[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MG89VWGA17NNCWJTHJ5KMQ":3,"skill-same:01M6MG89VWGA17NNCWJTHJ5KMQ":58},{"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":27,"linkOnly":28,"markdownContent":29,"markdownBody":30,"frontMatter":31,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M6MG89VWGA17NNCWJTHJ5KMQ","discover",null,"Trigger: vague\u002Funfocused request or solution-without-problem. Also invoked via \u002Fdiscover command. Reframes goal before acting.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Fdiscover\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26],"command","auto","goal","trigger","problem","via","vague","request","2026-11-10 10:12:30",false,"---\nname: discover\ndescription: \"Trigger: vague\u002Funfocused request or solution-without-problem. Also invoked via \u002Fdiscover command. Reframes goal before acting.\"\nmodes:\n  - auto   # auto-triggered on vague\u002Funfocused requests\n  - \u002Fdiscover  # explicit invocation\n---\n\n# Discover — Problem Discovery\n\nYou are starting the **Discover** phase. Your job is to help the user articulate what problem they are actually trying to solve, before jumping to solutions or specs.\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic-harness path)` first. NEVER use `.harness\u002F` in the project directory.\n\n## Iron Law\n\nNO SPEC WITHOUT A PROBLEM STATEMENT. Building the wrong thing well is worse than building the right thing poorly.\n\n## Process\n\n### Step 0: Prerequisites\n\n- Resolve harness directory: `HARNESS_DIR=$(epic-harness path)`\n- Read any existing context (CLAUDE.md, README, codebase structure)\n- Check for existing problem statements in `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-*.md`\n- Call `mem_recall` with a hint describing the current topic area\n- Check for past `decision` or `pattern` nodes related to this domain\n- If prior problem exploration exists, reference it: \"We discussed something similar before...\"\n- If existing PROBLEM files are found, review them — the user may be continuing prior work\n\n**Why**: Past context prevents re-exploring ground already covered. The knowledge graph connects today's vague request to yesterday's decisions.\n\n### Step 1: Listen\n\nRead the user's request carefully. Repeat it back in your own words and ask:\n- \"Is that the core of it, or is there more?\"\n\nCategorize the request:\n\n| Category | Signal | Example |\n|----------|--------|---------|\n| Solution without problem | User names a technology or approach | \"Add Redis caching\" |\n| Feature without context | User describes output, not why | \"Build a dashboard\" |\n| Systemic complaint | Broad negative without specifics | \"Everything is slow\" |\n| Vague ambition | Goal with no boundaries | \"Make it better\" |\n| Clear problem | Observable gap stated | \"Login fails for 5% of users\" |\n\n**Why**: Categorization determines the probing technique. Misreading the category leads to wrong questions.\n\n### Step 2: Probe\n\nSelect the technique based on the category identified in Step 1. Ask **max 3 questions per round**, run **max 3 rounds**. If the user can't answer or says \"I'm not sure\", proceed to Frame with what you have.\n\n#### Technique Selection\n\n| User signal | Technique | Core question |\n|---|---|---|\n| Names a solution (\"Add Redis\") | **5 Whys** | \"What's happening that makes you need this?\" → repeat |\n| Describes a feature without why | **JTBD** | \"What situation makes you need this? What would 'done' look like?\" |\n| \"Everything is broken\" | **Fishbone** | \"Which area: People \u002F Process \u002F Technology \u002F Data \u002F Environment?\" |\n| Vague or contradictory | **Socratic** | \"What specifically do you mean by 'X'?\" |\n| Has a vision but no path | **Done looks like** | \"When this works perfectly, what do you see?\" |\n| Uncertain assumptions | **Assumption map** | \"What must be true for this to work?\" |\n\n#### Detailed Technique Reference\n\n**5 Whys** — when the user presents a solution without a problem:\n```\nUser: \"Add Redis caching to the API.\"\n→ \"What's happening that makes you want caching?\"\n→ \"Why is that slow?\"\n→ \"Why does that query take long?\"\n```\nStop when you reach an actionable root cause. Max 5 levels.\n\n**JTBD (Jobs To Be Done)** — when the user describes a feature without context:\n```\nUser: \"Build a dashboard.\"\n→ \"What situation makes you need this?\"\n→ \"What would you do with the information right now?\"\n→ \"What would have to be true for you to say 'this solved it'?\"\n```\nExtract job stories: \"When [situation], I want [motivation], so I can [outcome].\"\n\n**Fishbone** — when the user has a systemic complaint:\n```\nUser: \"Everything is broken.\"\n→ Walk through categories: People, Process, Technology, Data, Environment\n→ \"Which of these areas is the biggest contributor?\"\n→ \"Is this on all branches or specific ones?\"\n```\nMap causes across categories, then narrow to the top 1-2.\n\n**Socratic Questioning** — when the request is vague or contradictory:\n```\nUser: \"Make it more secure.\" \u002F \"I want it to be faster.\"\n→ Clarification: \"What specifically do you mean by 'secure' \u002F 'fast'?\"\n→ Probing assumptions: \"What makes you believe this is the issue?\"\n→ Implications: \"If we change X, what happens to Y?\"\n→ Alternatives: \"What other approaches did you consider?\"\n```\n\n**\"What Does Done Look Like?\"** — when the user has a vision but no path:\n```\n→ \"When this is shipped and working perfectly, what specifically do you see?\"\n→ \"What would I click, what output would appear, what would the logs show?\"\n```\nWork backwards from the concrete end state.\n\n**Assumption Mapping** — when the request depends on uncertain premises:\n```\n→ \"Let me check what we're assuming must be true for this to work.\"\n→ List 4-5 assumptions, ask which are uncertain.\n```\nShaky assumptions become prerequisites.\n\nEach round should narrow the space. If after 2 rounds you have enough to frame, don't force a third.\n\n**Why**: The right technique extracts the real problem in 2-3 rounds instead of 10 random questions. Technique mismatch wastes rounds and frustrates the user.\n\n### Step 3: Frame\n\nSynthesize everything into a structured problem statement:\n\n> **[Who]** experiences **[observable problem]** when **[trigger condition]**, resulting in **[quantified impact]**. The desired state is **[measurable outcome]**.\n\nCapture supporting context:\n- **Root cause** (from 5 Whys) or **Job story** (from JTBD)\n- **Constraints**: timeline, technology, scale, compatibility\n- **Assumptions**: what must be true, which are uncertain\n- **Out of scope**: what this problem explicitly does NOT cover\n\nShow the frame to the user and ask: \"Does this capture the problem accurately?\"\n\n**Why**: A written problem statement is testable. If you can't write one, you haven't discovered the problem yet.\n\n### Step 4: Save\n\nOnce confirmed, save the problem statement:\n\n```bash\nmkdir -p \"$HARNESS_DIR\u002Fspecs\"\n```\n\nWrite to `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-{timestamp}.md` (see Output Format below).\n\nIf the user realizes there are multiple problems during probing, address them one at a time. Each problem gets its own file.\n\n### Step 5: Transition\n\nTell the user: **\"Problem defined. Run `\u002Fspec` to turn this into a buildable specification.\"**\n\nIf the user wants to explore further (e.g., they realize there are actually 3 problems), loop back to Step 2 with the new angle.\n\n**Why**: The transition from problem to spec is natural but explicit. The user owns the decision to move forward.\n\n## When to Trigger\n\n**Auto-trigger** (no command needed):\n- User's request lacks a clear problem or goal\n- User names a technology\u002Fsolution without explaining why\n- User describes symptoms without identifying the underlying issue\n- User says \"I don't know where to start\" or equivalent\n- Request is so broad it could mean 3+ different things\n\n**Explicit invocation** (`\u002Fdiscover`):\n- User wants to formally start the discover phase for a new project or feature\n- User wants to re-explore a problem before re-specifying\n- Continuation from a previous discovery session\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"Let's just start building and figure it out\" | Building without a problem is expensive guessing. | Spend 5 minutes framing the problem. It saves hours of rework. |\n| \"The problem is obvious\" | If it were obvious, you'd have a spec, not a vague request. | Write the problem statement. If it's obvious, it takes 30 seconds. |\n| \"I don't have time for questions\" | You don't have time to build the wrong thing. | Run 2 focused rounds, not 10 open-ended ones. |\n| \"I already told you the problem\" | You told me a solution. The problem is why you need that solution. | Ask one \"why\" question. If the answer reveals the problem, proceed. |\n| \"Can't you just figure it out from the code?\" | Code shows what exists, not what's missing or why it hurts. | Combine code exploration with user context for the full picture. |\n| \"Let me just show you the bug\" | A bug is a symptom, not a problem. Fixing symptoms is whack-a-mole. | Trace the bug to its root cause before jumping to a fix. |\n\n## Evidence Required\n\nBefore claiming the problem is defined, show ALL of these:\n\n- [ ] Problem statement written in the structured format (Who \u002F Problem \u002F When \u002F Impact \u002F Desired state)\n- [ ] Root cause or job story identified\n- [ ] At least one measurable\u002Fobservable criterion for success\n- [ ] User confirmed the frame is accurate\n- [ ] Scope boundaries stated (what's in and out)\n\n**\"I think I understand\" without a written problem statement = guessing.**\n\n## Red Flags\n\n- Jumping to solutions or code during the discovery conversation\n- Asking more than 3 questions per round (overwhelming the user)\n- Running more than 3 rounds without attempting a frame (analysis paralysis)\n- Ignoring when the user says \"I'm not sure\" — that IS information\n- Producing a problem statement the user didn't confirm\n- Confusing symptoms with root causes\n- Framing the problem so broadly it could mean anything (\"improve the system\")\n- Skipping discovery for non-trivial, ambiguous work\n\n## Output Format\n\nSave to `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-{timestamp}.md`:\n\n```markdown\n---\nstatus: framed\ncreated: {ISO-8601 timestamp}\ncontext: {one-line summary}\n---\n\n# Problem: {title}\n\n## Problem Statement\n{Who} experiences {observable problem} when {trigger condition}, resulting in {quantified impact}. The desired state is {measurable outcome}.\n\n## Root Cause \u002F Job Story\n{5 Whys chain or JTBD job story}\n\n## Constraints\n- Timeline: {when is this needed}\n- Technology: {stack constraints}\n- Scale: {expected load\u002Fusers}\n- Compatibility: {backward-compat requirements}\n\n## Assumptions\n- {assumption} — {certain \u002F uncertain}\n- {assumption} — {certain \u002F uncertain}\n\n## Out of Scope\n- {what this problem explicitly does NOT cover}\n```\n","# Discover — Problem Discovery\n\nYou are starting the **Discover** phase. Your job is to help the user articulate what problem they are actually trying to solve, before jumping to solutions or specs.\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic-harness path)` first. NEVER use `.harness\u002F` in the project directory.\n\n## Iron Law\n\nNO SPEC WITHOUT A PROBLEM STATEMENT. Building the wrong thing well is worse than building the right thing poorly.\n\n## Process\n\n### Step 0: Prerequisites\n\n- Resolve harness directory: `HARNESS_DIR=$(epic-harness path)`\n- Read any existing context (CLAUDE.md, README, codebase structure)\n- Check for existing problem statements in `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-*.md`\n- Call `mem_recall` with a hint describing the current topic area\n- Check for past `decision` or `pattern` nodes related to this domain\n- If prior problem exploration exists, reference it: \"We discussed something similar before...\"\n- If existing PROBLEM files are found, review them — the user may be continuing prior work\n\n**Why**: Past context prevents re-exploring ground already covered. The knowledge graph connects today's vague request to yesterday's decisions.\n\n### Step 1: Listen\n\nRead the user's request carefully. Repeat it back in your own words and ask:\n- \"Is that the core of it, or is there more?\"\n\nCategorize the request:\n\n| Category | Signal | Example |\n|----------|--------|---------|\n| Solution without problem | User names a technology or approach | \"Add Redis caching\" |\n| Feature without context | User describes output, not why | \"Build a dashboard\" |\n| Systemic complaint | Broad negative without specifics | \"Everything is slow\" |\n| Vague ambition | Goal with no boundaries | \"Make it better\" |\n| Clear problem | Observable gap stated | \"Login fails for 5% of users\" |\n\n**Why**: Categorization determines the probing technique. Misreading the category leads to wrong questions.\n\n### Step 2: Probe\n\nSelect the technique based on the category identified in Step 1. Ask **max 3 questions per round**, run **max 3 rounds**. If the user can't answer or says \"I'm not sure\", proceed to Frame with what you have.\n\n#### Technique Selection\n\n| User signal | Technique | Core question |\n|---|---|---|\n| Names a solution (\"Add Redis\") | **5 Whys** | \"What's happening that makes you need this?\" → repeat |\n| Describes a feature without why | **JTBD** | \"What situation makes you need this? What would 'done' look like?\" |\n| \"Everything is broken\" | **Fishbone** | \"Which area: People \u002F Process \u002F Technology \u002F Data \u002F Environment?\" |\n| Vague or contradictory | **Socratic** | \"What specifically do you mean by 'X'?\" |\n| Has a vision but no path | **Done looks like** | \"When this works perfectly, what do you see?\" |\n| Uncertain assumptions | **Assumption map** | \"What must be true for this to work?\" |\n\n#### Detailed Technique Reference\n\n**5 Whys** — when the user presents a solution without a problem:\n```\nUser: \"Add Redis caching to the API.\"\n→ \"What's happening that makes you want caching?\"\n→ \"Why is that slow?\"\n→ \"Why does that query take long?\"\n```\nStop when you reach an actionable root cause. Max 5 levels.\n\n**JTBD (Jobs To Be Done)** — when the user describes a feature without context:\n```\nUser: \"Build a dashboard.\"\n→ \"What situation makes you need this?\"\n→ \"What would you do with the information right now?\"\n→ \"What would have to be true for you to say 'this solved it'?\"\n```\nExtract job stories: \"When [situation], I want [motivation], so I can [outcome].\"\n\n**Fishbone** — when the user has a systemic complaint:\n```\nUser: \"Everything is broken.\"\n→ Walk through categories: People, Process, Technology, Data, Environment\n→ \"Which of these areas is the biggest contributor?\"\n→ \"Is this on all branches or specific ones?\"\n```\nMap causes across categories, then narrow to the top 1-2.\n\n**Socratic Questioning** — when the request is vague or contradictory:\n```\nUser: \"Make it more secure.\" \u002F \"I want it to be faster.\"\n→ Clarification: \"What specifically do you mean by 'secure' \u002F 'fast'?\"\n→ Probing assumptions: \"What makes you believe this is the issue?\"\n→ Implications: \"If we change X, what happens to Y?\"\n→ Alternatives: \"What other approaches did you consider?\"\n```\n\n**\"What Does Done Look Like?\"** — when the user has a vision but no path:\n```\n→ \"When this is shipped and working perfectly, what specifically do you see?\"\n→ \"What would I click, what output would appear, what would the logs show?\"\n```\nWork backwards from the concrete end state.\n\n**Assumption Mapping** — when the request depends on uncertain premises:\n```\n→ \"Let me check what we're assuming must be true for this to work.\"\n→ List 4-5 assumptions, ask which are uncertain.\n```\nShaky assumptions become prerequisites.\n\nEach round should narrow the space. If after 2 rounds you have enough to frame, don't force a third.\n\n**Why**: The right technique extracts the real problem in 2-3 rounds instead of 10 random questions. Technique mismatch wastes rounds and frustrates the user.\n\n### Step 3: Frame\n\nSynthesize everything into a structured problem statement:\n\n> **[Who]** experiences **[observable problem]** when **[trigger condition]**, resulting in **[quantified impact]**. The desired state is **[measurable outcome]**.\n\nCapture supporting context:\n- **Root cause** (from 5 Whys) or **Job story** (from JTBD)\n- **Constraints**: timeline, technology, scale, compatibility\n- **Assumptions**: what must be true, which are uncertain\n- **Out of scope**: what this problem explicitly does NOT cover\n\nShow the frame to the user and ask: \"Does this capture the problem accurately?\"\n\n**Why**: A written problem statement is testable. If you can't write one, you haven't discovered the problem yet.\n\n### Step 4: Save\n\nOnce confirmed, save the problem statement:\n\n```bash\nmkdir -p \"$HARNESS_DIR\u002Fspecs\"\n```\n\nWrite to `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-{timestamp}.md` (see Output Format below).\n\nIf the user realizes there are multiple problems during probing, address them one at a time. Each problem gets its own file.\n\n### Step 5: Transition\n\nTell the user: **\"Problem defined. Run `\u002Fspec` to turn this into a buildable specification.\"**\n\nIf the user wants to explore further (e.g., they realize there are actually 3 problems), loop back to Step 2 with the new angle.\n\n**Why**: The transition from problem to spec is natural but explicit. The user owns the decision to move forward.\n\n## When to Trigger\n\n**Auto-trigger** (no command needed):\n- User's request lacks a clear problem or goal\n- User names a technology\u002Fsolution without explaining why\n- User describes symptoms without identifying the underlying issue\n- User says \"I don't know where to start\" or equivalent\n- Request is so broad it could mean 3+ different things\n\n**Explicit invocation** (`\u002Fdiscover`):\n- User wants to formally start the discover phase for a new project or feature\n- User wants to re-explore a problem before re-specifying\n- Continuation from a previous discovery session\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"Let's just start building and figure it out\" | Building without a problem is expensive guessing. | Spend 5 minutes framing the problem. It saves hours of rework. |\n| \"The problem is obvious\" | If it were obvious, you'd have a spec, not a vague request. | Write the problem statement. If it's obvious, it takes 30 seconds. |\n| \"I don't have time for questions\" | You don't have time to build the wrong thing. | Run 2 focused rounds, not 10 open-ended ones. |\n| \"I already told you the problem\" | You told me a solution. The problem is why you need that solution. | Ask one \"why\" question. If the answer reveals the problem, proceed. |\n| \"Can't you just figure it out from the code?\" | Code shows what exists, not what's missing or why it hurts. | Combine code exploration with user context for the full picture. |\n| \"Let me just show you the bug\" | A bug is a symptom, not a problem. Fixing symptoms is whack-a-mole. | Trace the bug to its root cause before jumping to a fix. |\n\n## Evidence Required\n\nBefore claiming the problem is defined, show ALL of these:\n\n- [ ] Problem statement written in the structured format (Who \u002F Problem \u002F When \u002F Impact \u002F Desired state)\n- [ ] Root cause or job story identified\n- [ ] At least one measurable\u002Fobservable criterion for success\n- [ ] User confirmed the frame is accurate\n- [ ] Scope boundaries stated (what's in and out)\n\n**\"I think I understand\" without a written problem statement = guessing.**\n\n## Red Flags\n\n- Jumping to solutions or code during the discovery conversation\n- Asking more than 3 questions per round (overwhelming the user)\n- Running more than 3 rounds without attempting a frame (analysis paralysis)\n- Ignoring when the user says \"I'm not sure\" — that IS information\n- Producing a problem statement the user didn't confirm\n- Confusing symptoms with root causes\n- Framing the problem so broadly it could mean anything (\"improve the system\")\n- Skipping discovery for non-trivial, ambiguous work\n\n## Output Format\n\nSave to `$HARNESS_DIR\u002Fspecs\u002FPROBLEM-{timestamp}.md`:\n\n```markdown\n---\nstatus: framed\ncreated: {ISO-8601 timestamp}\ncontext: {one-line summary}\n---\n\n# Problem: {title}\n\n## Problem Statement\n{Who} experiences {observable problem} when {trigger condition}, resulting in {quantified impact}. The desired state is {measurable outcome}.\n\n## Root Cause \u002F Job Story\n{5 Whys chain or JTBD job story}\n\n## Constraints\n- Timeline: {when is this needed}\n- Technology: {stack constraints}\n- Scale: {expected load\u002Fusers}\n- Compatibility: {backward-compat requirements}\n\n## Assumptions\n- {assumption} — {certain \u002F uncertain}\n- {assumption} — {certain \u002F uncertain}\n\n## Out of Scope\n- {what this problem explicitly does NOT cover}\n```\n",{"name":5,"modes":32,"description":7},[20,33],"\u002Fdiscover","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Fdiscover",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill discover",{"tool":50,"command":51},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill discover",{"tool":53,"command":54},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill discover","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Fdiscover\u002FSKILL.md",true,[],[59,69,77,85,93,101],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":68},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":68},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":68},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":68},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":68},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]