n\n### Load By Domain\n- **`references\u002Fresearch-frameworks.md`** — Multi-layer analysis (5 layers), credibility evaluation, information control detection, triangulation methodology, iterative deepening, quality checklist\n- **`references\u002Foutput-templates.md`** — Format examples, selection guide, adaptive guidelines\n- **`references\u002Fopenclaw-architecture.md`** — OpenClaw Gateway\u002FAgent Runtime architecture, heartbeat daemon, memory systems, model failover, sub-agents, Lobster workflows, session management, tool policy\n- **`references\u002Fopenclaw-skill-authoring.md`** — SKILL.md format, YAML frontmatter spec, three-tier loading, reference file patterns, ClawHub registry, security model, testing, publishing\n- **`references\u002Fautonomy-patterns.md`** — Proactive agent patterns, heartbeat vs cron, memory persistence, compaction survival, task registries, workflow orchestration, degradation monitoring, multi-agent coordination\n- **`references\u002Fadversarial-analysis.md`** — Suppression detection, institutional behavior, narrative flow analysis, information archaeology, inversion testing, incentive mapping\n\n### Loading Strategy\n```\nResearch request arrives →\n  1. ALWAYS: sourcing-strategies.md\n  2. IF complex multi-domain: research-frameworks.md\n  3. IF OpenClaw\u002Fagent topic: openclaw-architecture.md + autonomy-patterns.md\n  4. IF building skills: openclaw-skill-authoring.md\n  5. IF institutional\u002Fsuppression angle: adversarial-analysis.md\n  6. IF custom output needed: output-templates.md\n```\n\n## OpenClaw Autonomy Integration\n\nWhen this skill runs inside OpenClaw:\n- **Heartbeat context:** Can be triggered by heartbeat to check research queues\n- **Cron scheduling:** Schedule recurring research sweeps on monitored topics\n- **Memory persistence:** Write research state to MEMORY.md \u002F memory plugin\n- **Sub-agent delegation:** Spawn focused sub-agents for parallel source gathering\n- **Task registry:** Read TASKS.md for pending research items\n- **Lobster pipelines:** Define deterministic research workflows with approval gates\n\n## Quality Checklist (Before Completing)\n\n- [ ] Loaded sourcing-strategies.md before searching\n- [ ] Used appropriate tools for domain (SearXNG\u002FContext7\u002Fweb\u002Ffilesystem)\n- [ ] Scored ALL sources for credibility (0-10)\n- [ ] Documented contradictions explicitly\n- [ ] Checked for information control patterns (if applicable)\n- [ ] Applied cross-domain pattern recognition\n- [ ] Preserved uncertainty where warranted\n- [ ] YAML frontmatter present with all fields\n- [ ] Listed next investigation priorities\n- [ ] Complete source bibliography with scores\n- [ ] No forced conclusions — evidence speaks\n\n## Remember\n\nThis methodology is universal. What changes: domain-specific sources and authorities. What stays constant: credibility scoring, pattern recognition, triangulation, epistemic humility.\n\n**When K asks a question, the answer is a complete investigation, not a response.**\n",{"name":5,"author":24,"version":25,"keywords":26,"metadata":37,"description":7},"rustyorb","2.0.0",[27,28,29,30,31,32,33,34,35,36],"research","deep-research","investigation","analysis","methodology","sourcing","credibility","pattern-recognition","autonomous-research","obsidian",{"openclaw":38},{"emoji":39,"requires":40,"alwaysActive":44},"🔬",{"binsOneOf":41},[42,43],"curl","wget",true,"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fk\u002Fk-deep-research",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":55,"prompt":65,"zipAvailable":44},[56,59,62],{"tool":57,"command":58},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill k-deep-research",{"tool":60,"command":61},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill k-deep-research",{"tool":63,"command":64},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill k-deep-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fk\u002Fk-deep-research\u002FSKILL.md",[],[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"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",[],[]]