[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EXJMMP0QMAWK26N75EDTB4":3,"skill-same:01M7EXJMMP0QMAWK26N75EDTB4":83},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7EXJMMP0QMAWK26N75EDTB4","brand-discovery",null,"Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand tension across 8 modules using laddering, 5 Whys, and projective techniques. Produces a resumable session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).","ronaldwindwaai\u002Fnetsight","ronaldwindwaai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F326191?v=4","01M7EXHGGD3CSAZEGYH4VHYW29","Ronald Windwaai","01M7EXHGH91JB0BD45CXXCHSAD",0,"MIT","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: brand-discovery\ndescription: >-\n  Use when a brand needs to discover or articulate its identity through\n  structured multi-session interviews. Covers purpose, positioning, audience,\n  personality, voice, narrative, and founder-brand tension across 8 modules\n  using laddering, 5 Whys, and projective techniques. Produces a resumable\n  session with disk-persisted state and a master brandbook (90_SYNTHESIS.md).\nlicense: MIT\n---\n\n# Brand Discovery\n\nUse this skill to conduct a structured, adaptive brand identity interview.\nThe goal is a complete `90_SYNTHESIS.md` — a master brandbook the\norganization can use to brief designers, writers, and external\ncollaborators.\n\nThe interview runs across multiple sessions. Capture answers to disk as you\ngo so that no elicited knowledge is lost when a conversation ends, and so a\nlater session can resume from where the last one stopped.\n\n## When to Activate\n\n- A brand is being created, repositioned, or needs a written identity reference to brief collaborators.\n- Multiple sessions are expected — the conversation will span days or weeks.\n- Multiple founders or stakeholders need individual interviews before a reconciliation pass.\n- The user wants a structured, repeatable method rather than an ad-hoc chat.\n- Existing brand documentation is scattered, implicit, or founder-dependent and needs to be made explicit.\n\n## Session start protocol\n\nOn every activation, perform these steps **before** asking any interview\nquestion:\n\n1. **Check for prior progress.** Look for an existing set of module files\n   and a `state.json` checkpoint in the project's brand-identity directory.\n   If none exists, this is a fresh start — confirm the brand name,\n   participants, and where to save the brand-identity files, then begin at\n   the first module.\n2. **Read the current module file** if one is in progress, and scan its Raw\n   section for previously captured answers.\n3. **Report to the user** in two or three sentences: which module we are\n   in, its status, and what remains. Then ask: \"Continue here, or switch\n   module?\"\n\n## Interview discipline\n\nApply these rules throughout every module:\n\n1. **One question at a time.** Never present a list of questions.\n2. **After each answer:** short paraphrase → one deepening probe OR close\n   the thread if the topic is saturated. Never move on silently.\n3. **Laddering:** for every \"what\" answer, follow with \"Why does that\n   matter to you?\" until a core value surfaces (typically two to four\n   iterations).\n4. **5 Whys:** for beliefs or positioning claims — push until the root\n   reason, not the surface declaration, is on the table.\n5. **Detect thin answers:** if generic, jargon-heavy, or vague, ask for\n   one concrete example, a client story, or a number.\n6. **Projective techniques** (use once per module to break a plateau):\n   - \"If the brand were a person, how would they walk into a room?\"\n   - Brand obituary: \"If the organization closed in five years, what would\n     customers miss? What would you regret not having said?\"\n   - Competitive contrast: \"Name one peer you admire but would never want\n     to become. What specifically makes them the wrong model?\"\n7. **Saturation signal:** when two consecutive probes produce no new\n   information, summarise and close the module.\n8. **End of module:** write a structured module file with two sections:\n   - `## Raw` — verbatim quotes and examples.\n   - `## Synthesis` — your interpretation, three candidate formulations,\n     open questions, contradictions between participants.\n   Then update the `state.json` checkpoint (see State protocol below).\n\n## Module sequence\n\n| File | Label | Frameworks used |\n|------|-------|-----------------|\n| `10_purpose-why.md` | Purpose \u002F Why | Sinek Golden Circle, Lencioni |\n| `20_positioning.md` | Positioning | Dunford \"Obviously Awesome\", Moore template |\n| `30_audience-niche.md` | Audience & Niche | Baker \"Business of Expertise\", ICP |\n| `40_personality-archetype.md` | Personality & Archetype | Mark & Pearson 12 archetypes, J. Aaker 5 dims |\n| `50_voice-tone.md` | Voice & Tone | Brand voice guidelines |\n| `60_narrative-story.md` | Narrative \u002F Story | Neumeier trueline, brand story arc |\n| `70_founder-tension.md` | Founder Brands vs Studio Brand | Enns \"Win Without Pitching\" |\n| `90_SYNTHESIS.md` | Master Brandbook | Kapferer prism, Aaker brand system |\n\nComplete modules in order. Honour a user request to jump modules and note\nthe skip in `state.json`.\n\n## State write protocol\n\nAfter each module reaches saturation or done status, write two files:\n\n**Module file** at `modules\u002F{moduleFile}` — full Raw and Synthesis content.\n\n**`state.json`** — a lightweight checkpoint so a later session can resume.\nUpdate `completedModules`, `inProgressModule`, `nextModule`, `lastUpdated`.\nSchema:\n\n```json\n{\n  \"session\": \"{brand_name}-brand-{YYYY-MM}\",\n  \"outputPath\": \"{path_to_brand_identity_directory}\",\n  \"completedModules\": [],\n  \"inProgressModule\": \"10_purpose-why.md\",\n  \"nextModule\": \"20_positioning.md\",\n  \"participants\": [\"founder-A\"],\n  \"lastUpdated\": \"{ISO-8601}\"\n}\n```\n\nAfter writing, confirm: \"Module X saved. State updated. Next: Y.\"\n\n**Terminal module (90_SYNTHESIS.md):** when writing the final synthesis,\nset `inProgressModule` to `\"90_SYNTHESIS.md\"` and `nextModule` to `null`\nin `state.json`. After writing, set `completedModules` to include\n`\"90_SYNTHESIS.md\"`, then set `inProgressModule` to `null` — leaving it\npopulated would cause a future resumption to treat the completed brandbook\nas still in progress. Confirm: \"Brandbook complete. All modules saved.\"\n\n## Multi-founder mode\n\nWhen more than one founder participates, write each founder's answers to\n`founders\u002F{participant}.md` instead of the main module files. Validate the\n`participant` name before writing: accept only alphanumeric characters and\nhyphens (e.g. `founder-a`, `anna`); reject names containing path separators\n(`\u002F`, `\\`, `..`) or special characters. Validate `moduleFile` against the\nenumerated module sequence (10 through 90 only). Validate `outputPath` to\nensure it is an absolute path within the project directory — reject relative\npaths and paths that escape via `..` segments. After all founders complete a\nmodule, run a reconciliation pass: summarise convergences and divergences in\nthe module file, flag \"productive tensions\" for the group alignment workshop.\n\n## Anti-Patterns\n\n- **Starting without reading state first.** Every session must open by checking for existing module files and `state.json`. Skipping this loses all continuity from prior sessions.\n- **Asking multiple questions at once.** One question at a time is not optional — lists produce checklist answers, not real insight.\n- **Moving to Synthesis before saturation.** If the last two probes produced no new information, the module is done. If they did — it isn't.\n- **Skipping multi-founder reconciliation.** When multiple stakeholders are involved, individual interviews must complete before reconciliation. Discussing the brand collectively first introduces anchoring bias.\n- **Treating this as a one-shot session.** This skill is designed for multiple sessions. Rushing to `90_SYNTHESIS.md` in one conversation produces shallow output.\n\n## Related Skills\n\n- `competitive-platform-analysis` — after brand-discovery establishes the positioning brief, use this to scope and categorise the competitor set.\n- `brand-voice` (ECC) — if the brand-discovery voice-and-tone module needs a separate, source-derived writing-style profile.\n","# Brand Discovery\n\nUse this skill to conduct a structured, adaptive brand identity interview.\nThe goal is a complete `90_SYNTHESIS.md` — a master brandbook the\norganization can use to brief designers, writers, and external\ncollaborators.\n\nThe interview runs across multiple sessions. Capture answers to disk as you\ngo so that no elicited knowledge is lost when a conversation ends, and so a\nlater session can resume from where the last one stopped.\n\n## When to Activate\n\n- A brand is being created, repositioned, or needs a written identity reference to brief collaborators.\n- Multiple sessions are expected — the conversation will span days or weeks.\n- Multiple founders or stakeholders need individual interviews before a reconciliation pass.\n- The user wants a structured, repeatable method rather than an ad-hoc chat.\n- Existing brand documentation is scattered, implicit, or founder-dependent and needs to be made explicit.\n\n## Session start protocol\n\nOn every activation, perform these steps **before** asking any interview\nquestion:\n\n1. **Check for prior progress.** Look for an existing set of module files\n   and a `state.json` checkpoint in the project's brand-identity directory.\n   If none exists, this is a fresh start — confirm the brand name,\n   participants, and where to save the brand-identity files, then begin at\n   the first module.\n2. **Read the current module file** if one is in progress, and scan its Raw\n   section for previously captured answers.\n3. **Report to the user** in two or three sentences: which module we are\n   in, its status, and what remains. Then ask: \"Continue here, or switch\n   module?\"\n\n## Interview discipline\n\nApply these rules throughout every module:\n\n1. **One question at a time.** Never present a list of questions.\n2. **After each answer:** short paraphrase → one deepening probe OR close\n   the thread if the topic is saturated. Never move on silently.\n3. **Laddering:** for every \"what\" answer, follow with \"Why does that\n   matter to you?\" until a core value surfaces (typically two to four\n   iterations).\n4. **5 Whys:** for beliefs or positioning claims — push until the root\n   reason, not the surface declaration, is on the table.\n5. **Detect thin answers:** if generic, jargon-heavy, or vague, ask for\n   one concrete example, a client story, or a number.\n6. **Projective techniques** (use once per module to break a plateau):\n   - \"If the brand were a person, how would they walk into a room?\"\n   - Brand obituary: \"If the organization closed in five years, what would\n     customers miss? What would you regret not having said?\"\n   - Competitive contrast: \"Name one peer you admire but would never want\n     to become. What specifically makes them the wrong model?\"\n7. **Saturation signal:** when two consecutive probes produce no new\n   information, summarise and close the module.\n8. **End of module:** write a structured module file with two sections:\n   - `## Raw` — verbatim quotes and examples.\n   - `## Synthesis` — your interpretation, three candidate formulations,\n     open questions, contradictions between participants.\n   Then update the `state.json` checkpoint (see State protocol below).\n\n## Module sequence\n\n| File | Label | Frameworks used |\n|------|-------|-----------------|\n| `10_purpose-why.md` | Purpose \u002F Why | Sinek Golden Circle, Lencioni |\n| `20_positioning.md` | Positioning | Dunford \"Obviously Awesome\", Moore template |\n| `30_audience-niche.md` | Audience & Niche | Baker \"Business of Expertise\", ICP |\n| `40_personality-archetype.md` | Personality & Archetype | Mark & Pearson 12 archetypes, J. Aaker 5 dims |\n| `50_voice-tone.md` | Voice & Tone | Brand voice guidelines |\n| `60_narrative-story.md` | Narrative \u002F Story | Neumeier trueline, brand story arc |\n| `70_founder-tension.md` | Founder Brands vs Studio Brand | Enns \"Win Without Pitching\" |\n| `90_SYNTHESIS.md` | Master Brandbook | Kapferer prism, Aaker brand system |\n\nComplete modules in order. Honour a user request to jump modules and note\nthe skip in `state.json`.\n\n## State write protocol\n\nAfter each module reaches saturation or done status, write two files:\n\n**Module file** at `modules\u002F{moduleFile}` — full Raw and Synthesis content.\n\n**`state.json`** — a lightweight checkpoint so a later session can resume.\nUpdate `completedModules`, `inProgressModule`, `nextModule`, `lastUpdated`.\nSchema:\n\n```json\n{\n  \"session\": \"{brand_name}-brand-{YYYY-MM}\",\n  \"outputPath\": \"{path_to_brand_identity_directory}\",\n  \"completedModules\": [],\n  \"inProgressModule\": \"10_purpose-why.md\",\n  \"nextModule\": \"20_positioning.md\",\n  \"participants\": [\"founder-A\"],\n  \"lastUpdated\": \"{ISO-8601}\"\n}\n```\n\nAfter writing, confirm: \"Module X saved. State updated. Next: Y.\"\n\n**Terminal module (90_SYNTHESIS.md):** when writing the final synthesis,\nset `inProgressModule` to `\"90_SYNTHESIS.md\"` and `nextModule` to `null`\nin `state.json`. After writing, set `completedModules` to include\n`\"90_SYNTHESIS.md\"`, then set `inProgressModule` to `null` — leaving it\npopulated would cause a future resumption to treat the completed brandbook\nas still in progress. Confirm: \"Brandbook complete. All modules saved.\"\n\n## Multi-founder mode\n\nWhen more than one founder participates, write each founder's answers to\n`founders\u002F{participant}.md` instead of the main module files. Validate the\n`participant` name before writing: accept only alphanumeric characters and\nhyphens (e.g. `founder-a`, `anna`); reject names containing path separators\n(`\u002F`, `\\`, `..`) or special characters. Validate `moduleFile` against the\nenumerated module sequence (10 through 90 only). Validate `outputPath` to\nensure it is an absolute path within the project directory — reject relative\npaths and paths that escape via `..` segments. After all founders complete a\nmodule, run a reconciliation pass: summarise convergences and divergences in\nthe module file, flag \"productive tensions\" for the group alignment workshop.\n\n## Anti-Patterns\n\n- **Starting without reading state first.** Every session must open by checking for existing module files and `state.json`. Skipping this loses all continuity from prior sessions.\n- **Asking multiple questions at once.** One question at a time is not optional — lists produce checklist answers, not real insight.\n- **Moving to Synthesis before saturation.** If the last two probes produced no new information, the module is done. If they did — it isn't.\n- **Skipping multi-founder reconciliation.** When multiple stakeholders are involved, individual interviews must complete before reconciliation. Discussing the brand collectively first introduces anchoring bias.\n- **Treating this as a one-shot session.** This skill is designed for multiple sessions. Rushing to `90_SYNTHESIS.md` in one conversation produces shallow output.\n\n## Related Skills\n\n- `competitive-platform-analysis` — after brand-discovery establishes the positioning brief, use this to scope and categorise the competitor set.\n- `brand-voice` (ECC) — if the brand-discovery voice-and-tone module needs a separate, source-derived writing-style profile.\n",{"name":5,"license":15,"description":7},"main","7eaa4602b6f70d0a7930a9771eacc6910126b1e1",".claude\u002F.agents\u002Fskills\u002Fbrand-discovery","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai","www.taburusolutions.com","2026-11-05 15:36:20",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ronaldwindwaai\u002Fnetsight --skill brand-discovery",{"tool":37,"command":38},"bunx","bunx skills add ronaldwindwaai\u002Fnetsight --skill brand-discovery",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ronaldwindwaai\u002Fnetsight --skill brand-discovery","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,79],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"agents\u002Fopenai.yaml","REFERENCE","参考文档",271,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Fagents\u002Fopenai.yaml",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002F10_purpose-why.md",1179,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F10_purpose-why.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002F20_positioning.md",1481,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F20_positioning.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002F30_audience-niche.md",1496,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F30_audience-niche.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002F40_personality-archetype.md",1925,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F40_personality-archetype.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002F50_voice-tone.md",1767,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F50_voice-tone.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002F60_narrative-story.md",1560,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F60_narrative-story.md",{"path":76,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":77,"sourceHtmlUrl":78},"references\u002F70_founder-tension.md",1517,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F70_founder-tension.md",{"path":80,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002F90_SYNTHESIS.md",3063,"https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fbrand-discovery\u002Freferences\u002F90_SYNTHESIS.md",[84,92,99,106,112,119],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":91},"01M7EYB41DSM0Z6MD90B4CQ5G1","verification-loop","Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage, security grep, and diff review — then produce a PASS\u002FFAIL verification report. Use when verifying work after completing a feature or refactor, before creating a PR, or when quality gates must pass.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7EXQ4MKRSRCQEBWBG4P7QWA","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fx-api\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":19},"01M7EXPXVF85KA9AZ0Q11GDN0W","video-editing","AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fvideo-editing\u002FSKILL.md",[],[],{"skillNo":107,"name":86,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":19},"01M7EXPTMVSV0XK1CR2TV891QA","A comprehensive verification system for Claude Code sessions. Use when verifying a Claude Code session's work before claiming it is complete.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":19},"01M7EXPP7DCYTX35S1MHNDP7DJ","unified-memory","Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Funified-memory\u002FSKILL.md",[],[],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":123,"categories":124,"keywords":125,"publishedAt":19},"01M7EXPG0HZEMB054C156KG54Z","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002Fronaldwindwaai\u002Fnetsight\u002Fblob\u002Fmain\u002F.claude\u002F.agents\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[]]