[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F4Q94YEZSRG2EBGPKDVR71":3,"skill-same:01M7F4Q94YEZSRG2EBGPKDVR71":52},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7F4Q94YEZSRG2EBGPKDVR71","skill-context-detection",null,"Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type","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\u002F05-技能与代理开发\u002Fskill-context-detection\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: skill-context-detection\ndescription: \"Auto-detect work context (Dev vs Knowledge) — use to tailor workflows based on current task type\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Context Detection - Internal Skill\n\n## Purpose\n\nThis skill provides **automatic context detection** to determine whether the user is working in a **Development context** (code-focused) or **Knowledge context** (research\u002Fstrategy-focused). This replaces the manual `\u002Focto:km` toggle with intelligent auto-detection.\n\n## Detection Algorithm\n\nWhen a workflow skill activates, detect context using these signals:\n\n### Step 1: Check for Explicit Override\n\nIf user has explicitly set mode via `\u002Focto:km on` or `\u002Focto:km off`, respect that setting.\n\n```bash\n# Check if knowledge mode is explicitly set\nif [[ -f ~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode ]]; then\n  EXPLICIT_MODE=$(cat ~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode)\n  if [[ \"$EXPLICIT_MODE\" == \"on\" ]]; then\n    echo \"knowledge\"\n    exit 0\n  elif [[ \"$EXPLICIT_MODE\" == \"off\" ]]; then\n    echo \"dev\"\n    exit 0\n  fi\nfi\n# If \"auto\" or not set, proceed with auto-detection\n```\n\n### Step 2: Analyze Prompt Content (Strongest Signal)\n\n**Knowledge Context Indicators** (check prompt for these terms):\n- Business\u002Fstrategy: \"market\", \"ROI\", \"stakeholders\", \"strategy\", \"business case\", \"competitive\"\n- Research: \"literature\", \"synthesis\", \"academic\", \"papers\", \"research question\"\n- UX: \"personas\", \"user research\", \"journey map\", \"pain points\", \"interviews\"\n- Deliverables: \"presentation\", \"report\", \"PRD\", \"proposal\", \"executive summary\"\n\n**Dev Context Indicators** (check prompt for these terms):\n- Technical: \"API\", \"endpoint\", \"database\", \"function\", \"class\", \"module\"\n- Actions: \"implement\", \"debug\", \"refactor\", \"test\", \"deploy\", \"build\"\n- Artifacts: \"code\", \"tests\", \"migration\", \"schema\", \"controller\"\n\n**Scoring:**\n- Count knowledge indicators in prompt\n- Count dev indicators in prompt\n- Higher count wins\n- If tied, check project context (Step 3)\n\n### Step 3: Analyze Project Context (Secondary Signal)\n\n**Dev Project Indicators:**\n- Has `package.json`, `Cargo.toml`, `go.mod`, `pyproject.toml`, `pom.xml`\n- Has `src\u002F`, `lib\u002F`, `app\u002F` directories with code files\n- Recent files are `.ts`, `.js`, `.py`, `.go`, `.rs`, `.java`\n\n**Knowledge Project Indicators:**\n- Has `docs\u002F`, `research\u002F`, `strategy\u002F`, `reports\u002F` directories\n- Majority of files are `.md`, `.docx`, `.pdf`, `.pptx`\n- No code package managers detected\n\n### Step 4: Default Fallback\n\nIf signals are ambiguous or equal:\n- In a git repo with code files → Default to **Dev Context**\n- No code files detected → Default to **Knowledge Context**\n\n\n## Context Output Format\n\nReturn detected context as a structured object for use by workflow skills:\n\n```json\n{\n  \"context\": \"dev\" | \"knowledge\",\n  \"confidence\": \"high\" | \"medium\" | \"low\",\n  \"signals\": {\n    \"prompt_indicators\": [\"API\", \"endpoint\", \"database\"],\n    \"project_type\": \"node_typescript\",\n    \"explicit_override\": false\n  }\n}\n```\n\n\n## How Workflow Skills Use Context\n\n### flow-discover (Research)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Research Focus** | Technical implementation, library comparison, code patterns | Market analysis, academic synthesis, competitive research |\n| **Primary Agents** | Codex (implementation), Antigravity (ecosystem) | Antigravity (analysis), research-synthesizer |\n| **Output Format** | Code examples, API comparisons, tech recommendations | Reports, frameworks, strategic recommendations |\n| **Visual Banner** | `🔍 [Dev] Discover Phase: Technical research` | `🔍 [Knowledge] Discover Phase: Strategic research` |\n\n### flow-develop (Build)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Build Focus** | Code generation, implementation, architecture | PRDs, strategy docs, presentations |\n| **Primary Agents** | Codex (code), backend-architect, tdd-orchestrator | product-writer, strategy-analyst, exec-communicator |\n| **Output Format** | Source files, tests, migrations | Documents, frameworks, action plans |\n| **Visual Banner** | `🛠️ [Dev] Develop Phase: Building code` | `🛠️ [Knowledge] Develop Phase: Building deliverables` |\n\n### flow-deliver (Review)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Review Focus** | Code quality, security, performance | Document quality, argument strength, completeness |\n| **Primary Agents** | code-reviewer, security-auditor | exec-communicator, strategy-analyst |\n| **Quality Gates** | OWASP, test coverage, maintainability | Evidence quality, clarity, actionability |\n| **Visual Banner** | `✅ [Dev] Deliver Phase: Code review` | `✅ [Knowledge] Deliver Phase: Document review` |\n\n\n## Visual Indicator Update\n\nWhen context is detected, update the visual banner to show context:\n\n**Dev Context:**\n```\n🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode\n🔍 [Dev] Discover Phase: Researching OAuth implementation patterns\n\nProviders:\n🔴 Codex CLI - Technical implementation analysis\n🟡 Antigravity CLI - Ecosystem and library comparison\n🔵 Claude - Strategic synthesis\n```\n\n**Knowledge Context:**\n```\n🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode\n🔍 [Knowledge] Discover Phase: Researching market entry strategies\n\nProviders:\n🔴 Codex CLI - Data analysis and modeling\n🟡 Antigravity CLI - Market and competitive research\n🔵 Claude - Strategic synthesis\n```\n\n\n## Implementation in Workflow Skills\n\nEach flow skill should:\n\n1. **Before executing workflow**, run context detection\n2. **Show detected context** in visual banner\n3. **Adjust behavior** based on context:\n   - Agent selection\n   - Prompt framing for external CLIs\n   - Output format expectations\n   - Quality gate criteria\n\n### Example Integration (Pseudocode)\n\n```markdown\nWhen this skill activates:\n\n1. **Detect context**\n   - Analyze user's prompt for knowledge vs dev indicators\n   - Check project type (code repo vs doc-heavy)\n   - Check for explicit override (~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode)\n   - Determine: \"dev\" or \"knowledge\" with confidence level\n\n2. **Show context-aware banner**\n   ```\n   🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider [research|implementation|validation] mode\n   [Phase Emoji] [Context] [Phase Name]: [Description]\n   \n   Detected Context: [Dev|Knowledge] (confidence: [high|medium|low])\n   ```\n\n3. **Execute workflow with context-appropriate behavior**\n   - Frame prompts for external providers based on context\n   - Select appropriate synthesis approach\n   - Apply context-specific quality gates\n```\n\n\n## Override Mechanism\n\nUsers can still explicitly set context when auto-detection is wrong:\n\n```bash\n# Force knowledge mode\n\u002Focto:km on\n\n# Force dev mode  \n\u002Focto:km off\n\n# Return to auto-detection\n\u002Focto:km auto\n```\n\nWhen explicit override is set, context detection respects it until user resets to \"auto\".\n\n\n## Confidence Levels\n\n- **High**: Strong signals in prompt AND project context agree\n- **Medium**: Signals in prompt OR project context (not both)\n- **Low**: Ambiguous signals, using fallback default\n\nWhen confidence is \"low\", consider briefly mentioning the detected context to user:\n> \"I detected this as a [dev\u002Fknowledge] task. If that's wrong, you can use `\u002Focto:km` to override.\"\n\n\n## Testing Context Detection\n\nTo verify context detection is working:\n\n1. In a code repository, ask \"octo research caching patterns\" → Should detect **Dev Context**\n2. In same repo, ask \"octo research market opportunities\" → Should detect **Knowledge Context**\n3. With `\u002Focto:km on` set, ask \"octo research API patterns\" → Should use **Knowledge Context** (explicit override)\n\n\n## Proactive Skill Suggestions\n\nWhen detecting the user's work stage, surface relevant command suggestions:\n\n| Detected Context | Suggestion |\n|-----------------|------------|\n| Brainstorming \u002F exploring ideas | Consider `\u002Focto:brainstorm` for structured ideation |\n| Reviewing a plan or strategy | Consider `\u002Focto:plan` for strategic planning |\n| Debugging errors or failures | Consider `\u002Focto:debug` for systematic investigation |\n| Writing or running tests | Consider `\u002Focto:tdd` for test-driven development |\n| Code review before merge | Use Claude-native `\u002Freview` for ordinary review; suggest `\u002Focto:review` for multi-AI escalation |\n| Ready to deploy or ship | Consider `\u002Focto:deliver` for quality-gated delivery |\n| Researching a topic | Consider `\u002Focto:research` for multi-source synthesis |\n| Working on security | Use Claude-native `\u002Fsecurity-review` for ordinary security review; suggest `\u002Focto:security` for escalated OWASP or adversarial audit |\n\n### Suggestion Format\n\nSuggestions should be non-intrusive, appended as a brief note:\n\n```\n💡 Tip: You appear to be debugging — `\u002Focto:debug` provides systematic investigation with multi-AI support.\n```\n\n### Persistent Opt-Out\n\n- If user says \"stop suggesting\" or \"no more tips\": set `OCTO_PROACTIVE_SUGGESTIONS=off` in `.claude-octopus\u002Fpreferences.json`\n- If user says \"be proactive\" or \"turn on tips\": set `OCTO_PROACTIVE_SUGGESTIONS=on`\n- Check preference at suggestion time — never suggest when opted out\n- Respect current mode: dev mode suggestions differ from knowledge work suggestions\n\n### Re-Enable Suggestions\n\nUsers who previously opted out can re-enable suggestions at any time:\n- Say \"be proactive\", \"turn on tips\", or \"enable suggestions\"\n- Manually edit `~\u002F.claude-octopus\u002Fpreferences.json` and set `OCTO_PROACTIVE_SUGGESTIONS` to `on`\n- Default state (no preference set) is suggestions enabled\n\n### Detection Signals\n\nDetect work stage from:\n- Recent tool usage (many Bash calls = likely implementing\u002Fdebugging)\n- File types being edited (.test.ts = testing, .md = documentation)\n- Error patterns in recent output (stack traces = debugging)\n- Git state (uncommitted changes = implementing, clean tree = ready to review\u002Fship)\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Context Detection - Internal Skill\n\n## Purpose\n\nThis skill provides **automatic context detection** to determine whether the user is working in a **Development context** (code-focused) or **Knowledge context** (research\u002Fstrategy-focused). This replaces the manual `\u002Focto:km` toggle with intelligent auto-detection.\n\n## Detection Algorithm\n\nWhen a workflow skill activates, detect context using these signals:\n\n### Step 1: Check for Explicit Override\n\nIf user has explicitly set mode via `\u002Focto:km on` or `\u002Focto:km off`, respect that setting.\n\n```bash\n# Check if knowledge mode is explicitly set\nif [[ -f ~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode ]]; then\n  EXPLICIT_MODE=$(cat ~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode)\n  if [[ \"$EXPLICIT_MODE\" == \"on\" ]]; then\n    echo \"knowledge\"\n    exit 0\n  elif [[ \"$EXPLICIT_MODE\" == \"off\" ]]; then\n    echo \"dev\"\n    exit 0\n  fi\nfi\n# If \"auto\" or not set, proceed with auto-detection\n```\n\n### Step 2: Analyze Prompt Content (Strongest Signal)\n\n**Knowledge Context Indicators** (check prompt for these terms):\n- Business\u002Fstrategy: \"market\", \"ROI\", \"stakeholders\", \"strategy\", \"business case\", \"competitive\"\n- Research: \"literature\", \"synthesis\", \"academic\", \"papers\", \"research question\"\n- UX: \"personas\", \"user research\", \"journey map\", \"pain points\", \"interviews\"\n- Deliverables: \"presentation\", \"report\", \"PRD\", \"proposal\", \"executive summary\"\n\n**Dev Context Indicators** (check prompt for these terms):\n- Technical: \"API\", \"endpoint\", \"database\", \"function\", \"class\", \"module\"\n- Actions: \"implement\", \"debug\", \"refactor\", \"test\", \"deploy\", \"build\"\n- Artifacts: \"code\", \"tests\", \"migration\", \"schema\", \"controller\"\n\n**Scoring:**\n- Count knowledge indicators in prompt\n- Count dev indicators in prompt\n- Higher count wins\n- If tied, check project context (Step 3)\n\n### Step 3: Analyze Project Context (Secondary Signal)\n\n**Dev Project Indicators:**\n- Has `package.json`, `Cargo.toml`, `go.mod`, `pyproject.toml`, `pom.xml`\n- Has `src\u002F`, `lib\u002F`, `app\u002F` directories with code files\n- Recent files are `.ts`, `.js`, `.py`, `.go`, `.rs`, `.java`\n\n**Knowledge Project Indicators:**\n- Has `docs\u002F`, `research\u002F`, `strategy\u002F`, `reports\u002F` directories\n- Majority of files are `.md`, `.docx`, `.pdf`, `.pptx`\n- No code package managers detected\n\n### Step 4: Default Fallback\n\nIf signals are ambiguous or equal:\n- In a git repo with code files → Default to **Dev Context**\n- No code files detected → Default to **Knowledge Context**\n\n\n## Context Output Format\n\nReturn detected context as a structured object for use by workflow skills:\n\n```json\n{\n  \"context\": \"dev\" | \"knowledge\",\n  \"confidence\": \"high\" | \"medium\" | \"low\",\n  \"signals\": {\n    \"prompt_indicators\": [\"API\", \"endpoint\", \"database\"],\n    \"project_type\": \"node_typescript\",\n    \"explicit_override\": false\n  }\n}\n```\n\n\n## How Workflow Skills Use Context\n\n### flow-discover (Research)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Research Focus** | Technical implementation, library comparison, code patterns | Market analysis, academic synthesis, competitive research |\n| **Primary Agents** | Codex (implementation), Antigravity (ecosystem) | Antigravity (analysis), research-synthesizer |\n| **Output Format** | Code examples, API comparisons, tech recommendations | Reports, frameworks, strategic recommendations |\n| **Visual Banner** | `🔍 [Dev] Discover Phase: Technical research` | `🔍 [Knowledge] Discover Phase: Strategic research` |\n\n### flow-develop (Build)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Build Focus** | Code generation, implementation, architecture | PRDs, strategy docs, presentations |\n| **Primary Agents** | Codex (code), backend-architect, tdd-orchestrator | product-writer, strategy-analyst, exec-communicator |\n| **Output Format** | Source files, tests, migrations | Documents, frameworks, action plans |\n| **Visual Banner** | `🛠️ [Dev] Develop Phase: Building code` | `🛠️ [Knowledge] Develop Phase: Building deliverables` |\n\n### flow-deliver (Review)\n\n| Aspect | Dev Context | Knowledge Context |\n|--------|-------------|-------------------|\n| **Review Focus** | Code quality, security, performance | Document quality, argument strength, completeness |\n| **Primary Agents** | code-reviewer, security-auditor | exec-communicator, strategy-analyst |\n| **Quality Gates** | OWASP, test coverage, maintainability | Evidence quality, clarity, actionability |\n| **Visual Banner** | `✅ [Dev] Deliver Phase: Code review` | `✅ [Knowledge] Deliver Phase: Document review` |\n\n\n## Visual Indicator Update\n\nWhen context is detected, update the visual banner to show context:\n\n**Dev Context:**\n```\n🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode\n🔍 [Dev] Discover Phase: Researching OAuth implementation patterns\n\nProviders:\n🔴 Codex CLI - Technical implementation analysis\n🟡 Antigravity CLI - Ecosystem and library comparison\n🔵 Claude - Strategic synthesis\n```\n\n**Knowledge Context:**\n```\n🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider research mode\n🔍 [Knowledge] Discover Phase: Researching market entry strategies\n\nProviders:\n🔴 Codex CLI - Data analysis and modeling\n🟡 Antigravity CLI - Market and competitive research\n🔵 Claude - Strategic synthesis\n```\n\n\n## Implementation in Workflow Skills\n\nEach flow skill should:\n\n1. **Before executing workflow**, run context detection\n2. **Show detected context** in visual banner\n3. **Adjust behavior** based on context:\n   - Agent selection\n   - Prompt framing for external CLIs\n   - Output format expectations\n   - Quality gate criteria\n\n### Example Integration (Pseudocode)\n\n```markdown\nWhen this skill activates:\n\n1. **Detect context**\n   - Analyze user's prompt for knowledge vs dev indicators\n   - Check project type (code repo vs doc-heavy)\n   - Check for explicit override (~\u002F.claude-octopus\u002Fconfig\u002Fknowledge-mode)\n   - Determine: \"dev\" or \"knowledge\" with confidence level\n\n2. **Show context-aware banner**\n   ```\n   🐙 **CLAUDE OCTOPUS ACTIVATED** - Multi-provider [research|implementation|validation] mode\n   [Phase Emoji] [Context] [Phase Name]: [Description]\n   \n   Detected Context: [Dev|Knowledge] (confidence: [high|medium|low])\n   ```\n\n3. **Execute workflow with context-appropriate behavior**\n   - Frame prompts for external providers based on context\n   - Select appropriate synthesis approach\n   - Apply context-specific quality gates\n```\n\n\n## Override Mechanism\n\nUsers can still explicitly set context when auto-detection is wrong:\n\n```bash\n# Force knowledge mode\n\u002Focto:km on\n\n# Force dev mode  \n\u002Focto:km off\n\n# Return to auto-detection\n\u002Focto:km auto\n```\n\nWhen explicit override is set, context detection respects it until user resets to \"auto\".\n\n\n## Confidence Levels\n\n- **High**: Strong signals in prompt AND project context agree\n- **Medium**: Signals in prompt OR project context (not both)\n- **Low**: Ambiguous signals, using fallback default\n\nWhen confidence is \"low\", consider briefly mentioning the detected context to user:\n> \"I detected this as a [dev\u002Fknowledge] task. If that's wrong, you can use `\u002Focto:km` to override.\"\n\n\n## Testing Context Detection\n\nTo verify context detection is working:\n\n1. In a code repository, ask \"octo research caching patterns\" → Should detect **Dev Context**\n2. In same repo, ask \"octo research market opportunities\" → Should detect **Knowledge Context**\n3. With `\u002Focto:km on` set, ask \"octo research API patterns\" → Should use **Knowledge Context** (explicit override)\n\n\n## Proactive Skill Suggestions\n\nWhen detecting the user's work stage, surface relevant command suggestions:\n\n| Detected Context | Suggestion |\n|-----------------|------------|\n| Brainstorming \u002F exploring ideas | Consider `\u002Focto:brainstorm` for structured ideation |\n| Reviewing a plan or strategy | Consider `\u002Focto:plan` for strategic planning |\n| Debugging errors or failures | Consider `\u002Focto:debug` for systematic investigation |\n| Writing or running tests | Consider `\u002Focto:tdd` for test-driven development |\n| Code review before merge | Use Claude-native `\u002Freview` for ordinary review; suggest `\u002Focto:review` for multi-AI escalation |\n| Ready to deploy or ship | Consider `\u002Focto:deliver` for quality-gated delivery |\n| Researching a topic | Consider `\u002Focto:research` for multi-source synthesis |\n| Working on security | Use Claude-native `\u002Fsecurity-review` for ordinary security review; suggest `\u002Focto:security` for escalated OWASP or adversarial audit |\n\n### Suggestion Format\n\nSuggestions should be non-intrusive, appended as a brief note:\n\n```\n💡 Tip: You appear to be debugging — `\u002Focto:debug` provides systematic investigation with multi-AI support.\n```\n\n### Persistent Opt-Out\n\n- If user says \"stop suggesting\" or \"no more tips\": set `OCTO_PROACTIVE_SUGGESTIONS=off` in `.claude-octopus\u002Fpreferences.json`\n- If user says \"be proactive\" or \"turn on tips\": set `OCTO_PROACTIVE_SUGGESTIONS=on`\n- Check preference at suggestion time — never suggest when opted out\n- Respect current mode: dev mode suggestions differ from knowledge work suggestions\n\n### Re-Enable Suggestions\n\nUsers who previously opted out can re-enable suggestions at any time:\n- Say \"be proactive\", \"turn on tips\", or \"enable suggestions\"\n- Manually edit `~\u002F.claude-octopus\u002Fpreferences.json` and set `OCTO_PROACTIVE_SUGGESTIONS` to `on`\n- Default state (no preference set) is suggestions enabled\n\n### Detection Signals\n\nDetect work stage from:\n- Recent tool usage (many Bash calls = likely implementing\u002Fdebugging)\n- File types being edited (.test.ts = testing, .md = documentation)\n- Error patterns in recent output (stack traces = debugging)\n- Git state (uncommitted changes = implementing, clean tree = ready to review\u002Fship)\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","05-技能与代理开发\u002Fskill-context-detection",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":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-context-detection",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-context-detection",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-context-detection","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-context-detection\u002FSKILL.md",[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",178,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F05-技能与代理开发\u002Fskill-context-detection\u002Fagents\u002Fopenai.yaml",[53,60,65,72,79,86],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":61,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]