[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MG8FS03BN597MW1DWSJ97T":3,"skill-same:01M6MG8FS03BN597MW1DWSJ97T":62},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6MG8FS03BN597MW1DWSJ97T","eval",null,"Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS\u002FWARN\u002FFAIL per dimension. Use for pre-ship evaluation or regression checks.","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\u002Feval\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32],"performance","Evaluation","baseline","ship","regression","quality","use","comparison","with","correctness","for","modes","pre-ship","outputs","2026-11-10 10:12:30",false,"---\nname: eval\ndescription: \"Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS\u002FWARN\u002FFAIL per dimension. Use for pre-ship evaluation or regression checks.\"\n---\n\n# Eval — Quality & Regression Gate\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic path)` first. Never use `.harness\u002F` in the project directory.\n\n## When to Trigger\n- Before `\u002Fship` creates a PR (automatic if eval.yaml exists)\n- After `\u002Fgo` completes a feature\n- On explicit `\u002Feval` command\n- When user mentions \"regression\", \"baseline\", \"eval suite\", \"quality check\"\n- CI: `make eval` or `epic eval --json`\n\n## Execution Modes\n\n4 dimensions run in parallel where possible:\n\n1. **eval:correctness** — Test pass rate, mutation score, assertion density\n2. **eval:performance** — Throughput, latency, memory (opt-in)\n3. **eval:quality** — Lint, code quality, LLM-as-judge\n4. **eval:regression** — Baseline comparison, score deltas\n\n---\n\n## Process\n\n### Step 0: Prerequisites\n\n```bash\nHARNESS_DIR=$(epic path)\n```\n\nIf `$HARNESS_DIR\u002Feval\u002Feval.yaml` does not exist, run scaffold:\n```bash\nepic eval --init\n```\n\nRead the config:\n```bash\ncat $HARNESS_DIR\u002Feval\u002Feval.yaml\n```\n\n### Step 0.5: Scaffold benchmarks (when no benchmark infrastructure exists)\n\nIf `eval.yaml` has `benchmarks: []` and no benchmark files are found in the project:\n\n1. **Generate stub files** using the CLI:\n   ```bash\n   epic eval --scaffold\n   ```\n   Supported stacks (auto-detected from project markers):\n\n   | Stack | Detected by | Generated file | Output format |\n   |-------|-------------|----------------|---------------|\n   | Rust | `Cargo.toml` | `benches\u002Feval_harness.rs` | criterion (exit code) |\n   | Python | `pyproject.toml` \u002F `setup.py` | `benchmarks\u002Feval_runner.py` | JSON composite |\n   | TypeScript | `tsconfig.json` | `benchmarks\u002Feval.ts` | JSON composite |\n   | Node.js | `package.json` | `benchmarks\u002Feval.mjs` | JSON composite |\n   | Go | `go.mod` | `benchmarks\u002Feval_test.go` | JSON composite |\n   | Java | `pom.xml` \u002F `build.gradle` | `benchmarks\u002FEvalBenchmark.java` | exit code |\n   | Kotlin | `build.gradle.kts` | `benchmarks\u002FEvalBenchmark.kt` | exit code |\n   | Ruby | `Gemfile` | `benchmarks\u002Feval_benchmark.rb` | JSON composite |\n   | PHP | `composer.json` | `benchmarks\u002Feval_benchmark.php` | JSON composite |\n   | C# | `*.csproj` \u002F `*.sln` | `Benchmarks\u002FEvalBenchmark.cs` | JSON composite |\n   | Swift | `Package.swift` | `benchmarks\u002FEvalBenchmark.swift` | JSON composite |\n   | Elixir | `mix.exs` | `benchmarks\u002Feval_benchmark.exs` | JSON composite |\n   | C++ | `CMakeLists.txt` | `benchmarks\u002Feval_benchmark.cpp` | exit code |\n\n2. **Customize the generated file** — every file has `# TODO` \u002F `\u002F\u002F TODO` markers:\n   - Replace placeholder logic with calls to your actual domain functions\n   - Adjust the composite score weights to reflect your domain priorities\n   - For precision\u002Frecall benchmarks: wire in your real test set and model\n\n3. **If `--scaffold` can't generate a useful stub** (domain too complex, custom evaluation logic needed), generate a custom benchmark with LLM assistance:\n   - Read the project's main source files to understand the domain\n   - Identify the 2–3 most critical quality signals (latency, accuracy, throughput, precision\u002Frecall)\n   - Write a benchmark that measures those signals and outputs `{\"composite\": 0.0–1.0, ...}`\n   - Save to `benchmarks\u002Feval_runner.{ext}` matching the project language\n\n4. **Wire into eval.yaml**:\n   ```yaml\n   benchmarks:\n     - name: eval_runner\n       command: python3 benchmarks\u002Feval_runner.py full\n       result_type: composite   # parse composite field from JSON stdout\n   ```\n   Use `result_type: exit_code` for frameworks (criterion, JMH, BenchmarkDotNet) that manage their own output.\n\n### Step 1: Run Rust CLI\n\nExecute the structured evaluation via the Rust binary:\n```bash\nepic eval --json\n```\n\nThis runs all enabled dimensions and outputs a JSON result. Capture the output.\n\nIf the CLI reports `llm_judge: SKIPPED` (no LLM available in CLI mode), proceed to Step 2 for LLM-as-judge. Otherwise, skip to Step 3.\n\n### Step 2: LLM-as-Judge (when llm_judge enabled)\n\nIf the quality dimension has `llm_judge: true` and CLI marked it SKIPPED:\n\n1. Sample 3–5 changed files from the current branch:\n   ```bash\n   git diff --name-only $(git merge-base HEAD main)\n   ```\n\n2. For each sampled file, evaluate on a 1-10 rubric:\n   - **Readability** (naming, structure, flow)\n   - **Correctness** (logic, edge cases, error handling)\n   - **DRY** (no unjustified duplication)\n   - **Security** (no obvious vulnerabilities)\n\n3. Average scores across files. Map to 0.0–1.0 scale.\n\n4. Record results alongside CLI output.\n\n### Step 3: Load Baseline\n\n```bash\ncat $HARNESS_DIR\u002Feval\u002Fbaselines\u002Flatest.json\n```\n\nIf no baseline exists, the current run BECOMES the first baseline. Save it:\n```bash\nepic eval --baseline-update\n```\n\nReport: \"First baseline established. Future runs will compare against this.\"\n\n### Step 4: Synthesize Report\n\nCombine CLI output + LLM-as-judge results into a single report:\n\n```\n## Eval Report\n- Branch: {branch}\n- Commit: {commit_short}\n\n### Correctness: [PASS\u002FWARN\u002FFAIL] — score: {score}\n- Tests: {passed}\u002F{total} passing ({pass_rate}%)\n- Mutation score: {mutation_score}% (if enabled)\n- Delta vs baseline: {+\u002F-delta}\n\n### Performance: [PASS\u002FWARN\u002FFAIL] — score: {score} (if enabled)\n- Avg latency: {latency}ms (delta: {+\u002F-delta})\n- Throughput: {throughput} (delta: {+\u002F-delta})\n\n### Quality: [PASS\u002FWARN\u002FFAIL] — score: {score}\n- Lint errors: {count}\n- LLM judge: {score}\u002F10 (if enabled)\n\n### Regression: [PASS\u002FFAIL]\n| Dimension | Baseline | Current | Delta | Verdict |\n|-----------|----------|---------|-------|---------|\n| correctness | {prev} | {cur} | {delta} | {pass\u002Ffail} |\n| quality | {prev} | {cur} | {delta} | {pass\u002Ffail} |\n\n### Overall: [PASS\u002FWARN\u002FFAIL] — {overall_score}\n```\n\n### Step 5: Act\n\n- **All PASS + no regression**: \"Eval passed. Run `\u002Fship` to create a PR.\"\n- **WARN**: Show warnings. Ask whether to fix before shipping.\n- **FAIL or regression detected**: List each failure with fix hint. \"Fix with `\u002Fgo`, then re-run `\u002Feval`.\"\n\n### Step 6: Save Results\n\n```bash\nepic eval --baseline-update  # if user approves this as new baseline\n```\n\nResults auto-saved to `$HARNESS_DIR\u002Feval\u002Fresults\u002FEVAL-{timestamp}.json`.\n\n---\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"Tests pass, no need for eval\" | Tests pass today but regress tomorrow without baselines | Run eval and establish a baseline |\n| \"Performance testing is premature\" | Latency regressions are invisible until users complain | Enable performance dimension, run benchmarks now |\n| \"Mutation testing is too slow\" | Slow mutation catches bugs fast tests miss | Run on changed modules only (`--dimension correctness`) |\n| \"LLM-as-judge is subjective\" | Subjective beats absent — fixed rubric + averaging reduces variance | Use the 4-axis rubric, average across 3+ files |\n| \"We can add eval later\" | Later never comes; regressions accumulate silently | Start with correctness+quality, add dimensions incrementally |\n| \"CI will catch regressions\" | CI only catches build\u002Ftest failures, not quality drift | Eval measures what CI misses: mutation score, LLM quality |\n\n## Evidence Required\n\n- [ ] `epic eval --json` output captured (all enabled dimensions scored)\n- [ ] Baseline comparison performed (or first baseline established)\n- [ ] Each dimension has PASS\u002FWARN\u002FFAIL verdict\n- [ ] No dimension regressed beyond threshold (or explicit user override)\n- [ ] Results saved to `$HARNESS_DIR\u002Feval\u002Fresults\u002F`\n- [ ] LLM-as-judge scores recorded (if enabled)\n\n## Red Flags\n\n- Reporting PASS without actual `epic eval` output\n- Skipping regression comparison \"because it's the first run\" (first run should ESTABLISH baseline)\n- Reporting PASS with 0 test coverage\n- Ignoring mutation score drops >5%\n- Marking eval PASS when any dimension below minimum threshold\n- Running eval on main branch instead of feature branch\n","# Eval — Quality & Regression Gate\n\n**CRITICAL**: Run `HARNESS_DIR=$(epic path)` first. Never use `.harness\u002F` in the project directory.\n\n## When to Trigger\n- Before `\u002Fship` creates a PR (automatic if eval.yaml exists)\n- After `\u002Fgo` completes a feature\n- On explicit `\u002Feval` command\n- When user mentions \"regression\", \"baseline\", \"eval suite\", \"quality check\"\n- CI: `make eval` or `epic eval --json`\n\n## Execution Modes\n\n4 dimensions run in parallel where possible:\n\n1. **eval:correctness** — Test pass rate, mutation score, assertion density\n2. **eval:performance** — Throughput, latency, memory (opt-in)\n3. **eval:quality** — Lint, code quality, LLM-as-judge\n4. **eval:regression** — Baseline comparison, score deltas\n\n---\n\n## Process\n\n### Step 0: Prerequisites\n\n```bash\nHARNESS_DIR=$(epic path)\n```\n\nIf `$HARNESS_DIR\u002Feval\u002Feval.yaml` does not exist, run scaffold:\n```bash\nepic eval --init\n```\n\nRead the config:\n```bash\ncat $HARNESS_DIR\u002Feval\u002Feval.yaml\n```\n\n### Step 0.5: Scaffold benchmarks (when no benchmark infrastructure exists)\n\nIf `eval.yaml` has `benchmarks: []` and no benchmark files are found in the project:\n\n1. **Generate stub files** using the CLI:\n   ```bash\n   epic eval --scaffold\n   ```\n   Supported stacks (auto-detected from project markers):\n\n   | Stack | Detected by | Generated file | Output format |\n   |-------|-------------|----------------|---------------|\n   | Rust | `Cargo.toml` | `benches\u002Feval_harness.rs` | criterion (exit code) |\n   | Python | `pyproject.toml` \u002F `setup.py` | `benchmarks\u002Feval_runner.py` | JSON composite |\n   | TypeScript | `tsconfig.json` | `benchmarks\u002Feval.ts` | JSON composite |\n   | Node.js | `package.json` | `benchmarks\u002Feval.mjs` | JSON composite |\n   | Go | `go.mod` | `benchmarks\u002Feval_test.go` | JSON composite |\n   | Java | `pom.xml` \u002F `build.gradle` | `benchmarks\u002FEvalBenchmark.java` | exit code |\n   | Kotlin | `build.gradle.kts` | `benchmarks\u002FEvalBenchmark.kt` | exit code |\n   | Ruby | `Gemfile` | `benchmarks\u002Feval_benchmark.rb` | JSON composite |\n   | PHP | `composer.json` | `benchmarks\u002Feval_benchmark.php` | JSON composite |\n   | C# | `*.csproj` \u002F `*.sln` | `Benchmarks\u002FEvalBenchmark.cs` | JSON composite |\n   | Swift | `Package.swift` | `benchmarks\u002FEvalBenchmark.swift` | JSON composite |\n   | Elixir | `mix.exs` | `benchmarks\u002Feval_benchmark.exs` | JSON composite |\n   | C++ | `CMakeLists.txt` | `benchmarks\u002Feval_benchmark.cpp` | exit code |\n\n2. **Customize the generated file** — every file has `# TODO` \u002F `\u002F\u002F TODO` markers:\n   - Replace placeholder logic with calls to your actual domain functions\n   - Adjust the composite score weights to reflect your domain priorities\n   - For precision\u002Frecall benchmarks: wire in your real test set and model\n\n3. **If `--scaffold` can't generate a useful stub** (domain too complex, custom evaluation logic needed), generate a custom benchmark with LLM assistance:\n   - Read the project's main source files to understand the domain\n   - Identify the 2–3 most critical quality signals (latency, accuracy, throughput, precision\u002Frecall)\n   - Write a benchmark that measures those signals and outputs `{\"composite\": 0.0–1.0, ...}`\n   - Save to `benchmarks\u002Feval_runner.{ext}` matching the project language\n\n4. **Wire into eval.yaml**:\n   ```yaml\n   benchmarks:\n     - name: eval_runner\n       command: python3 benchmarks\u002Feval_runner.py full\n       result_type: composite   # parse composite field from JSON stdout\n   ```\n   Use `result_type: exit_code` for frameworks (criterion, JMH, BenchmarkDotNet) that manage their own output.\n\n### Step 1: Run Rust CLI\n\nExecute the structured evaluation via the Rust binary:\n```bash\nepic eval --json\n```\n\nThis runs all enabled dimensions and outputs a JSON result. Capture the output.\n\nIf the CLI reports `llm_judge: SKIPPED` (no LLM available in CLI mode), proceed to Step 2 for LLM-as-judge. Otherwise, skip to Step 3.\n\n### Step 2: LLM-as-Judge (when llm_judge enabled)\n\nIf the quality dimension has `llm_judge: true` and CLI marked it SKIPPED:\n\n1. Sample 3–5 changed files from the current branch:\n   ```bash\n   git diff --name-only $(git merge-base HEAD main)\n   ```\n\n2. For each sampled file, evaluate on a 1-10 rubric:\n   - **Readability** (naming, structure, flow)\n   - **Correctness** (logic, edge cases, error handling)\n   - **DRY** (no unjustified duplication)\n   - **Security** (no obvious vulnerabilities)\n\n3. Average scores across files. Map to 0.0–1.0 scale.\n\n4. Record results alongside CLI output.\n\n### Step 3: Load Baseline\n\n```bash\ncat $HARNESS_DIR\u002Feval\u002Fbaselines\u002Flatest.json\n```\n\nIf no baseline exists, the current run BECOMES the first baseline. Save it:\n```bash\nepic eval --baseline-update\n```\n\nReport: \"First baseline established. Future runs will compare against this.\"\n\n### Step 4: Synthesize Report\n\nCombine CLI output + LLM-as-judge results into a single report:\n\n```\n## Eval Report\n- Branch: {branch}\n- Commit: {commit_short}\n\n### Correctness: [PASS\u002FWARN\u002FFAIL] — score: {score}\n- Tests: {passed}\u002F{total} passing ({pass_rate}%)\n- Mutation score: {mutation_score}% (if enabled)\n- Delta vs baseline: {+\u002F-delta}\n\n### Performance: [PASS\u002FWARN\u002FFAIL] — score: {score} (if enabled)\n- Avg latency: {latency}ms (delta: {+\u002F-delta})\n- Throughput: {throughput} (delta: {+\u002F-delta})\n\n### Quality: [PASS\u002FWARN\u002FFAIL] — score: {score}\n- Lint errors: {count}\n- LLM judge: {score}\u002F10 (if enabled)\n\n### Regression: [PASS\u002FFAIL]\n| Dimension | Baseline | Current | Delta | Verdict |\n|-----------|----------|---------|-------|---------|\n| correctness | {prev} | {cur} | {delta} | {pass\u002Ffail} |\n| quality | {prev} | {cur} | {delta} | {pass\u002Ffail} |\n\n### Overall: [PASS\u002FWARN\u002FFAIL] — {overall_score}\n```\n\n### Step 5: Act\n\n- **All PASS + no regression**: \"Eval passed. Run `\u002Fship` to create a PR.\"\n- **WARN**: Show warnings. Ask whether to fix before shipping.\n- **FAIL or regression detected**: List each failure with fix hint. \"Fix with `\u002Fgo`, then re-run `\u002Feval`.\"\n\n### Step 6: Save Results\n\n```bash\nepic eval --baseline-update  # if user approves this as new baseline\n```\n\nResults auto-saved to `$HARNESS_DIR\u002Feval\u002Fresults\u002FEVAL-{timestamp}.json`.\n\n---\n\n## Anti-Rationalization\n\n| Excuse | Rebuttal | What to do instead |\n|--------|----------|-------------------|\n| \"Tests pass, no need for eval\" | Tests pass today but regress tomorrow without baselines | Run eval and establish a baseline |\n| \"Performance testing is premature\" | Latency regressions are invisible until users complain | Enable performance dimension, run benchmarks now |\n| \"Mutation testing is too slow\" | Slow mutation catches bugs fast tests miss | Run on changed modules only (`--dimension correctness`) |\n| \"LLM-as-judge is subjective\" | Subjective beats absent — fixed rubric + averaging reduces variance | Use the 4-axis rubric, average across 3+ files |\n| \"We can add eval later\" | Later never comes; regressions accumulate silently | Start with correctness+quality, add dimensions incrementally |\n| \"CI will catch regressions\" | CI only catches build\u002Ftest failures, not quality drift | Eval measures what CI misses: mutation score, LLM quality |\n\n## Evidence Required\n\n- [ ] `epic eval --json` output captured (all enabled dimensions scored)\n- [ ] Baseline comparison performed (or first baseline established)\n- [ ] Each dimension has PASS\u002FWARN\u002FFAIL verdict\n- [ ] No dimension regressed beyond threshold (or explicit user override)\n- [ ] Results saved to `$HARNESS_DIR\u002Feval\u002Fresults\u002F`\n- [ ] LLM-as-judge scores recorded (if enabled)\n\n## Red Flags\n\n- Reporting PASS without actual `epic eval` output\n- Skipping regression comparison \"because it's the first run\" (first run should ESTABLISH baseline)\n- Reporting PASS with 0 test coverage\n- Ignoring mutation score drops >5%\n- Marking eval PASS when any dimension below minimum threshold\n- Running eval on main branch instead of feature branch\n",{"name":5,"description":7},"main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Feval",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill eval",{"tool":54,"command":55},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill eval",{"tool":57,"command":58},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill eval","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fepicsagas\u002Fepic-harness\u002Fskills\u002Feval\u002FSKILL.md",true,[],[63,73,81,89,97,105],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":72},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":72},"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":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":72},"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":72},"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":72},"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":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":67,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":72},"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",[],[]]