[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EP4QGTA37R664VDDFBC4FQ":3,"skill-same:01M7EP4QGTA37R664VDDFBC4FQ":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},"01M7EP4QGTA37R664VDDFBC4FQ","octopus-security-audit",null,"OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews","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\u002Foctopus-security-audit\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: octopus-security-audit\ndescription: \"OWASP compliance, vulnerability scanning, and adversarial red team testing — use for security reviews\"\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## Execution Contract (MANDATORY - CANNOT SKIP)\n\nThis generated Codex skill preserves an enforced workflow contract from the source skill.\n\n**PROHIBITED:**\n- Do not summarize, simulate, or skip the referenced workflow command when this skill requires execution.\n- Do not claim provider output or validation artifacts exist without checking the actual files or command output.\n- Do not continue silently when a required provider, command, or host capability is unavailable; report the unavailable dependency and use a supported fallback.\n\n\n# Security Audit Skill\n\n**Your first output line MUST be:** `🐙 **CLAUDE OCTOPUS ACTIVATED** - Security Audit`\n\nInvokes the security-auditor persona for thorough security analysis during the `ink` (deliver) phase. Supports both quick OWASP scanning and full adversarial red\u002Fblue team testing.\n\n## Usage\n\n```bash\n# Quick scan via security-auditor persona\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh spawn security-auditor \"Scan for SQL injection vulnerabilities\"\n\n# Adversarial red team via squeeze workflow\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze \"Security audit the authentication module\"\n\n# Via auto-routing (detects security intent)\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh auto \"security audit the payment processing module\"\n```\n\n## Modes (Auto-Detected)\n\n| Mode | Auto-Trigger | Confidence Gate | Scope |\n|------|-------------|----------------|-------|\n| **Quick** (default) | Standard security scan, no sensitive files in diff | 8\u002F10 — only high-confidence findings | Changed files only |\n| **Deep** (auto-escalated) | Diff touches auth\u002Fsecurity\u002FCI files, OR explicit request | 2\u002F10 — flag anything suspicious | Entire codebase |\n\n**Auto-escalation to Deep mode:** The skill automatically switches to Deep mode when ANY of these are true:\n- Diff includes files matching: `*auth*`, `*login*`, `*password*`, `*session*`, `*token*`, `*secret*`, `*crypt*`, `*oauth*`, `*saml*`, `*jwt*`, `*permission*`, `*rbac*`, `*acl*`\n- Diff includes CI\u002FCD files: `.github\u002Fworkflows\u002F*`, `Dockerfile*`, `docker-compose*`, `.gitlab-ci*`\n- Diff includes dependency files: `package-lock.json`, `yarn.lock`, `Gemfile.lock`, `requirements.txt`, `go.sum`\n- The user explicitly says \"deep\", \"full\", \"comprehensive\", or \"CSO\"\n\nNo user action needed — mode detection happens automatically from the git diff context.\n\n## Model Selection Caveat: Fable 5.1\n\nBy default, do not dispatch security-audit passes to Claude Fable 5.1 or the preserved Fable 5 ID. Their safety classifiers can refuse adversarial red-team phrasing in authorized audits. Route these passes to `OCTOPUS_FABLE5_FALLBACK_MODEL` (default `claude-opus-5`) and keep prompts defensively framed (find and report vulnerabilities; do not request working exploits). Reject an exact model-qualified override that targets `claude-fable-5-1` or `claude-fable-5`. On refusal, retry exactly once on the fallback unless `OCTOPUS_FABLE5_NO_RETRY=1`; when retries are disabled or the retry refuses, surface the refusal without further dispatches. `OCTOPUS_FABLE5_MODE=off` is the explicit exception: it disables automatic rerouting for ordinary environment pins, while exact Fable security seats still fail closed. Details: `skills\u002Fblocks\u002Ffable5-prompting.md`.\n\n## Capabilities\n\n### Core (both modes)\n- OWASP Top 10 vulnerability detection\n- SQL injection and XSS scanning\n- Authentication\u002Fauthorization review\n- Secrets and credential detection\n- Dependency vulnerability assessment\n- Security configuration review\n\n### Secrets Archaeology (Deep mode)\nScan git history for leaked credentials that may have been \"deleted\" but remain in commits:\n\n```bash\n# Search git history for common secret patterns\ngit log --all -p --diff-filter=D -- '*.env' '*.key' '*.pem' 2>\u002Fdev\u002Fnull | head -200\ngit log --all -p -S 'AKIA' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # AWS keys\ngit log --all -p -S 'sk-[a-zA-Z0-9]{20,}' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # API keys\ngit log --all -p -S 'ghp_|gho_|github_pat_' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # GitHub tokens\ngit log --all -p -S 'password\\s*[:=]' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # Passwords\n```\n\nReport any findings with the commit SHA, file, and recommendation to rotate the credential.\n\n### CI\u002FCD Pipeline Security (Deep mode)\nAudit GitHub Actions and CI configuration for injection and privilege escalation:\n\n```bash\n# Find all workflow files\nfind .github\u002Fworkflows -name '*.yml' -o -name '*.yaml' 2>\u002Fdev\u002Fnull\n\n# Check for dangerous patterns:\n# 1. Untrusted input in run: blocks (command injection via PR titles\u002Fbranch names)\n# 2. pull_request_target with checkout of PR code (code execution from forks)\n# 3. Overly broad permissions (write-all, contents: write)\n# 4. Missing pinned action versions (uses: actions\u002Fcheckout vs actions\u002Fcheckout@v4)\n# 5. Secrets exposed to pull_request events (accessible to forks)\n```\n\nFlag each finding with severity (CRITICAL\u002FHIGH\u002FMEDIUM\u002FLOW).\n\n### Skill & Plugin Supply Chain (Deep mode)\nVerify integrity of installed Claude Code skills and plugins:\n\n```bash\n# List installed plugins\nls -la ~\u002F.claude\u002Fplugins\u002F 2>\u002Fdev\u002Fnull\n\n# Check for skills that execute arbitrary bash\ngrep -r 'exec\\|eval\\|bash -c' ~\u002F.claude\u002Fskills\u002F*\u002FSKILL.md 2>\u002Fdev\u002Fnull | head -20\n\n# Verify plugin sources (are they from known registries?)\ncat ~\u002F.claude\u002Fplugins\u002F*\u002Fplugin.json 2>\u002Fdev\u002Fnull | grep -E '\"source\"|\"registry\"'\n```\n\n### STRIDE Threat Modeling (Deep mode)\nFor the target component, enumerate threats across all 6 STRIDE categories:\n\n| Category | Question |\n|----------|----------|\n| **S**poofing | Can an attacker impersonate a user or component? |\n| **T**ampering | Can data be modified in transit or at rest? |\n| **R**epudiation | Can actions be denied without audit trail? |\n| **I**nformation Disclosure | Can sensitive data leak through logs, errors, or side channels? |\n| **D**enial of Service | Can the service be overwhelmed or starved? |\n| **E**levation of Privilege | Can a low-privilege user gain admin access? |\n\n## Persona Reference\n\nThis skill wraps the `security-auditor` persona defined in:\n- `agents\u002Fpersonas\u002Fsecurity-auditor.md`\n- CLI: `codex-review`\n- Model: `gpt-5.2-codex`\n- Phases: `ink`\n- Expertise: `owasp`, `vulnerability-scanning`, `security-review`\n\n## Example Prompts\n\n```\n\"Scan for hardcoded credentials in the codebase\"\n\"Check for CSRF vulnerabilities in form handlers\"\n\"Review the API authentication implementation\"\n\"Red team review the payment API\"\n```\n\n\n## Adversarial Mode (squeeze workflow)\n\nFor comprehensive security testing, use the squeeze workflow which runs a 4-phase adversarial cycle:\n\n1. **Blue Team** (Defense): Codex reviews code, identifies attack surface, proposes defenses\n2. **Red Team** (Attack): Antigravity attempts to break defenses, generates exploit PoCs\n3. **Remediation** (Fix): Codex patches all vulnerabilities found\n4. **Validation** (Verify): Antigravity re-tests, confirms fixes or fails\n\n```bash\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze \"[user's security request]\"\n```\n\n### OWASP Top 10 Coverage\n\n- Broken Access Control\n- Cryptographic Failures\n- Injection\n- Insecure Design\n- Security Misconfiguration\n- Vulnerable Components\n- Authentication Failures\n- Software Integrity Failures\n- Logging & Monitoring Failures\n- Server-Side Request Forgery\n\n### Additional Attack Patterns\n\n- Race conditions, business logic flaws\n- Denial of service, information disclosure\n- Client-side attacks (XSS, CSRF)\n\n### Advanced Options\n\n```bash\n# Focus on specific vulnerabilities\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze --principles security \"Audit for auth bypass only\"\n\n# Loop until all vulnerabilities fixed\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze --loop --quality 100 \"Zero tolerance audit\"\n```\n\n### When to Use Adversarial Mode\n\n| Aspect | Quick Scan (spawn) | Adversarial (squeeze) |\n|--------|-------------------|----------------------|\n| Speed | 1-2 min | 5-10 min |\n| Depth | Single perspective | Blue + Red team |\n| Output | Issue list | Exploit PoCs + fixes |\n| Best for | Pre-commit checks | Pre-deployment review |\n\n## When NOT to Use This\n\n- Production systems (use real pentest tools)\n- Compliance audits (use certified auditors)\n- Legal verification (consult security lawyers)\n\n**Do use for**: pre-commit security checks, development-phase testing, architecture security review, CI\u002FCD security gates.\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## Execution Contract (MANDATORY - CANNOT SKIP)\n\nThis generated Codex skill preserves an enforced workflow contract from the source skill.\n\n**PROHIBITED:**\n- Do not summarize, simulate, or skip the referenced workflow command when this skill requires execution.\n- Do not claim provider output or validation artifacts exist without checking the actual files or command output.\n- Do not continue silently when a required provider, command, or host capability is unavailable; report the unavailable dependency and use a supported fallback.\n\n\n# Security Audit Skill\n\n**Your first output line MUST be:** `🐙 **CLAUDE OCTOPUS ACTIVATED** - Security Audit`\n\nInvokes the security-auditor persona for thorough security analysis during the `ink` (deliver) phase. Supports both quick OWASP scanning and full adversarial red\u002Fblue team testing.\n\n## Usage\n\n```bash\n# Quick scan via security-auditor persona\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh spawn security-auditor \"Scan for SQL injection vulnerabilities\"\n\n# Adversarial red team via squeeze workflow\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze \"Security audit the authentication module\"\n\n# Via auto-routing (detects security intent)\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh auto \"security audit the payment processing module\"\n```\n\n## Modes (Auto-Detected)\n\n| Mode | Auto-Trigger | Confidence Gate | Scope |\n|------|-------------|----------------|-------|\n| **Quick** (default) | Standard security scan, no sensitive files in diff | 8\u002F10 — only high-confidence findings | Changed files only |\n| **Deep** (auto-escalated) | Diff touches auth\u002Fsecurity\u002FCI files, OR explicit request | 2\u002F10 — flag anything suspicious | Entire codebase |\n\n**Auto-escalation to Deep mode:** The skill automatically switches to Deep mode when ANY of these are true:\n- Diff includes files matching: `*auth*`, `*login*`, `*password*`, `*session*`, `*token*`, `*secret*`, `*crypt*`, `*oauth*`, `*saml*`, `*jwt*`, `*permission*`, `*rbac*`, `*acl*`\n- Diff includes CI\u002FCD files: `.github\u002Fworkflows\u002F*`, `Dockerfile*`, `docker-compose*`, `.gitlab-ci*`\n- Diff includes dependency files: `package-lock.json`, `yarn.lock`, `Gemfile.lock`, `requirements.txt`, `go.sum`\n- The user explicitly says \"deep\", \"full\", \"comprehensive\", or \"CSO\"\n\nNo user action needed — mode detection happens automatically from the git diff context.\n\n## Model Selection Caveat: Fable 5.1\n\nBy default, do not dispatch security-audit passes to Claude Fable 5.1 or the preserved Fable 5 ID. Their safety classifiers can refuse adversarial red-team phrasing in authorized audits. Route these passes to `OCTOPUS_FABLE5_FALLBACK_MODEL` (default `claude-opus-5`) and keep prompts defensively framed (find and report vulnerabilities; do not request working exploits). Reject an exact model-qualified override that targets `claude-fable-5-1` or `claude-fable-5`. On refusal, retry exactly once on the fallback unless `OCTOPUS_FABLE5_NO_RETRY=1`; when retries are disabled or the retry refuses, surface the refusal without further dispatches. `OCTOPUS_FABLE5_MODE=off` is the explicit exception: it disables automatic rerouting for ordinary environment pins, while exact Fable security seats still fail closed. Details: `skills\u002Fblocks\u002Ffable5-prompting.md`.\n\n## Capabilities\n\n### Core (both modes)\n- OWASP Top 10 vulnerability detection\n- SQL injection and XSS scanning\n- Authentication\u002Fauthorization review\n- Secrets and credential detection\n- Dependency vulnerability assessment\n- Security configuration review\n\n### Secrets Archaeology (Deep mode)\nScan git history for leaked credentials that may have been \"deleted\" but remain in commits:\n\n```bash\n# Search git history for common secret patterns\ngit log --all -p --diff-filter=D -- '*.env' '*.key' '*.pem' 2>\u002Fdev\u002Fnull | head -200\ngit log --all -p -S 'AKIA' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # AWS keys\ngit log --all -p -S 'sk-[a-zA-Z0-9]{20,}' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # API keys\ngit log --all -p -S 'ghp_|gho_|github_pat_' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # GitHub tokens\ngit log --all -p -S 'password\\s*[:=]' --pickaxe-regex 2>\u002Fdev\u002Fnull | head -100  # Passwords\n```\n\nReport any findings with the commit SHA, file, and recommendation to rotate the credential.\n\n### CI\u002FCD Pipeline Security (Deep mode)\nAudit GitHub Actions and CI configuration for injection and privilege escalation:\n\n```bash\n# Find all workflow files\nfind .github\u002Fworkflows -name '*.yml' -o -name '*.yaml' 2>\u002Fdev\u002Fnull\n\n# Check for dangerous patterns:\n# 1. Untrusted input in run: blocks (command injection via PR titles\u002Fbranch names)\n# 2. pull_request_target with checkout of PR code (code execution from forks)\n# 3. Overly broad permissions (write-all, contents: write)\n# 4. Missing pinned action versions (uses: actions\u002Fcheckout vs actions\u002Fcheckout@v4)\n# 5. Secrets exposed to pull_request events (accessible to forks)\n```\n\nFlag each finding with severity (CRITICAL\u002FHIGH\u002FMEDIUM\u002FLOW).\n\n### Skill & Plugin Supply Chain (Deep mode)\nVerify integrity of installed Claude Code skills and plugins:\n\n```bash\n# List installed plugins\nls -la ~\u002F.claude\u002Fplugins\u002F 2>\u002Fdev\u002Fnull\n\n# Check for skills that execute arbitrary bash\ngrep -r 'exec\\|eval\\|bash -c' ~\u002F.claude\u002Fskills\u002F*\u002FSKILL.md 2>\u002Fdev\u002Fnull | head -20\n\n# Verify plugin sources (are they from known registries?)\ncat ~\u002F.claude\u002Fplugins\u002F*\u002Fplugin.json 2>\u002Fdev\u002Fnull | grep -E '\"source\"|\"registry\"'\n```\n\n### STRIDE Threat Modeling (Deep mode)\nFor the target component, enumerate threats across all 6 STRIDE categories:\n\n| Category | Question |\n|----------|----------|\n| **S**poofing | Can an attacker impersonate a user or component? |\n| **T**ampering | Can data be modified in transit or at rest? |\n| **R**epudiation | Can actions be denied without audit trail? |\n| **I**nformation Disclosure | Can sensitive data leak through logs, errors, or side channels? |\n| **D**enial of Service | Can the service be overwhelmed or starved? |\n| **E**levation of Privilege | Can a low-privilege user gain admin access? |\n\n## Persona Reference\n\nThis skill wraps the `security-auditor` persona defined in:\n- `agents\u002Fpersonas\u002Fsecurity-auditor.md`\n- CLI: `codex-review`\n- Model: `gpt-5.2-codex`\n- Phases: `ink`\n- Expertise: `owasp`, `vulnerability-scanning`, `security-review`\n\n## Example Prompts\n\n```\n\"Scan for hardcoded credentials in the codebase\"\n\"Check for CSRF vulnerabilities in form handlers\"\n\"Review the API authentication implementation\"\n\"Red team review the payment API\"\n```\n\n\n## Adversarial Mode (squeeze workflow)\n\nFor comprehensive security testing, use the squeeze workflow which runs a 4-phase adversarial cycle:\n\n1. **Blue Team** (Defense): Codex reviews code, identifies attack surface, proposes defenses\n2. **Red Team** (Attack): Antigravity attempts to break defenses, generates exploit PoCs\n3. **Remediation** (Fix): Codex patches all vulnerabilities found\n4. **Validation** (Verify): Antigravity re-tests, confirms fixes or fails\n\n```bash\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze \"[user's security request]\"\n```\n\n### OWASP Top 10 Coverage\n\n- Broken Access Control\n- Cryptographic Failures\n- Injection\n- Insecure Design\n- Security Misconfiguration\n- Vulnerable Components\n- Authentication Failures\n- Software Integrity Failures\n- Logging & Monitoring Failures\n- Server-Side Request Forgery\n\n### Additional Attack Patterns\n\n- Race conditions, business logic flaws\n- Denial of service, information disclosure\n- Client-side attacks (XSS, CSRF)\n\n### Advanced Options\n\n```bash\n# Focus on specific vulnerabilities\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze --principles security \"Audit for auth bypass only\"\n\n# Loop until all vulnerabilities fixed\n${HOME}\u002F.claude-octopus\u002Fplugin\u002Fscripts\u002Forchestrate.sh squeeze --loop --quality 100 \"Zero tolerance audit\"\n```\n\n### When to Use Adversarial Mode\n\n| Aspect | Quick Scan (spawn) | Adversarial (squeeze) |\n|--------|-------------------|----------------------|\n| Speed | 1-2 min | 5-10 min |\n| Depth | Single perspective | Blue + Red team |\n| Output | Issue list | Exploit PoCs + fixes |\n| Best for | Pre-commit checks | Pre-deployment review |\n\n## When NOT to Use This\n\n- Production systems (use real pentest tools)\n- Compliance audits (use certified auditors)\n- Legal verification (consult security lawyers)\n\n**Do use for**: pre-commit security checks, development-phase testing, architecture security review, CI\u002FCD security gates.\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","04-安全渗透\u002Foctopus-security-audit",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 octopus-security-audit",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill octopus-security-audit",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill octopus-security-audit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Foctopus-security-audit\u002FSKILL.md",[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",175,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F04-安全渗透\u002Foctopus-security-audit\u002Fagents\u002Fopenai.yaml",[53,61,66,73,80,87],{"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":60},"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",[],[],"2026-11-16 10:05:34",{"skillNo":62,"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":63,"categories":64,"keywords":65,"publishedAt":60},"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":60},"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":60},"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":60},"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":60},"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",[],[]]