[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFVZXHK63BG3DJM7DWS68K":3,"skill-same:01M6AFVZXHK63BG3DJM7DWS68K":105},{"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":23,"publishedAt":48,"linkOnly":49,"markdownContent":50,"markdownBody":51,"frontMatter":52,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":60,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":64,"ownerDescription":65,"updatedAt":66,"install":67,"resources":80},"01M6AFVZXHK63BG3DJM7DWS68K","supply-chain-guard",null,"Detect and remediate software supply chain attacks in npm, PyPI, crates.io, GitHub Actions, and CI\u002FCD pipelines by scanning for known compromised packages, malicious versions, filesystem IOCs, C2 indicators, and CI\u002FCD misconfigurations.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47],"supply","chain","supply chain guard","guard","supply chain","filesystem","2026","remediate","for","attacks","CI\u002FCD","software","io","scanning","malicious","indicators","c2","github actions","ci","actions","pypi","npm","packages","github","2026-11-10 10:12:30",false,"---\nname: supply-chain-guard\ndescription: \"Detect and remediate software supply chain attacks in npm, PyPI, crates.io, GitHub Actions, and CI\u002FCD pipelines by scanning for known compromised packages, malicious versions, filesystem IOCs, C2 indicators, and CI\u002FCD misconfigurations.\"\nmetadata:\n  author: dan-avila\n  version: '1.0'\n  ioc-db-date: '2026-03-31'\n---\n\n# Supply Chain Guard\n\nAutomated detection and remediation of software supply chain attacks across npm, PyPI, crates.io, GitHub Actions, and CI\u002FCD pipelines. Built from real-world attack intelligence gathered through March 31, 2026.\n\n## When to Use This Skill\n\nUse this skill when:\n\n- The user asks to audit a project's dependencies for security issues\n- Before deploying code to production\n- When investigating a potential supply chain compromise\n- When the user mentions a recent supply chain attack and wants to check their projects\n- As a regular security check in development workflows\n- When setting up CI\u002FCD pipelines and wanting to harden them\n- When a new supply chain attack is reported and the user wants to verify exposure\n\n## Instructions\n\n### Step 1: Understand the Project\n\nIdentify what the user's project uses:\n- **Node.js\u002Fnpm**: Look for `package.json`, `package-lock.json`, `yarn.lock`, `pnpm-lock.yaml`\n- **Python\u002FPyPI**: Look for `requirements.txt`, `Pipfile`, `pyproject.toml`, `poetry.lock`\n- **Rust\u002Fcrates.io**: Look for `Cargo.toml`, `Cargo.lock`\n- **CI\u002FCD**: Look for `.github\u002Fworkflows\u002F`, `Dockerfile`, `docker-compose.yml`\n\n### Step 2: Run the Appropriate Scanners\n\nThe skill includes three specialized scanners plus a unified runner. All scripts are in the `scripts\u002F` directory.\n\n**Full audit (recommended):**\n```bash\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-all.sh \u002Fpath\u002Fto\u002Fproject\n```\n\n**Individual scanners:**\n```bash\n# npm\u002FNode.js projects\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-npm.sh \u002Fpath\u002Fto\u002Fproject\n\n# Python\u002FPyPI projects\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-python.sh \u002Fpath\u002Fto\u002Fproject\n\n# CI\u002FCD pipeline audit\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-ci.sh \u002Fpath\u002Fto\u002Fproject\n```\n\nEach scanner checks for:\n1. **Known compromised packages** — exact matches against the IOC database\n2. **Malicious versions** — specific version numbers known to contain malware\n3. **Filesystem IOCs** — persistence mechanisms left by attackers\n4. **Network IOCs** — C2 domains and IPs in source code\n5. **CI\u002FCD misconfigurations** — unpinned actions, dangerous triggers, exposed secrets\n6. **Credential exposure** — npm tokens, PyPI credentials, .env files\n\n### Step 3: Interpret Results\n\nScanners exit with the number of issues found (0 = clean). Issues are categorized:\n\n- **[CRITICAL]** — Known malicious package or active IOC detected. Immediate action required.\n- **[WARNING]** — Security concern that needs investigation. May not be an active compromise.\n\n### Step 4: Remediate\n\nBased on findings, guide the user through remediation:\n\n#### If a compromised package is found:\n1. Remove or downgrade to a known safe version immediately\n2. Clear package caches: `npm cache clean --force` \u002F `pip cache purge`\n3. Delete `node_modules` \u002F `.venv` and reinstall from lockfile\n4. Rotate ALL credentials that were accessible from the environment\n\n#### If filesystem IOCs are found:\n1. The system should be treated as **fully compromised**\n2. Identify and remove persistence mechanisms (systemd services, .pth files, cron jobs)\n3. Rotate every credential on the system\n4. Audit cloud provider logs (AWS CloudTrail, GCP Audit Logs, Azure Activity Log)\n5. Check for lateral movement in Kubernetes clusters\n6. Consider reimaging the machine\n\n#### If CI\u002FCD issues are found:\n1. Pin all GitHub Actions to full commit SHAs (not version tags)\n2. Add `--ignore-scripts` to npm install\u002Fci commands\n3. Add `--require-hashes` to pip install commands\n4. Remove or secure `pull_request_target` triggers\n5. Apply least-privilege permissions to workflow tokens\n6. Audit pipeline execution logs for the attack window periods\n\n### Step 5: Harden the Project\n\nAfter remediation, recommend these preventive measures:\n\n1. **Lock everything**: Exact version pins + lockfiles committed to repo\n2. **Hash-verify**: Use `npm ci` (not `npm install`), `pip install --require-hashes`\n3. **Disable scripts**: Use `--ignore-scripts` by default, enable only for trusted packages\n4. **Pin actions**: All GitHub Actions pinned to full SHA, never tags\n5. **Scope tokens**: CI\u002FCD tokens should have minimal permissions\n6. **Monitor**: Set up automated dependency scanning (but verify the scanner itself is not compromised — see Trivy incident)\n7. **Network controls**: Block known C2 domains\u002FIPs at firewall level\n8. **Audit regularly**: Run this scanner before every deployment\n\n## Reference Files\n\n- `references\u002Fioc-database.md` — Full IOC database with all compromised packages, malicious versions, C2 infrastructure, filesystem indicators, and attack timelines. Read this file for detailed intelligence on specific attacks.\n\n## Current Threat Landscape (as of 2026-03-31)\n\n### Active Campaign: TeamPCP (CRITICAL)\n\nThe most significant active threat. TeamPCP is executing a cascading credential-chain campaign:\n- Compromised Trivy (security scanner) → stole CI\u002FCD secrets from thousands of pipelines\n- Used stolen npm tokens to deploy CanisterWorm across 141+ npm packages\n- Used stolen PyPI tokens to backdoor LiteLLM (95M monthly downloads) and Telnyx\n- Uses blockchain (ICP) for C2, making takedown impossible\n- Deploys WAV steganography for payload delivery\n- Targets Kubernetes for lateral movement\n- Has a destructive variant that wipes Iranian systems\n\n### Active: axios npm Hijack (2026-03-31)\n\n- axios@1.14.1 and axios@0.30.4 contain RAT dropper via fake `plain-crypto-js` dependency\n- 300M+ weekly downloads makes this extremely high-impact\n- Cross-platform RAT for macOS, Windows, and Linux\n- Compromised maintainer account (jasonsaayman)\n\n### Recent: Malicious Rust Crates (2026-02\u002F03)\n\n- 5 crates impersonating time utilities on crates.io\n- Steal .env files, AWS credentials, SSH keys\n- First significant supply chain attack targeting Rust ecosystem\n\n### Historical but Relevant: Shai-Hulud Worm\n\n- Self-replicating npm worm that compromised ~1000 packages\n- Targets npm tokens for self-propagation\n- Destructive fallback: wipes home directory if exfiltration fails\n\n## Updating the IOC Database\n\nWhen new supply chain attacks are reported:\n\n1. Search for the latest advisories from Socket, Aikido, Endor Labs, Snyk, JFrog\n2. Update `references\u002Fioc-database.md` with new packages, versions, domains, IPs\n3. Update the scanner scripts with new package entries in the MALICIOUS_* arrays\n4. Update the `ioc-db-date` in the SKILL.md frontmatter\n","# Supply Chain Guard\n\nAutomated detection and remediation of software supply chain attacks across npm, PyPI, crates.io, GitHub Actions, and CI\u002FCD pipelines. Built from real-world attack intelligence gathered through March 31, 2026.\n\n## When to Use This Skill\n\nUse this skill when:\n\n- The user asks to audit a project's dependencies for security issues\n- Before deploying code to production\n- When investigating a potential supply chain compromise\n- When the user mentions a recent supply chain attack and wants to check their projects\n- As a regular security check in development workflows\n- When setting up CI\u002FCD pipelines and wanting to harden them\n- When a new supply chain attack is reported and the user wants to verify exposure\n\n## Instructions\n\n### Step 1: Understand the Project\n\nIdentify what the user's project uses:\n- **Node.js\u002Fnpm**: Look for `package.json`, `package-lock.json`, `yarn.lock`, `pnpm-lock.yaml`\n- **Python\u002FPyPI**: Look for `requirements.txt`, `Pipfile`, `pyproject.toml`, `poetry.lock`\n- **Rust\u002Fcrates.io**: Look for `Cargo.toml`, `Cargo.lock`\n- **CI\u002FCD**: Look for `.github\u002Fworkflows\u002F`, `Dockerfile`, `docker-compose.yml`\n\n### Step 2: Run the Appropriate Scanners\n\nThe skill includes three specialized scanners plus a unified runner. All scripts are in the `scripts\u002F` directory.\n\n**Full audit (recommended):**\n```bash\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-all.sh \u002Fpath\u002Fto\u002Fproject\n```\n\n**Individual scanners:**\n```bash\n# npm\u002FNode.js projects\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-npm.sh \u002Fpath\u002Fto\u002Fproject\n\n# Python\u002FPyPI projects\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-python.sh \u002Fpath\u002Fto\u002Fproject\n\n# CI\u002FCD pipeline audit\nbash \u002Fpath\u002Fto\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-ci.sh \u002Fpath\u002Fto\u002Fproject\n```\n\nEach scanner checks for:\n1. **Known compromised packages** — exact matches against the IOC database\n2. **Malicious versions** — specific version numbers known to contain malware\n3. **Filesystem IOCs** — persistence mechanisms left by attackers\n4. **Network IOCs** — C2 domains and IPs in source code\n5. **CI\u002FCD misconfigurations** — unpinned actions, dangerous triggers, exposed secrets\n6. **Credential exposure** — npm tokens, PyPI credentials, .env files\n\n### Step 3: Interpret Results\n\nScanners exit with the number of issues found (0 = clean). Issues are categorized:\n\n- **[CRITICAL]** — Known malicious package or active IOC detected. Immediate action required.\n- **[WARNING]** — Security concern that needs investigation. May not be an active compromise.\n\n### Step 4: Remediate\n\nBased on findings, guide the user through remediation:\n\n#### If a compromised package is found:\n1. Remove or downgrade to a known safe version immediately\n2. Clear package caches: `npm cache clean --force` \u002F `pip cache purge`\n3. Delete `node_modules` \u002F `.venv` and reinstall from lockfile\n4. Rotate ALL credentials that were accessible from the environment\n\n#### If filesystem IOCs are found:\n1. The system should be treated as **fully compromised**\n2. Identify and remove persistence mechanisms (systemd services, .pth files, cron jobs)\n3. Rotate every credential on the system\n4. Audit cloud provider logs (AWS CloudTrail, GCP Audit Logs, Azure Activity Log)\n5. Check for lateral movement in Kubernetes clusters\n6. Consider reimaging the machine\n\n#### If CI\u002FCD issues are found:\n1. Pin all GitHub Actions to full commit SHAs (not version tags)\n2. Add `--ignore-scripts` to npm install\u002Fci commands\n3. Add `--require-hashes` to pip install commands\n4. Remove or secure `pull_request_target` triggers\n5. Apply least-privilege permissions to workflow tokens\n6. Audit pipeline execution logs for the attack window periods\n\n### Step 5: Harden the Project\n\nAfter remediation, recommend these preventive measures:\n\n1. **Lock everything**: Exact version pins + lockfiles committed to repo\n2. **Hash-verify**: Use `npm ci` (not `npm install`), `pip install --require-hashes`\n3. **Disable scripts**: Use `--ignore-scripts` by default, enable only for trusted packages\n4. **Pin actions**: All GitHub Actions pinned to full SHA, never tags\n5. **Scope tokens**: CI\u002FCD tokens should have minimal permissions\n6. **Monitor**: Set up automated dependency scanning (but verify the scanner itself is not compromised — see Trivy incident)\n7. **Network controls**: Block known C2 domains\u002FIPs at firewall level\n8. **Audit regularly**: Run this scanner before every deployment\n\n## Reference Files\n\n- `references\u002Fioc-database.md` — Full IOC database with all compromised packages, malicious versions, C2 infrastructure, filesystem indicators, and attack timelines. Read this file for detailed intelligence on specific attacks.\n\n## Current Threat Landscape (as of 2026-03-31)\n\n### Active Campaign: TeamPCP (CRITICAL)\n\nThe most significant active threat. TeamPCP is executing a cascading credential-chain campaign:\n- Compromised Trivy (security scanner) → stole CI\u002FCD secrets from thousands of pipelines\n- Used stolen npm tokens to deploy CanisterWorm across 141+ npm packages\n- Used stolen PyPI tokens to backdoor LiteLLM (95M monthly downloads) and Telnyx\n- Uses blockchain (ICP) for C2, making takedown impossible\n- Deploys WAV steganography for payload delivery\n- Targets Kubernetes for lateral movement\n- Has a destructive variant that wipes Iranian systems\n\n### Active: axios npm Hijack (2026-03-31)\n\n- axios@1.14.1 and axios@0.30.4 contain RAT dropper via fake `plain-crypto-js` dependency\n- 300M+ weekly downloads makes this extremely high-impact\n- Cross-platform RAT for macOS, Windows, and Linux\n- Compromised maintainer account (jasonsaayman)\n\n### Recent: Malicious Rust Crates (2026-02\u002F03)\n\n- 5 crates impersonating time utilities on crates.io\n- Steal .env files, AWS credentials, SSH keys\n- First significant supply chain attack targeting Rust ecosystem\n\n### Historical but Relevant: Shai-Hulud Worm\n\n- Self-replicating npm worm that compromised ~1000 packages\n- Targets npm tokens for self-propagation\n- Destructive fallback: wipes home directory if exfiltration fails\n\n## Updating the IOC Database\n\nWhen new supply chain attacks are reported:\n\n1. Search for the latest advisories from Socket, Aikido, Endor Labs, Snyk, JFrog\n2. Update `references\u002Fioc-database.md` with new packages, versions, domains, IPs\n3. Update the scanner scripts with new package entries in the MALICIOUS_* arrays\n4. Update the `ioc-db-date` in the SKILL.md frontmatter\n",{"name":5,"metadata":53,"description":7},{"author":54,"version":55,"ioc-db-date":56},"dan-avila","1.0","2026-03-31","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add davila7\u002Fclaude-code-templates --skill supply-chain-guard",{"tool":73,"command":74},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill supply-chain-guard",{"tool":76,"command":77},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill supply-chain-guard","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002FSKILL.md",true,[81,87,93,97,101],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fioc-database.md","REFERENCE","参考文档",5750,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002Freferences\u002Fioc-database.md",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fscan-all.sh","SCRIPT","脚本",4618,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-all.sh",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Fscan-ci.sh",10341,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-ci.sh",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fscan-npm.sh",12451,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-npm.sh",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Fscan-python.sh",10835,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fsupply-chain-guard\u002Fscripts\u002Fscan-python.sh",[106,135,162,194,229,253],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"publishedAt":48},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,119,120,32,121,122,123,124,125,126,127,128,129,130,131,132,133,134],"scoring","pool","wealthville pool scoring","liquidity","which","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":48},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[141],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[143,144,145,146,147,148,149,150,151,152,153,124,154,155,156,157,158,159,160,161],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":177,"publishedAt":48},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[168,171,172],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":173,"categoryName":174,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[178,27,179,180,181,182,183,32,184,185,186,187,188,189,190,123,191,192,124,193],"readonly","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":195,"name":196,"nameZh":6,"description":197,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":199,"sourceHtmlUrl":200,"categories":201,"keywords":205,"publishedAt":48},"01M6AFY6F7CC2BBZP1QD6VTNVC","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[202],{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",[206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,32,228],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":230,"name":231,"nameZh":6,"description":232,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":233,"sourceHtmlUrl":234,"categories":235,"keywords":240,"publishedAt":48},"01M6AFWF33SFV9Z3SF4PEEE4BF","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[236,239],{"categoryNo":237,"categoryName":238,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},[241,242,243,244,245,207,246,216,217,247,248,249,250,32,251,126,252],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":254,"name":255,"nameZh":6,"description":256,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":198,"licenseFileUrl":257,"sourceHtmlUrl":258,"categories":259,"keywords":267,"publishedAt":48},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[260,263,264],{"categoryNo":261,"categoryName":262,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":265,"categoryName":266,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000036","内容创作者",[268,269,270,271,272,273,274,275,209,276,219,154,277,278,279,280,281,189,282,124,283,284,285,286,287,132,288],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]