[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75D4S38CRV3RY74BPVA0QM5":3,"skill-same:01M75D4S38CRV3RY74BPVA0QM5":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75D4S38CRV3RY74BPVA0QM5","discover-tasks",null,"Use when user asks to \"discover tasks\", \"find next task\", \"prioritize issues\", \"what should I work on\", or \"list open issues\". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fdiscover-tasks\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: discover-tasks\ndescription: \"Use when user asks to \\\"discover tasks\\\", \\\"find next task\\\", \\\"prioritize issues\\\", \\\"what should I work on\\\", or \\\"list open issues\\\". Discovers and ranks tasks from GitHub, GitLab, local files, and custom sources.\"\nversion: 5.1.1\nallowed-tools: \"Bash(gh:*), Bash(glab:*), Bash(git:*), Bash(grep:*), Grep, Read, AskUserQuestion\"\n---\n\n# discover-tasks\n\nDiscover tasks from configured sources, validate them, and present for user selection.\n\n## When to Use\n\nInvoked during Phase 2 of `\u002Fnext-task` workflow, after policy selection. Also usable standalone when the user wants to discover and select tasks from configured sources.\n\n## Workflow\n\n### Phase 1: Load Policy and Claimed Tasks\n\n```javascript\n\u002F\u002F Use relative path from skill directory to plugin lib\n\u002F\u002F Path: skills\u002Fdiscover-tasks\u002F -> ..\u002F..\u002Flib\u002Fstate\u002Fworkflow-state.js\nconst workflowState = require('..\u002F..\u002Flib\u002Fstate\u002Fworkflow-state.js');\n\nconst state = workflowState.readState();\nconst policy = state.policy;\n\n\u002F\u002F Load claimed task IDs from registry (tasks[] contains worktree-manager claims)\nconst tasksRegistry = workflowState.readTasks();\nconst claimedIds = new Set(tasksRegistry.tasks.map(t => t.id));\n```\n\n### Phase 2: Fetch Tasks by Source\n\n**Source types:**\n- `github` \u002F `gh-issues`: GitHub CLI\n- `gh-projects`: GitHub Projects (v2 boards)\n- `gitlab`: GitLab CLI\n- `local` \u002F `tasks-md`: Local markdown files\n- `custom`: CLI\u002FMCP\u002FSkill tool\n- `other`: Agent interprets description\n\n**GitHub Issues:**\n```bash\n# Fetch with pagination awareness\ngh issue list --state open \\\n  --json number,title,body,labels,assignees,createdAt,url \\\n  --limit 100 > \u002Ftmp\u002Fgh-issues.json\n```\n\n**GitLab Issues:**\n```bash\nglab issue list --state opened --output json --per-page 100 > \u002Ftmp\u002Fglab-issues.json\n```\n\n**Local tasks.md:**\n```bash\nfor f in PLAN.md tasks.md TODO.md; do\n  [ -f \"$f\" ] && grep -n '^\\s*- \\[ \\]' \"$f\"\ndone\n```\n\n**GitHub Projects (v2):**\n```javascript\n\u002F\u002F Extract gh-projects parameters from policy\nconst projectNumber = policy.taskSource.projectNumber;\nconst owner = policy.taskSource.owner;\nif (!projectNumber || !owner) {\n  throw new Error('gh-projects source missing projectNumber or owner in policy.taskSource');\n}\n```\n\n```bash\n# Requires 'project' token scope. If permission error: gh auth refresh -s project\ngh project item-list \"$PROJECT_NUMBER\" --owner \"$OWNER\" --format json --limit 100 > \u002Ftmp\u002Fgh-project-items.json\n```\n\n```javascript\nconst fs = require('fs');\nconst raw = JSON.parse(fs.readFileSync('\u002Ftmp\u002Fgh-project-items.json', 'utf8'));\nconst items = (raw.items || []);\n\n\u002F\u002F Filter to ISSUE type only (exclude PULL_REQUEST, DRAFT_ISSUE)\nconst issues = items\n  .filter(item => item.content && item.content.type === 'ISSUE')\n  .map(item => ({\n    number: item.content.number,\n    title: item.content.title,\n    body: item.content.body || '',\n    labels: (item.content.labels || []).map(l => typeof l === 'object' ? l.name || '' : l).filter(Boolean),\n    url: item.content.url,\n    createdAt: item.content.createdAt\n  }));\n```\n\n[WARN] If `gh project item-list` returns a permission error, tell the user:\n`Run: gh auth refresh -s project`\n\n**Custom Source:**\n```javascript\nconst { sources } = require('..\u002F..\u002Flib');\nconst capabilities = sources.getToolCapabilities(toolName);\n\u002F\u002F Execute capabilities.commands.list_issues\n```\n\n### Phase 2.5: Collect PR-Linked Issues (GitHub only)\n\n```javascript\n\u002F\u002F Default for non-GitHub sources - always defined so Phase 3 filter is safe\nlet prLinkedIssues = new Set();\n```\n\nFor GitHub sources (`policy.taskSource?.source === 'github'`, `'gh-issues'`, or `'gh-projects'`), fetch all open PRs and build a Set of issue numbers that already have an associated PR. Skip to Phase 3 for all other sources.\n\n```bash\n# Only run when policy.taskSource?.source is 'github', 'gh-issues', or 'gh-projects'\n# Note: covers up to 100 open PRs. If repo has more, some linked issues may not be excluded.\ngh pr list --state open --json number,title,body,headRefName --limit 100 > \u002Ftmp\u002Fgh-prs.json\n```\n\n```javascript\nconst fs = require('fs');\ntry {\n  const prs = JSON.parse(fs.readFileSync('\u002Ftmp\u002Fgh-prs.json', 'utf8') || '[]');\n\n  for (const pr of prs) {\n    \u002F\u002F 1. Branch name suffix: fix\u002Fsome-thing-123 extracts 123\n    \u002F\u002F Note: heuristic - branches like \"release-2026\" will false-positive on issue #2026.\n    \u002F\u002F Patterns 2 and 3 are more precise; this is a best-effort supplement.\n    const branchMatch = (pr.headRefName || '').match(\u002F-(\\d+)$\u002F);\n    if (branchMatch) prLinkedIssues.add(branchMatch[1]);\n\n    \u002F\u002F 2. PR body closing keywords (GitHub's full keyword set, with word boundary)\n    if (pr.body) {\n      const bodyMatches = pr.body.matchAll(\u002F\\b(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\\s+#(\\d+)\u002Fgi);\n      for (const m of bodyMatches) prLinkedIssues.add(m[1]);\n    }\n\n    \u002F\u002F 3. PR title (#N) convention - capture all occurrences\n    const titleMatches = (pr.title || '').matchAll(\u002F\\(#(\\d+)\\)\u002Fg);\n    for (const m of titleMatches) prLinkedIssues.add(m[1]);\n  }\n} catch (e) {\n  console.log('[WARN] Could not parse open PRs, skipping PR-link filter:', e.message);\n  prLinkedIssues = new Set();\n}\n```\n\n### Phase 3: Filter and Score\n\n**Exclude claimed tasks:**\n```javascript\nconst available = tasks.filter(t => !claimedIds.has(String(t.number || t.id)));\n```\n\n**Exclude issues with open PRs (GitHub only):**\n```javascript\nconst filtered = available.filter(t => {\n  const id = String(t.number || t.id);\n  if (prLinkedIssues.has(id)) {\n    console.log(`[INFO] Skipping #${id} - already has an open PR`);\n    return false;\n  }\n  return true;\n});\n```\n\n**Apply priority filter** (pass `filtered` through scoring pipeline):\n```javascript\nconst LABEL_MAPS = {\n  bugs: ['bug', 'fix', 'error', 'defect'],\n  security: ['security', 'vulnerability', 'cve'],\n  features: ['enhancement', 'feature', 'improvement']\n};\n\nfunction filterByPriority(tasks, filter) {\n  if (filter === 'continue' || filter === 'all') return tasks;\n  const targetLabels = LABEL_MAPS[filter] || [];\n  return tasks.filter(t => {\n    const labels = (t.labels || []).map(l => (l.name || l).toLowerCase());\n    return targetLabels.some(target => labels.some(l => l.includes(target)));\n  });\n}\n\nconst prioritized = filterByPriority(filtered, policy.priorityFilter);\n\u002F\u002F Assign score to each task so it is available for display in the UI\nconst topTasks = prioritized.map(t => ({ ...t, score: scoreTask(t) })).sort((a, b) => b.score - a.score);\n```\n\n**Score tasks:**\n```javascript\nfunction scoreTask(task) {\n  let score = 0;\n  const labels = (task.labels || []).map(l => (l.name || l).toLowerCase());\n\n  \u002F\u002F Priority labels\n  if (labels.some(l => l.includes('critical') || l.includes('p0'))) score += 100;\n  if (labels.some(l => l.includes('high') || l.includes('p1'))) score += 50;\n  if (labels.some(l => l.includes('security'))) score += 40;\n\n  \u002F\u002F Quick wins\n  if (labels.some(l => l.includes('small') || l.includes('quick'))) score += 20;\n\n  \u002F\u002F Age (older bugs get priority)\n  if (task.createdAt) {\n    const ageInDays = (Date.now() - new Date(task.createdAt)) \u002F 86400000;\n    if (labels.includes('bug') && ageInDays > 30) score += 10;\n  }\n\n  return score;\n}\n```\n\n### Phase 4: Present to User via AskUserQuestion\n\n**CRITICAL**: Labels MUST be max 30 characters (OpenCode limit).\n\n```javascript\nfunction truncateLabel(num, title) {\n  const prefix = `#${num}: `;\n  const maxLen = 30 - prefix.length;\n  return title.length > maxLen\n    ? prefix + title.substring(0, maxLen - 1) + '...'\n    : prefix + title;\n}\n\nconst options = topTasks.slice(0, 5).map(task => ({\n  label: truncateLabel(task.number, task.title),\n  description: `Score: ${task.score} | ${(task.labels || []).slice(0, 2).join(', ')}`\n}));\n\nAskUserQuestion({\n  questions: [{\n    header: \"Select Task\",\n    question: \"Which task should I work on?\",\n    options,\n    multiSelect: false\n  }]\n});\n```\n\n### Phase 5: Update State\n\n```javascript\nworkflowState.updateState({\n  task: {\n    id: String(selectedTask.number),\n    source: policy.taskSource?.source || policy.taskSource,\n    title: selectedTask.title,\n    description: selectedTask.body || '',\n    labels: selectedTask.labels?.map(l => l.name || l) || [],\n    url: selectedTask.url\n  }\n});\n\nworkflowState.completePhase({\n  tasksAnalyzed: tasks.length,\n  selectedTask: selectedTask.number\n});\n```\n\n### Phase 6: Post Comment (GitHub only)\n\n**Skip this phase entirely for non-GitHub sources (GitLab, local, custom).** Run for `github`, `gh-issues`, and `gh-projects` sources.\n\n```bash\n# Only run for GitHub sources (github, gh-issues, gh-projects). Use policy.taskSource?.source from Phase 1 to check.\ngh issue comment \"$TASK_ID\" --body \"[BOT] Workflow started for this issue.\"\n```\n\n## Output Format\n\n```markdown\n## Task Selected\n\n**Task**: #{id} - {title}\n**Source**: {source}\n**URL**: {url}\n\nProceeding to worktree setup...\n```\n\n## Error Handling\n\nIf no tasks found:\n1. Suggest creating issues\n2. Suggest running \u002Faudit-project\n3. Suggest using 'all' priority filter\n\n## Constraints\n\n- MUST use AskUserQuestion for task selection (not plain text)\n- Labels MUST be max 30 characters\n- Exclude tasks already claimed by other workflows\n- Exclude issues that already have an open PR (GitHub and GitHub Projects sources)\n- PR-link detection covers up to 100 open PRs (--limit 100 is the fetch cap)\n- Top 5 tasks only\n","# discover-tasks\n\nDiscover tasks from configured sources, validate them, and present for user selection.\n\n## When to Use\n\nInvoked during Phase 2 of `\u002Fnext-task` workflow, after policy selection. Also usable standalone when the user wants to discover and select tasks from configured sources.\n\n## Workflow\n\n### Phase 1: Load Policy and Claimed Tasks\n\n```javascript\n\u002F\u002F Use relative path from skill directory to plugin lib\n\u002F\u002F Path: skills\u002Fdiscover-tasks\u002F -> ..\u002F..\u002Flib\u002Fstate\u002Fworkflow-state.js\nconst workflowState = require('..\u002F..\u002Flib\u002Fstate\u002Fworkflow-state.js');\n\nconst state = workflowState.readState();\nconst policy = state.policy;\n\n\u002F\u002F Load claimed task IDs from registry (tasks[] contains worktree-manager claims)\nconst tasksRegistry = workflowState.readTasks();\nconst claimedIds = new Set(tasksRegistry.tasks.map(t => t.id));\n```\n\n### Phase 2: Fetch Tasks by Source\n\n**Source types:**\n- `github` \u002F `gh-issues`: GitHub CLI\n- `gh-projects`: GitHub Projects (v2 boards)\n- `gitlab`: GitLab CLI\n- `local` \u002F `tasks-md`: Local markdown files\n- `custom`: CLI\u002FMCP\u002FSkill tool\n- `other`: Agent interprets description\n\n**GitHub Issues:**\n```bash\n# Fetch with pagination awareness\ngh issue list --state open \\\n  --json number,title,body,labels,assignees,createdAt,url \\\n  --limit 100 > \u002Ftmp\u002Fgh-issues.json\n```\n\n**GitLab Issues:**\n```bash\nglab issue list --state opened --output json --per-page 100 > \u002Ftmp\u002Fglab-issues.json\n```\n\n**Local tasks.md:**\n```bash\nfor f in PLAN.md tasks.md TODO.md; do\n  [ -f \"$f\" ] && grep -n '^\\s*- \\[ \\]' \"$f\"\ndone\n```\n\n**GitHub Projects (v2):**\n```javascript\n\u002F\u002F Extract gh-projects parameters from policy\nconst projectNumber = policy.taskSource.projectNumber;\nconst owner = policy.taskSource.owner;\nif (!projectNumber || !owner) {\n  throw new Error('gh-projects source missing projectNumber or owner in policy.taskSource');\n}\n```\n\n```bash\n# Requires 'project' token scope. If permission error: gh auth refresh -s project\ngh project item-list \"$PROJECT_NUMBER\" --owner \"$OWNER\" --format json --limit 100 > \u002Ftmp\u002Fgh-project-items.json\n```\n\n```javascript\nconst fs = require('fs');\nconst raw = JSON.parse(fs.readFileSync('\u002Ftmp\u002Fgh-project-items.json', 'utf8'));\nconst items = (raw.items || []);\n\n\u002F\u002F Filter to ISSUE type only (exclude PULL_REQUEST, DRAFT_ISSUE)\nconst issues = items\n  .filter(item => item.content && item.content.type === 'ISSUE')\n  .map(item => ({\n    number: item.content.number,\n    title: item.content.title,\n    body: item.content.body || '',\n    labels: (item.content.labels || []).map(l => typeof l === 'object' ? l.name || '' : l).filter(Boolean),\n    url: item.content.url,\n    createdAt: item.content.createdAt\n  }));\n```\n\n[WARN] If `gh project item-list` returns a permission error, tell the user:\n`Run: gh auth refresh -s project`\n\n**Custom Source:**\n```javascript\nconst { sources } = require('..\u002F..\u002Flib');\nconst capabilities = sources.getToolCapabilities(toolName);\n\u002F\u002F Execute capabilities.commands.list_issues\n```\n\n### Phase 2.5: Collect PR-Linked Issues (GitHub only)\n\n```javascript\n\u002F\u002F Default for non-GitHub sources - always defined so Phase 3 filter is safe\nlet prLinkedIssues = new Set();\n```\n\nFor GitHub sources (`policy.taskSource?.source === 'github'`, `'gh-issues'`, or `'gh-projects'`), fetch all open PRs and build a Set of issue numbers that already have an associated PR. Skip to Phase 3 for all other sources.\n\n```bash\n# Only run when policy.taskSource?.source is 'github', 'gh-issues', or 'gh-projects'\n# Note: covers up to 100 open PRs. If repo has more, some linked issues may not be excluded.\ngh pr list --state open --json number,title,body,headRefName --limit 100 > \u002Ftmp\u002Fgh-prs.json\n```\n\n```javascript\nconst fs = require('fs');\ntry {\n  const prs = JSON.parse(fs.readFileSync('\u002Ftmp\u002Fgh-prs.json', 'utf8') || '[]');\n\n  for (const pr of prs) {\n    \u002F\u002F 1. Branch name suffix: fix\u002Fsome-thing-123 extracts 123\n    \u002F\u002F Note: heuristic - branches like \"release-2026\" will false-positive on issue #2026.\n    \u002F\u002F Patterns 2 and 3 are more precise; this is a best-effort supplement.\n    const branchMatch = (pr.headRefName || '').match(\u002F-(\\d+)$\u002F);\n    if (branchMatch) prLinkedIssues.add(branchMatch[1]);\n\n    \u002F\u002F 2. PR body closing keywords (GitHub's full keyword set, with word boundary)\n    if (pr.body) {\n      const bodyMatches = pr.body.matchAll(\u002F\\b(?:close[sd]?|fix(?:e[sd])?|resolve[sd]?)\\s+#(\\d+)\u002Fgi);\n      for (const m of bodyMatches) prLinkedIssues.add(m[1]);\n    }\n\n    \u002F\u002F 3. PR title (#N) convention - capture all occurrences\n    const titleMatches = (pr.title || '').matchAll(\u002F\\(#(\\d+)\\)\u002Fg);\n    for (const m of titleMatches) prLinkedIssues.add(m[1]);\n  }\n} catch (e) {\n  console.log('[WARN] Could not parse open PRs, skipping PR-link filter:', e.message);\n  prLinkedIssues = new Set();\n}\n```\n\n### Phase 3: Filter and Score\n\n**Exclude claimed tasks:**\n```javascript\nconst available = tasks.filter(t => !claimedIds.has(String(t.number || t.id)));\n```\n\n**Exclude issues with open PRs (GitHub only):**\n```javascript\nconst filtered = available.filter(t => {\n  const id = String(t.number || t.id);\n  if (prLinkedIssues.has(id)) {\n    console.log(`[INFO] Skipping #${id} - already has an open PR`);\n    return false;\n  }\n  return true;\n});\n```\n\n**Apply priority filter** (pass `filtered` through scoring pipeline):\n```javascript\nconst LABEL_MAPS = {\n  bugs: ['bug', 'fix', 'error', 'defect'],\n  security: ['security', 'vulnerability', 'cve'],\n  features: ['enhancement', 'feature', 'improvement']\n};\n\nfunction filterByPriority(tasks, filter) {\n  if (filter === 'continue' || filter === 'all') return tasks;\n  const targetLabels = LABEL_MAPS[filter] || [];\n  return tasks.filter(t => {\n    const labels = (t.labels || []).map(l => (l.name || l).toLowerCase());\n    return targetLabels.some(target => labels.some(l => l.includes(target)));\n  });\n}\n\nconst prioritized = filterByPriority(filtered, policy.priorityFilter);\n\u002F\u002F Assign score to each task so it is available for display in the UI\nconst topTasks = prioritized.map(t => ({ ...t, score: scoreTask(t) })).sort((a, b) => b.score - a.score);\n```\n\n**Score tasks:**\n```javascript\nfunction scoreTask(task) {\n  let score = 0;\n  const labels = (task.labels || []).map(l => (l.name || l).toLowerCase());\n\n  \u002F\u002F Priority labels\n  if (labels.some(l => l.includes('critical') || l.includes('p0'))) score += 100;\n  if (labels.some(l => l.includes('high') || l.includes('p1'))) score += 50;\n  if (labels.some(l => l.includes('security'))) score += 40;\n\n  \u002F\u002F Quick wins\n  if (labels.some(l => l.includes('small') || l.includes('quick'))) score += 20;\n\n  \u002F\u002F Age (older bugs get priority)\n  if (task.createdAt) {\n    const ageInDays = (Date.now() - new Date(task.createdAt)) \u002F 86400000;\n    if (labels.includes('bug') && ageInDays > 30) score += 10;\n  }\n\n  return score;\n}\n```\n\n### Phase 4: Present to User via AskUserQuestion\n\n**CRITICAL**: Labels MUST be max 30 characters (OpenCode limit).\n\n```javascript\nfunction truncateLabel(num, title) {\n  const prefix = `#${num}: `;\n  const maxLen = 30 - prefix.length;\n  return title.length > maxLen\n    ? prefix + title.substring(0, maxLen - 1) + '...'\n    : prefix + title;\n}\n\nconst options = topTasks.slice(0, 5).map(task => ({\n  label: truncateLabel(task.number, task.title),\n  description: `Score: ${task.score} | ${(task.labels || []).slice(0, 2).join(', ')}`\n}));\n\nAskUserQuestion({\n  questions: [{\n    header: \"Select Task\",\n    question: \"Which task should I work on?\",\n    options,\n    multiSelect: false\n  }]\n});\n```\n\n### Phase 5: Update State\n\n```javascript\nworkflowState.updateState({\n  task: {\n    id: String(selectedTask.number),\n    source: policy.taskSource?.source || policy.taskSource,\n    title: selectedTask.title,\n    description: selectedTask.body || '',\n    labels: selectedTask.labels?.map(l => l.name || l) || [],\n    url: selectedTask.url\n  }\n});\n\nworkflowState.completePhase({\n  tasksAnalyzed: tasks.length,\n  selectedTask: selectedTask.number\n});\n```\n\n### Phase 6: Post Comment (GitHub only)\n\n**Skip this phase entirely for non-GitHub sources (GitLab, local, custom).** Run for `github`, `gh-issues`, and `gh-projects` sources.\n\n```bash\n# Only run for GitHub sources (github, gh-issues, gh-projects). Use policy.taskSource?.source from Phase 1 to check.\ngh issue comment \"$TASK_ID\" --body \"[BOT] Workflow started for this issue.\"\n```\n\n## Output Format\n\n```markdown\n## Task Selected\n\n**Task**: #{id} - {title}\n**Source**: {source}\n**URL**: {url}\n\nProceeding to worktree setup...\n```\n\n## Error Handling\n\nIf no tasks found:\n1. Suggest creating issues\n2. Suggest running \u002Faudit-project\n3. Suggest using 'all' priority filter\n\n## Constraints\n\n- MUST use AskUserQuestion for task selection (not plain text)\n- Labels MUST be max 30 characters\n- Exclude tasks already claimed by other workflows\n- Exclude issues that already have an open PR (GitHub and GitHub Projects sources)\n- PR-link detection covers up to 100 open PRs (--limit 100 is the fetch cap)\n- Top 5 tasks only\n",{"name":5,"version":23,"description":7,"allowed-tools":24},"5.1.1","Bash(gh:*), Bash(glab:*), Bash(git:*), Bash(grep:*), Grep, Read, AskUserQuestion","main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fdiscover-tasks",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add agisota\u002Fold-one --skill discover-tasks",{"tool":40,"command":41},"bunx","bunx skills add agisota\u002Fold-one --skill discover-tasks",{"tool":43,"command":44},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill discover-tasks","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fdiscover-tasks\u002FSKILL.md",true,[],[49,56,63,72,79,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]