[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ES0371FZ24PB3C4JC73WKG":3,"skill-same:01M7ES0371FZ24PB3C4JC73WKG":48},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7ES0371FZ24PB3C4JC73WKG","gaia-debugging",null,"Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix. Use when a GAIA benchmark run reports a failed\u002Fincorrect task_id and you need to root-cause it before resubmitting.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fruflo\u002Fplugins\u002Fruflo-workflows\u002Fskills\u002Fgaia-debugging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gaia-debugging\ndescription: Diagnose why a GAIA question failed — extract trace, classify failure mode, and propose a fix. Use when a GAIA benchmark run reports a failed\u002Fincorrect task_id and you need to root-cause it before resubmitting.\nargument-hint: \"\u003Ctask_id> [--results=\u003Cpath>]\"\nallowed-tools: Bash Read mcp__plugin_ruflo-core_ruflo__memory_search mcp__plugin_ruflo-core_ruflo__memory_store mcp__plugin_ruflo-core_ruflo__agentdb_pattern_search mcp__plugin_ruflo-core_ruflo__agentdb_pattern_store\n---\n\n# GAIA Debugging Skill\n\nWhen a GAIA question fails, systematically diagnose the root cause and propose\na targeted fix.\n\n## When to use\n\n- A specific `task_id` returns the wrong answer or times out\n- Pass-rate dropped between two runs and you need to find the regression\n- You want to understand why a particular question class is consistently failing\n\n## Failure mode taxonomy\n\n| Code | Mode | Symptom | Fix direction |\n|------|------|---------|--------------|\n| TG | Tool Gap | Agent lacks a required tool (no image OCR, no PDF reader) | Add tool to catalogue |\n| RM | Reasoning Miss | Agent has the right data but draws wrong conclusion | Improve system prompt, add CoT instruction |\n| EB | Extraction Bug | Answer is in the trace but `FINAL_ANSWER:` regex fails | Fix answer extraction pattern |\n| LI | Loop Issue | Agent loops (re-asks same tool call) and hits turn limit | Increase max-turns or add loop-detection |\n| DS | Dataset Shift | Ground truth differs from what web currently shows | Flag for HAL dataset audit |\n| AT | API Timeout | Tool call times out; agent never gets the result | Increase per-turn timeout |\n\n## Diagnostic workflow\n\n### Step 1 — Load the question trace\n\n```bash\n# Find the result for the task_id in the latest run\nRESULTS=~\u002F.cache\u002Fruflo\u002Fgaia\u002Fresults-latest.json\nnode -e \"\n  const r = JSON.parse(require('fs').readFileSync('$RESULTS'));\n  const q = r.results.find(x => x.task_id === '$TASK_ID');\n  console.log(JSON.stringify(q, null, 2));\n\"\n```\n\n### Step 2 — Classify the failure\n\nLook at the trace output:\n\n1. **No tools called at all** → RM or configuration issue\n2. **Tool called but returned error** → TG or AT\n3. **Tool returned data, wrong answer** → RM or EB\n4. **Correct answer in trace but marked wrong** → EB\n5. **max-turns hit** → LI or question too hard for current model\n\n### Step 3 — Re-run with extended logging\n\n```bash\nnode v3\u002F@claude-flow\u002Fcli\u002Fbin\u002Fcli.js gaia-bench run \\\n  --level 1 --limit 1 \\\n  --task-id $TASK_ID \\\n  --models claude-sonnet-4-6 \\\n  --max-turns 20 \\\n  --output json\n```\n\n### Step 4 — Apply targeted fix\n\n| Failure | Action |\n|---------|--------|\n| TG — missing web_browse | Verify `gaia-tools\u002Findex.ts` exports `web_browse`; check tool registration |\n| TG — missing image OCR | Add `image_describe` tool call; verify `GOOGLE_AI_API_KEY` |\n| RM — reasoning | Add a system prompt instruction: \"Before answering, list all facts you have gathered\" |\n| EB — extraction | Test the `FINAL_ANSWER_RE` regex against the trace manually |\n| LI — loop | Add a tool-call deduplication guard in `gaia-agent.ts` |\n| AT — timeout | Set `DEFAULT_PER_TURN_TIMEOUT_MS` higher or use `--max-turns` flag |\n\n### Step 5 — Verify fix and store pattern\n\n```bash\n# Re-run the single question\nnode … gaia-bench run --task-id $TASK_ID --models $MODEL --output json\n\n# If now passing, store the pattern\nnpx @claude-flow\u002Fcli@latest memory store \\\n  --namespace gaia-debug-patterns \\\n  --key \"fix-$FAILURE_CODE-$(date +%Y%m%d)\" \\\n  --value \"task_id=$TASK_ID, mode=$FAILURE_CODE, fix=$FIX_DESCRIPTION\"\n```\n\n## Quick reference: tool catalogue check\n\n```bash\nnode -e \"\n  const { createDefaultToolCatalogue } = require('.\u002Fv3\u002F@claude-flow\u002Fcli\u002Fsrc\u002Fbenchmarks\u002Fgaia-tools\u002Findex.js');\n  const cat = createDefaultToolCatalogue({});\n  console.log('Tools registered:', cat.definitions.map(t => t.name));\n\"\n```\n\nExpected: `web_search`, `file_read`, `web_browse`, `image_describe`, `python_exec`\n\n## Pattern storage\n\nAfter resolving a debugging session, store the finding:\n```bash\nnpx @claude-flow\u002Fcli@latest memory store \\\n  --namespace gaia-debug-patterns \\\n  --key \"session-$(date +%Y%m%d-%H%M)\" \\\n  --value '{\"task_id\":\"$TASK_ID\",\"failure_mode\":\"$CODE\",\"fix\":\"$FIX\",\"verified\":true}'\n```\n\nSearch for similar past failures:\n```bash\nnpx @claude-flow\u002Fcli@latest memory search \\\n  --namespace gaia-debug-patterns \\\n  --query \"extraction bug final answer regex\"\n```\n","# GAIA Debugging Skill\n\nWhen a GAIA question fails, systematically diagnose the root cause and propose\na targeted fix.\n\n## When to use\n\n- A specific `task_id` returns the wrong answer or times out\n- Pass-rate dropped between two runs and you need to find the regression\n- You want to understand why a particular question class is consistently failing\n\n## Failure mode taxonomy\n\n| Code | Mode | Symptom | Fix direction |\n|------|------|---------|--------------|\n| TG | Tool Gap | Agent lacks a required tool (no image OCR, no PDF reader) | Add tool to catalogue |\n| RM | Reasoning Miss | Agent has the right data but draws wrong conclusion | Improve system prompt, add CoT instruction |\n| EB | Extraction Bug | Answer is in the trace but `FINAL_ANSWER:` regex fails | Fix answer extraction pattern |\n| LI | Loop Issue | Agent loops (re-asks same tool call) and hits turn limit | Increase max-turns or add loop-detection |\n| DS | Dataset Shift | Ground truth differs from what web currently shows | Flag for HAL dataset audit |\n| AT | API Timeout | Tool call times out; agent never gets the result | Increase per-turn timeout |\n\n## Diagnostic workflow\n\n### Step 1 — Load the question trace\n\n```bash\n# Find the result for the task_id in the latest run\nRESULTS=~\u002F.cache\u002Fruflo\u002Fgaia\u002Fresults-latest.json\nnode -e \"\n  const r = JSON.parse(require('fs').readFileSync('$RESULTS'));\n  const q = r.results.find(x => x.task_id === '$TASK_ID');\n  console.log(JSON.stringify(q, null, 2));\n\"\n```\n\n### Step 2 — Classify the failure\n\nLook at the trace output:\n\n1. **No tools called at all** → RM or configuration issue\n2. **Tool called but returned error** → TG or AT\n3. **Tool returned data, wrong answer** → RM or EB\n4. **Correct answer in trace but marked wrong** → EB\n5. **max-turns hit** → LI or question too hard for current model\n\n### Step 3 — Re-run with extended logging\n\n```bash\nnode v3\u002F@claude-flow\u002Fcli\u002Fbin\u002Fcli.js gaia-bench run \\\n  --level 1 --limit 1 \\\n  --task-id $TASK_ID \\\n  --models claude-sonnet-4-6 \\\n  --max-turns 20 \\\n  --output json\n```\n\n### Step 4 — Apply targeted fix\n\n| Failure | Action |\n|---------|--------|\n| TG — missing web_browse | Verify `gaia-tools\u002Findex.ts` exports `web_browse`; check tool registration |\n| TG — missing image OCR | Add `image_describe` tool call; verify `GOOGLE_AI_API_KEY` |\n| RM — reasoning | Add a system prompt instruction: \"Before answering, list all facts you have gathered\" |\n| EB — extraction | Test the `FINAL_ANSWER_RE` regex against the trace manually |\n| LI — loop | Add a tool-call deduplication guard in `gaia-agent.ts` |\n| AT — timeout | Set `DEFAULT_PER_TURN_TIMEOUT_MS` higher or use `--max-turns` flag |\n\n### Step 5 — Verify fix and store pattern\n\n```bash\n# Re-run the single question\nnode … gaia-bench run --task-id $TASK_ID --models $MODEL --output json\n\n# If now passing, store the pattern\nnpx @claude-flow\u002Fcli@latest memory store \\\n  --namespace gaia-debug-patterns \\\n  --key \"fix-$FAILURE_CODE-$(date +%Y%m%d)\" \\\n  --value \"task_id=$TASK_ID, mode=$FAILURE_CODE, fix=$FIX_DESCRIPTION\"\n```\n\n## Quick reference: tool catalogue check\n\n```bash\nnode -e \"\n  const { createDefaultToolCatalogue } = require('.\u002Fv3\u002F@claude-flow\u002Fcli\u002Fsrc\u002Fbenchmarks\u002Fgaia-tools\u002Findex.js');\n  const cat = createDefaultToolCatalogue({});\n  console.log('Tools registered:', cat.definitions.map(t => t.name));\n\"\n```\n\nExpected: `web_search`, `file_read`, `web_browse`, `image_describe`, `python_exec`\n\n## Pattern storage\n\nAfter resolving a debugging session, store the finding:\n```bash\nnpx @claude-flow\u002Fcli@latest memory store \\\n  --namespace gaia-debug-patterns \\\n  --key \"session-$(date +%Y%m%d-%H%M)\" \\\n  --value '{\"task_id\":\"$TASK_ID\",\"failure_mode\":\"$CODE\",\"fix\":\"$FIX\",\"verified\":true}'\n```\n\nSearch for similar past failures:\n```bash\nnpx @claude-flow\u002Fcli@latest memory search \\\n  --namespace gaia-debug-patterns \\\n  --query \"extraction bug final answer regex\"\n```\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":25},"Bash Read mcp__plugin_ruflo-core_ruflo__memory_search mcp__plugin_ruflo-core_ruflo__memory_store mcp__plugin_ruflo-core_ruflo__agentdb_pattern_search mcp__plugin_ruflo-core_ruflo__agentdb_pattern_store","\u003Ctask_id> [--results=\u003Cpath>]","main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Fruflo\u002Fplugins\u002Fruflo-workflows\u002Fskills\u002Fgaia-debugging",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill gaia-debugging",{"tool":40,"command":41},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill gaia-debugging",{"tool":43,"command":44},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill gaia-debugging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Fruflo\u002Fplugins\u002Fruflo-workflows\u002Fskills\u002Fgaia-debugging\u002FSKILL.md",true,[],[49,56,63,70,78,85],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M7EXRM12046G0GM1WGMMFXCN","ci-cd-and-automation","Automates CI\u002FCD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fci-cd-and-automation\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EXRFYYSJ3Y15AGPDDEWWQD","chrome-devtools","Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to `--slim` mode (MCP configuration).","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-devtools\u002FSKILL.md",[],[],{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EXR6EYPE4X5X1BTAE6QJRV","chrome-cdp","Drive a real Chrome via the Chrome DevTools Protocol (CDP). Ensures a\ndebuggable Chrome is running (launching it if needed) so the agent can\nnavigate, read page content, inspect the DOM, run JavaScript, and take\nscreenshots — without the user typing any launch command. Includes a\nfirst-class \"review a live running app\" flow: point Chrome at the app under\ndevelopment and inspect\u002Fscreenshot the REAL page (what a static-artifact tool\ncannot do). Backed by Glimpse and the chrome-devtools MCP server. Use when\nasked to \"use chrome\", \"open chrome\", \"drive my browser\", \"read the page in\nchrome\", \"review the running app\", \"screenshot the app\", or \"\u002Fchrome-cdp\".","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchrome-cdp\u002FSKILL.md",[],[],{"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":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7EXR1Y7E79KQKG4J798XGH6","check-identity-pack","Run an AFP 100-point or AUSTRAC safe-harbour identity check over a set of documents, and report exactly what's missing. Use when the user asks to check identity documents, verify someone's ID for onboarding, or assess whether a document pack satisfies Australian identity requirements.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcheck-identity-pack\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7EXQXW7C7PGREJW9ZZTZ16H","changelog","Auto-generates a changelog from git commits, sprint data, and design documents. Produces both internal and player-facing versions.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fchangelog\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":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7EXQMH2ZME3ANN8Q8MEWPFB","cellxgene-census","Query the CZ CELLxGENE Census programmatically for versioned public single-cell and spatial transcriptomics data. Use when you need population-scale cell metadata, gene expression slices, Census summary counts, source H5AD URIs\u002Fdownloads, embeddings, spatial Census data, or reference atlas comparisons across organisms, tissues, diseases, assays, and cell types. For analyzing your own local single-cell data use scanpy, anndata, or scvi-tools.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fcellxgene-census\u002FSKILL.md",[],[]]