[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MGA4D2H0X16MYC4QVFNDDZ":3,"skill-same:01M6MGA4D2H0X16MYC4QVFNDDZ":69},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":48,"repositoryHtmlUrl":49,"repositoryHomepageUrl":50,"ownerHtmlUrl":51,"ownerBlogUrl":52,"ownerDescription":53,"updatedAt":54,"install":55,"resources":68},"01M6MGA4D2H0X16MYC4QVFNDDZ","vuln-scan",null,"Systematic vulnerability scan across injection, auth, data exposure, and dependencies — traced by reading code, not grepping for keywords. Use when scanning for vulnerabilities, reviewing security, or validating threat models.","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\u002Fvuln-scan\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"vuln scan","scan","models","when","for","data exposure","reading","systematic","across","dependencies","Scanning for Vulnerabilities","security","threat","scanning","use","vulnerability","injection","data","code","auth","vulnerabilities","2026-11-10 10:12:30",false,"---\nname: vuln-scan\ndescription: \"Systematic vulnerability scan across injection, auth, data exposure, and dependencies — traced by reading code, not grepping for keywords. Use when scanning for vulnerabilities, reviewing security, or validating threat models.\"\n---\n\n# Vuln Scan — Systematic Vulnerability Scanner\n\n## Iron Law\n\nCode you haven't traced from input to sink has vulnerabilities you haven't found. A grep hit is a lead, not a finding.\n\n## Process\n\n### Step 0: Load Engagement Context\n\nCheck for `.harness\u002Fengagement.md`. If present, load scope constraints — only scan in-scope paths and respect exclusions.\n\nCheck for `THREAT_MODEL.md` from a previous `\u002Fthreat-model` run. If present, use its threat scenarios as scan targets. If absent, run full-surface scan.\n\n### Step 1: Map Entry Points to Trust Boundaries\n\nEnumerate every place untrusted data enters the system, by reading the code:\n\n- **External → app**: HTTP handlers\u002Frouters, GraphQL resolvers, webhooks, file uploads, form fields, query params, headers\n- **Process boundary**: CLI args, environment variables, IPC, deserialization of stored data (cache, DB rows written earlier, config files)\n- **Client-supplied state**: cookies, JWT claims, API keys, referer\u002Forigin\n\nFor each entry point, note: what validation exists (yes\u002Fno\u002Fpartial), and where the data flows next. This list is the scan's backbone — a scan that cannot name its entry points has not started.\n\n### Step 2: Trace Data Flow to Sinks\n\nFrom each entry point, follow the data by reading code until it reaches a dangerous operation, or dies (validated, parameterized, dropped). Dangerous sink classes:\n\n| Sink class | Examples (non-exhaustive) |\n|-----------|--------------------------|\n| Command\u002Fcode execution | shell invocation, `eval`-family, template engines with code modes, deserialization to live objects |\n| Query construction | string-built SQL, raw-query escapes in any ORM (Knex `raw`, Prisma `$queryRaw`, SQLAlchemy `text()`, Sequelize `literal`, Django `extra`\u002F`raw`, Rails `where(\"...\")` with interpolation) |\n| Filesystem | path joins with user input, upload destinations, archive extraction (zip-slip), file reads driven by request params |\n| Web output | template rendering with non-auto-escaping engines, `innerHTML`-family, redirect targets, header values (CRLF) |\n| Auth decisions | IDOR — object lookups keyed only on user-supplied ids without ownership checks; role checks done client-side or per-endpoint instead of per-object |\n\nRead the surrounding code for every candidate sink. A sink that only receives validated\u002Fparameterized data is not a finding; a sink reachable from an entry point with no validation is.\n\n### Step 3: Reason About Encoding and Context at Each Sink\n\nFor each reachable sink, ask what context the data lands in and whether the encoding matches:\n\n- Interpolated into a SQL string? → parameterize, don't escape\n- Interpolated into a shell string? → arg-array execution, don't quote\n- Rendered into HTML\u002FJS\u002FCSS\u002FURL? → each needs context-specific output encoding; auto-escaping templates cover HTML only when actually enabled for that template\n- Joined into a path? → canonicalize, then verify containment inside the intended root\n- Deserialized? → prefer format + type that cannot instantiate attacker-chosen types\n\n### Step 4: Auth & Data-Exposure Pass\n\n- **Default-deny**: routes\u002Factions missing an auth middleware or check entirely — enumerate handlers and look for the gaps, not the checks\n- **Object-level authorization**: for each handler that reads\u002Fwrites a user-owned object, is ownership verified on THIS request?\n- **Secrets**: hardcoded credentials vs. config\u002Fenv references; secrets in logs, error messages, client bundles, API responses\n- **Error leakage**: verbose errors\u002Fstack traces\u002Fconfig in production paths; error messages that distinguish \"no such user\" from \"wrong password\"\n\n### Step 5: Dependency Pass\n\n```bash\ncargo audit 2>\u002Fdev\u002Fnull || echo \"cargo-audit not installed\"   # Rust\nnpm audit 2>\u002Fdev\u002Fnull || echo \"npm audit not available\"       # Node.js\n```\n\nFor each advisory: is a fix available, and is the vulnerable code path actually reachable from this codebase's usage? Unreachable advisories are LOW\u002FINFO, not silent drops. Also flag actively-used dependencies that are unmaintained (no release in ~2+ years, archived repo) even without a CVE.\n\n### Grep as Accelerator, Not Oracle\n\nGrep is fine for *candidate* sink locations (`raw(`, `exec`, `innerHTML`, `eval`, secret-ish identifiers) — use it to shortlist where to read. It misses framework-specific sinks, aliases, and data built across files. Never report a finding from a grep hit alone; never conclude \"clean\" because grep found nothing.\n\n### Step 6: Produce Output\n\nWrite `VULN-FINDINGS.json`:\n\n```json\n{\n  \"scan_date\": \"ISO-8601\",\n  \"scope\": \"full | incremental\",\n  \"threat_model_ref\": \"THREAT_MODEL.md | null\",\n  \"entry_points_traced\": [\"list every entry point examined — required for clean scans\"],\n  \"findings\": [\n    {\n      \"id\": \"V1\",\n      \"dimension\": \"injection | auth | exposure | dependency\",\n      \"severity\": \"CRITICAL | HIGH | MEDIUM | LOW | INFO\",\n      \"file\": \"path\u002Fto\u002Ffile\",\n      \"line\": 42,\n      \"source\": \"untrusted-input origin (entry point)\",\n      \"sink_chain\": [\"entry function\", \"...\", \"sink function\"],\n      \"description\": \"what was found\",\n      \"validated\": true,\n      \"false_positive\": false,\n      \"reachable\": true,\n      \"mitigated\": false,\n      \"threat_scenario\": \"T1 | null\",\n      \"remediation\": \"one-line fix hint\"\n    }\n  ],\n  \"summary\": {\n    \"total\": 10,\n    \"critical\": 1,\n    \"high\": 3,\n    \"medium\": 4,\n    \"low\": 2,\n    \"false_positives\": 0\n  }\n}\n```\n\n### Step 7: Feed into Triage\n\nAfter producing findings, suggest:\n**\"Run `\u002Ftriage` to validate findings with adversarial review.\"**\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"It's an internal tool \u002F not user-facing\" | Internal boundaries are attack surfaces — lateral movement starts inside. | Trace internal entry points with the same rigor. |\n| \"The framework sanitizes automatically\" | Auto-escaping and parameterization have opt-outs, raw escapes, and edges; business logic is framework-agnostic. | Find the raw\u002Fdangerous escapes and read them. |\n| \"We'll add validation later\" | Later never arrives for paths that already work. | Finding = now; remediation line goes in the output. |\n| \"Grep found nothing, so we're clean\" | Grep misses aliased and framework-specific sinks by construction. | A clean claim requires traced entry points, not an empty grep. |\n| \"Dependencies are vetted\" | Transitive dependencies aren't. | Run the dependency pass every time the lockfile changes. |\n\n## Evidence Required\n\n- [ ] Every finding cites file:line + the untrusted-input origin + the sink call chain\n- [ ] Each finding validated: reachable, not mitigated, severity confirmed\n- [ ] A clean (or low-finding) scan lists `entry_points_traced` — absence of evidence is not evidence of absence\n- [ ] All 4 dimensions completed (injection, auth, exposure, dependency)\n- [ ] VULN-FINDINGS.json written with summary\n- [ ] If THREAT_MODEL.md exists: each threat scenario mapped to findings\n- [ ] No CRITICAL\u002FHIGH finding dismissed without explicit justification\n\n## Red Flags\n\n- Reporting grep hits without reading the surrounding code\n- Skipping framework-specific sink types (ORM raw escapes, non-auto-escaping templates)\n- Claiming clean without naming which entry points were traced\n- Scanning only changed files when full-surface scan was requested\n- Marking findings as false positives without a traced reason\n- VULN-FINDINGS.json with zero findings on a non-trivial codebase — the scan was likely incomplete, not the codebase clean\n","# Vuln Scan — Systematic Vulnerability Scanner\n\n## Iron Law\n\nCode you haven't traced from input to sink has vulnerabilities you haven't found. A grep hit is a lead, not a finding.\n\n## Process\n\n### Step 0: Load Engagement Context\n\nCheck for `.harness\u002Fengagement.md`. If present, load scope constraints — only scan in-scope paths and respect exclusions.\n\nCheck for `THREAT_MODEL.md` from a previous `\u002Fthreat-model` run. If present, use its threat scenarios as scan targets. If absent, run full-surface scan.\n\n### Step 1: Map Entry Points to Trust Boundaries\n\nEnumerate every place untrusted data enters the system, by reading the code:\n\n- **External → app**: HTTP handlers\u002Frouters, GraphQL resolvers, webhooks, file uploads, form fields, query params, headers\n- **Process boundary**: CLI args, environment variables, IPC, deserialization of stored data (cache, DB rows written earlier, config files)\n- **Client-supplied state**: cookies, JWT claims, API keys, referer\u002Forigin\n\nFor each entry point, note: what validation exists (yes\u002Fno\u002Fpartial), and where the data flows next. This list is the scan's backbone — a scan that cannot name its entry points has not started.\n\n### Step 2: Trace Data Flow to Sinks\n\nFrom each entry point, follow the data by reading code until it reaches a dangerous operation, or dies (validated, parameterized, dropped). Dangerous sink classes:\n\n| Sink class | Examples (non-exhaustive) |\n|-----------|--------------------------|\n| Command\u002Fcode execution | shell invocation, `eval`-family, template engines with code modes, deserialization to live objects |\n| Query construction | string-built SQL, raw-query escapes in any ORM (Knex `raw`, Prisma `$queryRaw`, SQLAlchemy `text()`, Sequelize `literal`, Django `extra`\u002F`raw`, Rails `where(\"...\")` with interpolation) |\n| Filesystem | path joins with user input, upload destinations, archive extraction (zip-slip), file reads driven by request params |\n| Web output | template rendering with non-auto-escaping engines, `innerHTML`-family, redirect targets, header values (CRLF) |\n| Auth decisions | IDOR — object lookups keyed only on user-supplied ids without ownership checks; role checks done client-side or per-endpoint instead of per-object |\n\nRead the surrounding code for every candidate sink. A sink that only receives validated\u002Fparameterized data is not a finding; a sink reachable from an entry point with no validation is.\n\n### Step 3: Reason About Encoding and Context at Each Sink\n\nFor each reachable sink, ask what context the data lands in and whether the encoding matches:\n\n- Interpolated into a SQL string? → parameterize, don't escape\n- Interpolated into a shell string? → arg-array execution, don't quote\n- Rendered into HTML\u002FJS\u002FCSS\u002FURL? → each needs context-specific output encoding; auto-escaping templates cover HTML only when actually enabled for that template\n- Joined into a path? → canonicalize, then verify containment inside the intended root\n- Deserialized? → prefer format + type that cannot instantiate attacker-chosen types\n\n### Step 4: Auth & Data-Exposure Pass\n\n- **Default-deny**: routes\u002Factions missing an auth middleware or check entirely — enumerate handlers and look for the gaps, not the checks\n- **Object-level authorization**: for each handler that reads\u002Fwrites a user-owned object, is ownership verified on THIS request?\n- **Secrets**: hardcoded credentials vs. config\u002Fenv references; secrets in logs, error messages, client bundles, API responses\n- **Error leakage**: verbose errors\u002Fstack traces\u002Fconfig in production paths; error messages that distinguish \"no such user\" from \"wrong password\"\n\n### Step 5: Dependency Pass\n\n```bash\ncargo audit 2>\u002Fdev\u002Fnull || echo \"cargo-audit not installed\"   # Rust\nnpm audit 2>\u002Fdev\u002Fnull || echo \"npm audit not available\"       # Node.js\n```\n\nFor each advisory: is a fix available, and is the vulnerable code path actually reachable from this codebase's usage? Unreachable advisories are LOW\u002FINFO, not silent drops. Also flag actively-used dependencies that are unmaintained (no release in ~2+ years, archived repo) even without a CVE.\n\n### Grep as Accelerator, Not Oracle\n\nGrep is fine for *candidate* sink locations (`raw(`, `exec`, `innerHTML`, `eval`, secret-ish identifiers) — use it to shortlist where to read. It misses framework-specific sinks, aliases, and data built across files. Never report a finding from a grep hit alone; never conclude \"clean\" because grep found nothing.\n\n### Step 6: Produce Output\n\nWrite `VULN-FINDINGS.json`:\n\n```json\n{\n  \"scan_date\": \"ISO-8601\",\n  \"scope\": \"full | incremental\",\n  \"threat_model_ref\": \"THREAT_MODEL.md | null\",\n  \"entry_points_traced\": [\"list every entry point examined — required for clean scans\"],\n  \"findings\": [\n    {\n      \"id\": \"V1\",\n      \"dimension\": \"injection | auth | exposure | dependency\",\n      \"severity\": \"CRITICAL | HIGH | MEDIUM | LOW | INFO\",\n      \"file\": \"path\u002Fto\u002Ffile\",\n      \"line\": 42,\n      \"source\": \"untrusted-input origin (entry point)\",\n      \"sink_chain\": [\"entry function\", \"...\", \"sink function\"],\n      \"description\": \"what was found\",\n      \"validated\": true,\n      \"false_positive\": false,\n      \"reachable\": true,\n      \"mitigated\": false,\n      \"threat_scenario\": \"T1 | null\",\n      \"remediation\": \"one-line fix hint\"\n    }\n  ],\n  \"summary\": {\n    \"total\": 10,\n    \"critical\": 1,\n    \"high\": 3,\n    \"medium\": 4,\n    \"low\": 2,\n    \"false_positives\": 0\n  }\n}\n```\n\n### Step 7: Feed into Triage\n\nAfter producing findings, suggest:\n**\"Run `\u002Ftriage` to validate findings with adversarial review.\"**\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"It's an internal tool \u002F not user-facing\" | Internal boundaries are attack surfaces — lateral movement starts inside. | Trace internal entry points with the same rigor. |\n| \"The framework sanitizes automatically\" | Auto-escaping and parameterization have opt-outs, raw escapes, and edges; business logic is framework-agnostic. | Find the raw\u002Fdangerous escapes and read them. |\n| \"We'll add validation later\" | Later never arrives for paths that already work. | Finding = now; remediation line goes in the output. |\n| \"Grep found nothing, so we're clean\" | Grep misses aliased and framework-specific sinks by construction. | A clean claim requires traced entry points, not an empty grep. |\n| \"Dependencies are vetted\" | Transitive dependencies aren't. | Run the dependency pass every time the lockfile changes. |\n\n## Evidence Required\n\n- [ ] Every finding cites file:line + the untrusted-input origin + the sink call chain\n- [ ] Each finding validated: reachable, not mitigated, severity confirmed\n- [ ] A clean (or low-finding) scan lists `entry_points_traced` — absence of evidence is not evidence of absence\n- [ ] All 4 dimensions completed (injection, auth, exposure, dependency)\n- [ ] VULN-FINDINGS.json written with summary\n- [ ] If THREAT_MODEL.md exists: each threat scenario mapped to findings\n- [ ] No CRITICAL\u002FHIGH finding dismissed without explicit justification\n\n## Red Flags\n\n- Reporting grep hits without reading the surrounding code\n- Skipping framework-specific sink types (ORM raw escapes, non-auto-escaping templates)\n- Claiming clean without naming which entry points were traced\n- Scanning only changed files when full-surface scan was requested\n- Marking findings as false positives without a traced reason\n- VULN-FINDINGS.json with zero findings on a non-trivial codebase — the scan was likely incomplete, not the codebase clean\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Fvuln-scan",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":56,"prompt":66,"zipAvailable":67},[57,60,63],{"tool":58,"command":59},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill vuln-scan",{"tool":61,"command":62},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill vuln-scan",{"tool":64,"command":65},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill vuln-scan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Fvuln-scan\u002FSKILL.md",true,[],[70,80,88,96,104,112],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":79},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":84,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":79},"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":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":92,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":79},"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":100,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":79},"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":108,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":79},"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":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":74,"licenseFileUrl":116,"sourceHtmlUrl":117,"categories":118,"keywords":119,"publishedAt":79},"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",[],[]]