[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CDND1C6GAATS5KSXP48TRC":3,"skill-same:01M7CDND1C6GAATS5KSXP48TRC":48},{"skillNo":4,"name":5,"nameZh":6,"description":5,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"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":6,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CDND1C6GAATS5KSXP48TRC","sharp-edges",null,"YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fsharp-edges\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: sharp-edges\ndescription: sharp-edges\nrisk: unknown\nsource: community\n---\n\n---\nname: sharp-edges\ndescription: \"Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by...\n---\n\n# Sharp Edges Analysis\n\nEvaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Identifies designs where the \"easy path\" leads to insecurity.\n\n## When to Use\n- Reviewing API or library design decisions\n- Auditing configuration schemas for dangerous options\n- Evaluating cryptographic API ergonomics\n- Assessing authentication\u002Fauthorization interfaces\n- Reviewing any code that exposes security-relevant choices to developers\n\n## When NOT to Use\n\n- Implementation bugs (use standard code review)\n- Business logic flaws (use domain-specific analysis)\n- Performance optimization (different concern)\n\n## Core Principle\n\n**The pit of success**: Secure usage should be the path of least resistance. If developers must understand cryptography, read documentation carefully, or remember special rules to avoid vulnerabilities, the API has failed.\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"It's documented\" | Developers don't read docs under deadline pressure | Make the secure choice the default or only option |\n| \"Advanced users need flexibility\" | Flexibility creates footguns; most \"advanced\" usage is copy-paste | Provide safe high-level APIs; hide primitives |\n| \"It's the developer's responsibility\" | Blame-shifting; you designed the footgun | Remove the footgun or make it impossible to misuse |\n| \"Nobody would actually do that\" | Developers do everything imaginable under pressure | Assume maximum developer confusion |\n| \"It's just a configuration option\" | Config is code; wrong configs ship to production | Validate configs; reject dangerous combinations |\n| \"We need backwards compatibility\" | Insecure defaults can't be grandfather-claused | Deprecate loudly; force migration |\n\n## Sharp Edge Categories\n\n### 1. Algorithm\u002FMode Selection Footguns\n\nAPIs that let developers choose algorithms invite choosing wrong ones.\n\n**The JWT Pattern** (canonical example):\n- Header specifies algorithm: attacker can set `\"alg\": \"none\"` to bypass signatures\n- Algorithm confusion: RSA public key used as HMAC secret when switching RS256→HS256\n- Root cause: Letting untrusted input control security-critical decisions\n\n**Detection patterns:**\n- Function parameters like `algorithm`, `mode`, `cipher`, `hash_type`\n- Enums\u002Fstrings selecting cryptographic primitives\n- Configuration options for security mechanisms\n\n**Example - PHP password_hash allowing weak algorithms:**\n```php\n\u002F\u002F DANGEROUS: allows crc32, md5, sha1\npassword_hash($password, PASSWORD_DEFAULT); \u002F\u002F Good - no choice\nhash($algorithm, $password); \u002F\u002F BAD: accepts \"crc32\"\n```\n\n### 2. Dangerous Defaults\n\nDefaults that are insecure, or zero\u002Fempty values that disable security.\n\n**The OTP Lifetime Pattern:**\n```python\n# What happens when lifetime=0?\ndef verify_otp(code, lifetime=300):  # 300 seconds default\n    if lifetime == 0:\n        return True  # OOPS: 0 means \"accept all\"?\n        # Or does it mean \"expired immediately\"?\n```\n\n**Detection patterns:**\n- Timeouts\u002Flifetimes that accept 0 (infinite? immediate expiry?)\n- Empty strings that bypass checks\n- Null values that skip validation\n- Boolean defaults that disable security features\n- Negative values with undefined semantics\n\n**Questions to ask:**\n- What happens with `timeout=0`? `max_attempts=0`? `key=\"\"`?\n- Is the default the most secure option?\n- Can any default value disable security entirely?\n\n### 3. Primitive vs. Semantic APIs\n\nAPIs that expose raw bytes instead of meaningful types invite type confusion.\n\n**The Libsodium vs. Halite Pattern:**\n\n```php\n\u002F\u002F Libsodium (primitives): bytes are bytes\nsodium_crypto_box($message, $nonce, $keypair);\n\u002F\u002F Easy to: swap nonce\u002Fkeypair, reuse nonces, use wrong key type\n\n\u002F\u002F Halite (semantic): types enforce correct usage\nCrypto::seal($message, new EncryptionPublicKey($key));\n\u002F\u002F Wrong key type = type error, not silent failure\n```\n\n**Detection patterns:**\n- Functions taking `bytes`, `string`, `[]byte` for distinct security concepts\n- Parameters that could be swapped without type errors\n- Same type used for keys, nonces, ciphertexts, signatures\n\n**The comparison footgun:**\n```go\n\u002F\u002F Timing-safe comparison looks identical to unsafe\nif hmac == expected { }           \u002F\u002F BAD: timing attack\nif hmac.Equal(mac, expected) { }  \u002F\u002F Good: constant-time\n\u002F\u002F Same types, different security properties\n```\n\n### 4. Configuration Cliffs\n\nOne wrong setting creates catastrophic failure, with no warning.\n\n**Detection patterns:**\n- Boolean flags that disable security entirely\n- String configs that aren't validated\n- Combinations of settings that interact dangerously\n- Environment variables that override security settings\n- Constructor parameters with sensible defaults but no validation (callers can override with insecure values)\n\n**Examples:**\n```yaml\n# One typo = disaster\nverify_ssl: fasle  # Typo silently accepted as truthy?\n\n# Magic values\nsession_timeout: -1  # Does this mean \"never expire\"?\n\n# Dangerous combinations accepted silently\nauth_required: true\nbypass_auth_for_health_checks: true\nhealth_check_path: \"\u002F\"  # Oops\n```\n\n```php\n\u002F\u002F Sensible default doesn't protect against bad callers\npublic function __construct(\n    public string $hashAlgo = 'sha256',  \u002F\u002F Good default...\n    public int $otpLifetime = 120,       \u002F\u002F ...but accepts md5, 0, etc.\n) {}\n```\n\nSee config-patterns.md for detailed patterns.\n\n### 5. Silent Failures\n\nErrors that don't surface, or success that masks failure.\n\n**Detection patterns:**\n- Functions returning booleans instead of throwing on security failures\n- Empty catch blocks around security operations\n- Default values substituted on parse errors\n- Verification functions that \"succeed\" on malformed input\n\n**Examples:**\n```python\n# Silent bypass\ndef verify_signature(sig, data, key):\n    if not key:\n        return True  # No key = skip verification?!\n\n# Return value ignored\nsignature.verify(data, sig)  # Throws on failure\ncrypto.verify(data, sig)     # Returns False on failure\n# Developer forgets to check return value\n```\n\n### 6. Stringly-Typed Security\n\nSecurity-critical values as plain strings enable injection and confusion.\n\n**Detection patterns:**\n- SQL\u002Fcommands built from string concatenation\n- Permissions as comma-separated strings\n- Roles\u002Fscopes as arbitrary strings instead of enums\n- URLs constructed by joining strings\n\n**The permission accumulation footgun:**\n```python\npermissions = \"read,write\"\npermissions += \",admin\"  # Too easy to escalate\n\n# vs. type-safe\npermissions = {Permission.READ, Permission.WRITE}\npermissions.add(Permission.ADMIN)  # At least it's explicit\n```\n\n## Analysis Workflow\n\n### Phase 1: Surface Identification\n\n1. **Map security-relevant APIs**: authentication, authorization, cryptography, session management, input validation\n2. **Identify developer choice points**: Where can developers select algorithms, configure timeouts, choose modes?\n3. **Find configuration schemas**: Environment variables, config files, constructor parameters\n\n### Phase 2: Edge Case Probing\n\nFor each choice point, ask:\n- **Zero\u002Fempty\u002Fnull**: What happens with `0`, `\"\"`, `null`, `[]`?\n- **Negative values**: What does `-1` mean? Infinite? Error?\n- **Type confusion**: Can different security concepts be swapped?\n- **Default values**: Is the default secure? Is it documented?\n- **Error paths**: What happens on invalid input? Silent acceptance?\n\n### Phase 3: Threat Modeling\n\nConsider three adversaries:\n\n1. **The Scoundrel**: Actively malicious developer or attacker controlling config\n   - Can they disable security via configuration?\n   - Can they downgrade algorithms?\n   - Can they inject malicious values?\n\n2. **The Lazy Developer**: Copy-pastes examples, skips documentation\n   - Will the first example they find be secure?\n   - Is the path of least resistance secure?\n   - Do error messages guide toward secure usage?\n\n3. **The Confused Developer**: Misunderstands the API\n   - Can they swap parameters without type errors?\n   - Can they use the wrong key\u002Falgorithm\u002Fmode by accident?\n   - Are failure modes obvious or silent?\n\n### Phase 4: Validate Findings\n\nFor each identified sharp edge:\n\n1. **Reproduce the misuse**: Write minimal code demonstrating the footgun\n2. **Verify exploitability**: Does the misuse create a real vulnerability?\n3. **Check documentation**: Is the danger documented? (Documentation doesn't excuse bad design, but affects severity)\n4. **Test mitigations**: Can the API be used safely with reasonable effort?\n\nIf a finding seems questionable, return to Phase 2 and probe more edge cases.\n\n## Severity Classification\n\n| Severity | Criteria | Examples |\n|----------|----------|----------|\n| Critical | Default or obvious usage is insecure | `verify: false` default; empty password allowed |\n| High | Easy misconfiguration breaks security | Algorithm parameter accepts \"none\" |\n| Medium | Unusual but possible misconfiguration | Negative timeout has unexpected meaning |\n| Low | Requires deliberate misuse | Obscure parameter combination |\n\n## References\n\n**By category:**\n\n- **Cryptographic APIs**: See references\u002Fcrypto-apis.md\n- **Configuration Patterns**: See references\u002Fconfig-patterns.md\n- **Authentication\u002FSession**: See references\u002Fauth-patterns.md\n- **Real-World Case Studies**: See references\u002Fcase-studies.md (OpenSSL, GMP, etc.)\n\n**By language** (general footguns, not crypto-specific):\n\n| Language | Guide |\n|----------|-------|\n| C\u002FC++ | references\u002Flang-c.md |\n| Go | references\u002Flang-go.md |\n| Rust | references\u002Flang-rust.md |\n| Swift | references\u002Flang-swift.md |\n| Java | references\u002Flang-java.md |\n| Kotlin | references\u002Flang-kotlin.md |\n| C# | references\u002Flang-csharp.md |\n| PHP | references\u002Flang-php.md |\n| JavaScript\u002FTypeScript | references\u002Flang-javascript.md |\n| Python | references\u002Flang-python.md |\n| Ruby | references\u002Flang-ruby.md |\n\nSee also references\u002Flanguage-specific.md for a combined quick reference.\n\n## Quality Checklist\n\nBefore concluding analysis:\n\n- [ ] Probed all zero\u002Fempty\u002Fnull edge cases\n- [ ] Verified defaults are secure\n- [ ] Checked for algorithm\u002Fmode selection footguns\n- [ ] Tested type confusion between security concepts\n- [ ] Considered all three adversary types\n- [ ] Verified error paths don't bypass security\n- [ ] Checked configuration validation\n- [ ] Constructor params validated (not just defaulted) - see config-patterns.md\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","---\nname: sharp-edges\ndescription: \"Identifies error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes. Use when reviewing API designs, configuration schemas, cryptographic library ergonomics, or evaluating whether code follows 'secure by...\n---\n\n# Sharp Edges Analysis\n\nEvaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Identifies designs where the \"easy path\" leads to insecurity.\n\n## When to Use\n- Reviewing API or library design decisions\n- Auditing configuration schemas for dangerous options\n- Evaluating cryptographic API ergonomics\n- Assessing authentication\u002Fauthorization interfaces\n- Reviewing any code that exposes security-relevant choices to developers\n\n## When NOT to Use\n\n- Implementation bugs (use standard code review)\n- Business logic flaws (use domain-specific analysis)\n- Performance optimization (different concern)\n\n## Core Principle\n\n**The pit of success**: Secure usage should be the path of least resistance. If developers must understand cryptography, read documentation carefully, or remember special rules to avoid vulnerabilities, the API has failed.\n\n## Rationalizations to Reject\n\n| Rationalization | Why It's Wrong | Required Action |\n|-----------------|----------------|-----------------|\n| \"It's documented\" | Developers don't read docs under deadline pressure | Make the secure choice the default or only option |\n| \"Advanced users need flexibility\" | Flexibility creates footguns; most \"advanced\" usage is copy-paste | Provide safe high-level APIs; hide primitives |\n| \"It's the developer's responsibility\" | Blame-shifting; you designed the footgun | Remove the footgun or make it impossible to misuse |\n| \"Nobody would actually do that\" | Developers do everything imaginable under pressure | Assume maximum developer confusion |\n| \"It's just a configuration option\" | Config is code; wrong configs ship to production | Validate configs; reject dangerous combinations |\n| \"We need backwards compatibility\" | Insecure defaults can't be grandfather-claused | Deprecate loudly; force migration |\n\n## Sharp Edge Categories\n\n### 1. Algorithm\u002FMode Selection Footguns\n\nAPIs that let developers choose algorithms invite choosing wrong ones.\n\n**The JWT Pattern** (canonical example):\n- Header specifies algorithm: attacker can set `\"alg\": \"none\"` to bypass signatures\n- Algorithm confusion: RSA public key used as HMAC secret when switching RS256→HS256\n- Root cause: Letting untrusted input control security-critical decisions\n\n**Detection patterns:**\n- Function parameters like `algorithm`, `mode`, `cipher`, `hash_type`\n- Enums\u002Fstrings selecting cryptographic primitives\n- Configuration options for security mechanisms\n\n**Example - PHP password_hash allowing weak algorithms:**\n```php\n\u002F\u002F DANGEROUS: allows crc32, md5, sha1\npassword_hash($password, PASSWORD_DEFAULT); \u002F\u002F Good - no choice\nhash($algorithm, $password); \u002F\u002F BAD: accepts \"crc32\"\n```\n\n### 2. Dangerous Defaults\n\nDefaults that are insecure, or zero\u002Fempty values that disable security.\n\n**The OTP Lifetime Pattern:**\n```python\n# What happens when lifetime=0?\ndef verify_otp(code, lifetime=300):  # 300 seconds default\n    if lifetime == 0:\n        return True  # OOPS: 0 means \"accept all\"?\n        # Or does it mean \"expired immediately\"?\n```\n\n**Detection patterns:**\n- Timeouts\u002Flifetimes that accept 0 (infinite? immediate expiry?)\n- Empty strings that bypass checks\n- Null values that skip validation\n- Boolean defaults that disable security features\n- Negative values with undefined semantics\n\n**Questions to ask:**\n- What happens with `timeout=0`? `max_attempts=0`? `key=\"\"`?\n- Is the default the most secure option?\n- Can any default value disable security entirely?\n\n### 3. Primitive vs. Semantic APIs\n\nAPIs that expose raw bytes instead of meaningful types invite type confusion.\n\n**The Libsodium vs. Halite Pattern:**\n\n```php\n\u002F\u002F Libsodium (primitives): bytes are bytes\nsodium_crypto_box($message, $nonce, $keypair);\n\u002F\u002F Easy to: swap nonce\u002Fkeypair, reuse nonces, use wrong key type\n\n\u002F\u002F Halite (semantic): types enforce correct usage\nCrypto::seal($message, new EncryptionPublicKey($key));\n\u002F\u002F Wrong key type = type error, not silent failure\n```\n\n**Detection patterns:**\n- Functions taking `bytes`, `string`, `[]byte` for distinct security concepts\n- Parameters that could be swapped without type errors\n- Same type used for keys, nonces, ciphertexts, signatures\n\n**The comparison footgun:**\n```go\n\u002F\u002F Timing-safe comparison looks identical to unsafe\nif hmac == expected { }           \u002F\u002F BAD: timing attack\nif hmac.Equal(mac, expected) { }  \u002F\u002F Good: constant-time\n\u002F\u002F Same types, different security properties\n```\n\n### 4. Configuration Cliffs\n\nOne wrong setting creates catastrophic failure, with no warning.\n\n**Detection patterns:**\n- Boolean flags that disable security entirely\n- String configs that aren't validated\n- Combinations of settings that interact dangerously\n- Environment variables that override security settings\n- Constructor parameters with sensible defaults but no validation (callers can override with insecure values)\n\n**Examples:**\n```yaml\n# One typo = disaster\nverify_ssl: fasle  # Typo silently accepted as truthy?\n\n# Magic values\nsession_timeout: -1  # Does this mean \"never expire\"?\n\n# Dangerous combinations accepted silently\nauth_required: true\nbypass_auth_for_health_checks: true\nhealth_check_path: \"\u002F\"  # Oops\n```\n\n```php\n\u002F\u002F Sensible default doesn't protect against bad callers\npublic function __construct(\n    public string $hashAlgo = 'sha256',  \u002F\u002F Good default...\n    public int $otpLifetime = 120,       \u002F\u002F ...but accepts md5, 0, etc.\n) {}\n```\n\nSee config-patterns.md for detailed patterns.\n\n### 5. Silent Failures\n\nErrors that don't surface, or success that masks failure.\n\n**Detection patterns:**\n- Functions returning booleans instead of throwing on security failures\n- Empty catch blocks around security operations\n- Default values substituted on parse errors\n- Verification functions that \"succeed\" on malformed input\n\n**Examples:**\n```python\n# Silent bypass\ndef verify_signature(sig, data, key):\n    if not key:\n        return True  # No key = skip verification?!\n\n# Return value ignored\nsignature.verify(data, sig)  # Throws on failure\ncrypto.verify(data, sig)     # Returns False on failure\n# Developer forgets to check return value\n```\n\n### 6. Stringly-Typed Security\n\nSecurity-critical values as plain strings enable injection and confusion.\n\n**Detection patterns:**\n- SQL\u002Fcommands built from string concatenation\n- Permissions as comma-separated strings\n- Roles\u002Fscopes as arbitrary strings instead of enums\n- URLs constructed by joining strings\n\n**The permission accumulation footgun:**\n```python\npermissions = \"read,write\"\npermissions += \",admin\"  # Too easy to escalate\n\n# vs. type-safe\npermissions = {Permission.READ, Permission.WRITE}\npermissions.add(Permission.ADMIN)  # At least it's explicit\n```\n\n## Analysis Workflow\n\n### Phase 1: Surface Identification\n\n1. **Map security-relevant APIs**: authentication, authorization, cryptography, session management, input validation\n2. **Identify developer choice points**: Where can developers select algorithms, configure timeouts, choose modes?\n3. **Find configuration schemas**: Environment variables, config files, constructor parameters\n\n### Phase 2: Edge Case Probing\n\nFor each choice point, ask:\n- **Zero\u002Fempty\u002Fnull**: What happens with `0`, `\"\"`, `null`, `[]`?\n- **Negative values**: What does `-1` mean? Infinite? Error?\n- **Type confusion**: Can different security concepts be swapped?\n- **Default values**: Is the default secure? Is it documented?\n- **Error paths**: What happens on invalid input? Silent acceptance?\n\n### Phase 3: Threat Modeling\n\nConsider three adversaries:\n\n1. **The Scoundrel**: Actively malicious developer or attacker controlling config\n   - Can they disable security via configuration?\n   - Can they downgrade algorithms?\n   - Can they inject malicious values?\n\n2. **The Lazy Developer**: Copy-pastes examples, skips documentation\n   - Will the first example they find be secure?\n   - Is the path of least resistance secure?\n   - Do error messages guide toward secure usage?\n\n3. **The Confused Developer**: Misunderstands the API\n   - Can they swap parameters without type errors?\n   - Can they use the wrong key\u002Falgorithm\u002Fmode by accident?\n   - Are failure modes obvious or silent?\n\n### Phase 4: Validate Findings\n\nFor each identified sharp edge:\n\n1. **Reproduce the misuse**: Write minimal code demonstrating the footgun\n2. **Verify exploitability**: Does the misuse create a real vulnerability?\n3. **Check documentation**: Is the danger documented? (Documentation doesn't excuse bad design, but affects severity)\n4. **Test mitigations**: Can the API be used safely with reasonable effort?\n\nIf a finding seems questionable, return to Phase 2 and probe more edge cases.\n\n## Severity Classification\n\n| Severity | Criteria | Examples |\n|----------|----------|----------|\n| Critical | Default or obvious usage is insecure | `verify: false` default; empty password allowed |\n| High | Easy misconfiguration breaks security | Algorithm parameter accepts \"none\" |\n| Medium | Unusual but possible misconfiguration | Negative timeout has unexpected meaning |\n| Low | Requires deliberate misuse | Obscure parameter combination |\n\n## References\n\n**By category:**\n\n- **Cryptographic APIs**: See references\u002Fcrypto-apis.md\n- **Configuration Patterns**: See references\u002Fconfig-patterns.md\n- **Authentication\u002FSession**: See references\u002Fauth-patterns.md\n- **Real-World Case Studies**: See references\u002Fcase-studies.md (OpenSSL, GMP, etc.)\n\n**By language** (general footguns, not crypto-specific):\n\n| Language | Guide |\n|----------|-------|\n| C\u002FC++ | references\u002Flang-c.md |\n| Go | references\u002Flang-go.md |\n| Rust | references\u002Flang-rust.md |\n| Swift | references\u002Flang-swift.md |\n| Java | references\u002Flang-java.md |\n| Kotlin | references\u002Flang-kotlin.md |\n| C# | references\u002Flang-csharp.md |\n| PHP | references\u002Flang-php.md |\n| JavaScript\u002FTypeScript | references\u002Flang-javascript.md |\n| Python | references\u002Flang-python.md |\n| Ruby | references\u002Flang-ruby.md |\n\nSee also references\u002Flanguage-specific.md for a combined quick reference.\n\n## Quality Checklist\n\nBefore concluding analysis:\n\n- [ ] Probed all zero\u002Fempty\u002Fnull edge cases\n- [ ] Verified defaults are secure\n- [ ] Checked for algorithm\u002Fmode selection footguns\n- [ ] Tested type confusion between security concepts\n- [ ] Considered all three adversary types\n- [ ] Verified error paths don't bypass security\n- [ ] Checked configuration validation\n- [ ] Constructor params validated (not just defaulted) - see config-patterns.md\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":23,"source":24,"description":5},"unknown","community","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fsharp-edges",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":7,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill sharp-edges",{"tool":40,"command":41},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill sharp-edges",{"tool":43,"command":44},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill sharp-edges","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fsharp-edges\u002FSKILL.md",true,[],[49,56,63,70,77,84],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":18},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":18},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":18},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":7,"ownerLogin":8,"ownerAvatarUrl":9,"ownerAccountNo":10,"ownerDisplayName":11,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":18},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]