[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HMGAPJZKQSH9EFSPGAHF2":3,"skill-same:01M71HMGAPJZKQSH9EFSPGAHF2":88},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M71HMGAPJZKQSH9EFSPGAHF2","security-suite",null,"Composable binary security suite for static analysis, dynamic tracing, contract capture, baseline drift, and policy gating. Triggers: \"binary security\", \"reverse engineer binary\", \"black-box binary test\", \"behavioral trace\", \"baseline diff\", \"security suite\".","JSGforever\u002Fskillguard","JSGforever","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F85541948?v=4","01M71FQD3E132VMR5F4TAYX3YS","01M71FQD4DYW0XJ4XQ4YQH75Y9",2,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000037","律师与法务","PROFESSION","适用职业",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"suite","security","security suite","baseline","test","analysis","drift","gating","composable","black","contract","execution","triggers","engineer","policy","reverse engineer","static","for","diff","reverse","2026-11-10 10:12:30",false,"---\nname: security-suite\ndescription: 'Composable binary security suite for static analysis, dynamic tracing, contract capture, baseline drift, and policy gating. Triggers: \"binary security\", \"reverse engineer binary\", \"black-box binary test\", \"behavioral trace\", \"baseline diff\", \"security suite\".'\nskill_api_version: 1\nmetadata:\n  tier: execution\n  dependencies: []\n---\n\n# Security Suite\n\n> **Purpose:** Provide composable, repeatable security\u002Finternal-testing primitives for authorized binaries.\n\nThis skill separates concerns into primitives so security workflows stay testable and reusable.\n\n## Guardrails\n\n- Use only on binaries you own or are explicitly authorized to assess.\n- Do not use this workflow to bypass legal restrictions or extract third-party proprietary content without authorization.\n- Prefer behavioral assurance and policy gating over ad-hoc one-off reverse-engineering.\n\n## Primitive Model\n\n1. `collect-static` — file metadata, runtime heuristics, linked libraries, embedded archive signatures.\n2. `collect-dynamic` — sandboxed execution trace (processes, file changes, network endpoints).\n3. `collect-contract` — machine-readable behavior contract from help-surface probing.\n4. `compare-baseline` — current vs baseline contract drift (added\u002Fremoved commands, runtime change).\n5. `enforce-policy` — allowlist\u002Fdenylist gates and severity-based verdict.\n6. `run` — thin orchestrator that composes primitives and writes suite summary.\n\n## Quick Start\n\nSingle run (default dynamic command is `--help`):\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current\n```\n\nBaseline regression gate:\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current \\\n  --baseline-dir .tmp\u002Fsecurity-suite\u002Fao-baseline \\\n  --fail-on-removed\n```\n\nPolicy gate:\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current \\\n  --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json \\\n  --fail-on-policy-fail\n```\n\n## Recommended Workflow\n\n1. Capture baseline on known-good release.\n2. Run suite on candidate binary in CI.\n3. Compare against baseline and enforce policy.\n4. Block promotion on failing verdict.\n\n## Output Contract\n\nAll outputs are written under `--out-dir`:\n\n- `static\u002Fstatic-analysis.json`\n- `dynamic\u002Fdynamic-analysis.json`\n- `contract\u002Fcontract.json`\n- `compare\u002Fbaseline-diff.json` (when baseline supplied)\n- `policy\u002Fpolicy-verdict.json` (when policy supplied)\n- `suite-summary.json`\n\nThis output structure is intentionally machine-consumable for CI gates.\n\n## Policy Model\n\nUse `skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json` as a starting point.\n\nSupported checks:\n\n- `required_top_level_commands`\n- `deny_command_patterns`\n- `max_created_files`\n- `forbid_file_path_patterns`\n- `allow_network_endpoint_patterns`\n- `deny_network_endpoint_patterns`\n- `block_if_removed_commands`\n- `min_command_count`\n\n## Technique Coverage\n\nThis suite is designed for broad binary classes, not just CLI metadata:\n\n- static runtime\u002Flibrary fingerprinting\n- sandboxed behavior observation\n- command\u002Fcontract capture\n- drift classification\n- policy enforcement and CI verdicting\n\nIt is intentionally modular so you can add deeper primitives later (syscall tracing, SBOM attestation verification, fuzz harnesses) without rewriting the workflow.\n\n## Validation\n\nRun:\n\n```bash\nbash skills\u002Fsecurity-suite\u002Fscripts\u002Fvalidate.sh\n```\n\nSmoke test (recommended):\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite-smoke \\\n  --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json\n```\n\n## Examples\n\n### Scenario: Capture a Baseline and Gate a New Release\n\n**User says:** `\u002Fsecurity-suite run --binary $(command -v ao) --out-dir .tmp\u002Fsecurity-suite\u002Fao-v2.4`\n\n**What happens:**\n1. The suite runs static analysis (file metadata, linked libraries, embedded archive signatures), dynamic tracing (sandboxed `--help` execution observing processes, file changes, network endpoints), and contract capture against the `ao` binary.\n2. It writes `static\u002Fstatic-analysis.json`, `dynamic\u002Fdynamic-analysis.json`, `contract\u002Fcontract.json`, and `suite-summary.json` under the output directory.\n\n**Result:** A complete baseline snapshot is captured for `ao` v2.4, ready to be used as `--baseline-dir` for future release comparisons.\n\n### Scenario: CI Regression Gate With Baseline and Policy\n\n**User says:** `\u002Fsecurity-suite run --binary .\u002Fbin\u002Fao-candidate --out-dir .tmp\u002Fao-candidate --baseline-dir .tmp\u002Fsecurity-suite\u002Fao-v2.4 --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json --fail-on-removed --fail-on-policy-fail`\n\n**What happens:**\n1. The suite runs all three collection primitives on the candidate binary, then compares the resulting contract against the v2.4 baseline to produce `compare\u002Fbaseline-diff.json` with any added, removed, or changed commands.\n2. It evaluates the policy file checks (required commands, denied patterns, network allowlists, file limits) and writes `policy\u002Fpolicy-verdict.json` with a pass\u002Ffail verdict.\n\n**Result:** The suite exits non-zero if any commands were removed or a policy check failed, blocking the candidate from promotion in the CI pipeline.\n\n## Troubleshooting\n\n| Problem | Cause | Solution |\n|---------|-------|----------|\n| Suite exits non-zero with no clear finding | `--fail-on-removed` or `--fail-on-policy-fail` triggered on a legitimate change | Review `compare\u002Fbaseline-diff.json` and `policy\u002Fpolicy-verdict.json` to identify the specific delta, then update the baseline or policy file accordingly. |\n| `dynamic\u002Fdynamic-analysis.json` is empty or minimal | Binary requires arguments beyond `--help`, or sandbox blocked execution | Supply a custom dynamic command if supported, or verify the binary runs in the sandboxed environment (check permissions, missing shared libraries). |\n| `contract\u002Fcontract.json` shows zero commands | The binary does not expose a `--help` surface or uses a non-standard help flag | Verify the binary supports `--help`; for binaries with unusual help interfaces, run `collect-contract` separately with the correct invocation. |\n| Policy verdict fails on `deny_command_patterns` | A new subcommand matches a deny regex in the policy file | Either rename the subcommand or update `deny_command_patterns` in your policy JSON to exclude the legitimate pattern. |\n| `baseline-diff.json` not generated | `--baseline-dir` was not provided or points to a missing directory | Ensure the baseline directory exists and contains a valid `contract\u002Fcontract.json` from a prior run. |\n","# Security Suite\n\n> **Purpose:** Provide composable, repeatable security\u002Finternal-testing primitives for authorized binaries.\n\nThis skill separates concerns into primitives so security workflows stay testable and reusable.\n\n## Guardrails\n\n- Use only on binaries you own or are explicitly authorized to assess.\n- Do not use this workflow to bypass legal restrictions or extract third-party proprietary content without authorization.\n- Prefer behavioral assurance and policy gating over ad-hoc one-off reverse-engineering.\n\n## Primitive Model\n\n1. `collect-static` — file metadata, runtime heuristics, linked libraries, embedded archive signatures.\n2. `collect-dynamic` — sandboxed execution trace (processes, file changes, network endpoints).\n3. `collect-contract` — machine-readable behavior contract from help-surface probing.\n4. `compare-baseline` — current vs baseline contract drift (added\u002Fremoved commands, runtime change).\n5. `enforce-policy` — allowlist\u002Fdenylist gates and severity-based verdict.\n6. `run` — thin orchestrator that composes primitives and writes suite summary.\n\n## Quick Start\n\nSingle run (default dynamic command is `--help`):\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current\n```\n\nBaseline regression gate:\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current \\\n  --baseline-dir .tmp\u002Fsecurity-suite\u002Fao-baseline \\\n  --fail-on-removed\n```\n\nPolicy gate:\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite\u002Fao-current \\\n  --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json \\\n  --fail-on-policy-fail\n```\n\n## Recommended Workflow\n\n1. Capture baseline on known-good release.\n2. Run suite on candidate binary in CI.\n3. Compare against baseline and enforce policy.\n4. Block promotion on failing verdict.\n\n## Output Contract\n\nAll outputs are written under `--out-dir`:\n\n- `static\u002Fstatic-analysis.json`\n- `dynamic\u002Fdynamic-analysis.json`\n- `contract\u002Fcontract.json`\n- `compare\u002Fbaseline-diff.json` (when baseline supplied)\n- `policy\u002Fpolicy-verdict.json` (when policy supplied)\n- `suite-summary.json`\n\nThis output structure is intentionally machine-consumable for CI gates.\n\n## Policy Model\n\nUse `skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json` as a starting point.\n\nSupported checks:\n\n- `required_top_level_commands`\n- `deny_command_patterns`\n- `max_created_files`\n- `forbid_file_path_patterns`\n- `allow_network_endpoint_patterns`\n- `deny_network_endpoint_patterns`\n- `block_if_removed_commands`\n- `min_command_count`\n\n## Technique Coverage\n\nThis suite is designed for broad binary classes, not just CLI metadata:\n\n- static runtime\u002Flibrary fingerprinting\n- sandboxed behavior observation\n- command\u002Fcontract capture\n- drift classification\n- policy enforcement and CI verdicting\n\nIt is intentionally modular so you can add deeper primitives later (syscall tracing, SBOM attestation verification, fuzz harnesses) without rewriting the workflow.\n\n## Validation\n\nRun:\n\n```bash\nbash skills\u002Fsecurity-suite\u002Fscripts\u002Fvalidate.sh\n```\n\nSmoke test (recommended):\n\n```bash\npython3 skills\u002Fsecurity-suite\u002Fscripts\u002Fsecurity_suite.py run \\\n  --binary \"$(command -v ao)\" \\\n  --out-dir .tmp\u002Fsecurity-suite-smoke \\\n  --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json\n```\n\n## Examples\n\n### Scenario: Capture a Baseline and Gate a New Release\n\n**User says:** `\u002Fsecurity-suite run --binary $(command -v ao) --out-dir .tmp\u002Fsecurity-suite\u002Fao-v2.4`\n\n**What happens:**\n1. The suite runs static analysis (file metadata, linked libraries, embedded archive signatures), dynamic tracing (sandboxed `--help` execution observing processes, file changes, network endpoints), and contract capture against the `ao` binary.\n2. It writes `static\u002Fstatic-analysis.json`, `dynamic\u002Fdynamic-analysis.json`, `contract\u002Fcontract.json`, and `suite-summary.json` under the output directory.\n\n**Result:** A complete baseline snapshot is captured for `ao` v2.4, ready to be used as `--baseline-dir` for future release comparisons.\n\n### Scenario: CI Regression Gate With Baseline and Policy\n\n**User says:** `\u002Fsecurity-suite run --binary .\u002Fbin\u002Fao-candidate --out-dir .tmp\u002Fao-candidate --baseline-dir .tmp\u002Fsecurity-suite\u002Fao-v2.4 --policy-file skills\u002Fsecurity-suite\u002Freferences\u002Fpolicy-example.json --fail-on-removed --fail-on-policy-fail`\n\n**What happens:**\n1. The suite runs all three collection primitives on the candidate binary, then compares the resulting contract against the v2.4 baseline to produce `compare\u002Fbaseline-diff.json` with any added, removed, or changed commands.\n2. It evaluates the policy file checks (required commands, denied patterns, network allowlists, file limits) and writes `policy\u002Fpolicy-verdict.json` with a pass\u002Ffail verdict.\n\n**Result:** The suite exits non-zero if any commands were removed or a policy check failed, blocking the candidate from promotion in the CI pipeline.\n\n## Troubleshooting\n\n| Problem | Cause | Solution |\n|---------|-------|----------|\n| Suite exits non-zero with no clear finding | `--fail-on-removed` or `--fail-on-policy-fail` triggered on a legitimate change | Review `compare\u002Fbaseline-diff.json` and `policy\u002Fpolicy-verdict.json` to identify the specific delta, then update the baseline or policy file accordingly. |\n| `dynamic\u002Fdynamic-analysis.json` is empty or minimal | Binary requires arguments beyond `--help`, or sandbox blocked execution | Supply a custom dynamic command if supported, or verify the binary runs in the sandboxed environment (check permissions, missing shared libraries). |\n| `contract\u002Fcontract.json` shows zero commands | The binary does not expose a `--help` surface or uses a non-standard help flag | Verify the binary supports `--help`; for binaries with unusual help interfaces, run `collect-contract` separately with the correct invocation. |\n| Policy verdict fails on `deny_command_patterns` | A new subcommand matches a deny regex in the policy file | Either rename the subcommand or update `deny_command_patterns` in your policy JSON to exclude the legitimate pattern. |\n| `baseline-diff.json` not generated | `--baseline-dir` was not provided or points to a missing directory | Ensure the baseline directory exists and contains a valid `contract\u002Fcontract.json` from a prior run. |\n",{"name":5,"metadata":48,"description":7,"skill_api_version":50},{"tier":34,"dependencies":49},[],1,"main","f2ec4b3b9133d34eeaf9b38e4b0a97e8e5705a7f","benchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite",0,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard","https:\u002F\u002Fgithub.com\u002FJSGforever","2026-08-29 18:27:56",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add JSGforever\u002Fskillguard --skill security-suite",{"tool":64,"command":65},"bunx","bunx skills add JSGforever\u002Fskillguard --skill security-suite",{"tool":67,"command":68},"pnpm","pnpm dlx skills add JSGforever\u002Fskillguard --skill security-suite","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite\u002FSKILL.md",true,[72,78,84],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fpolicy-example.json","REFERENCE","参考文档",534,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite\u002Freferences\u002Fpolicy-example.json",{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fsecurity_suite.py","SCRIPT","脚本",31968,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite\u002Fscripts\u002Fsecurity_suite.py",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fvalidate.sh",960,"https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__boshu2--security-suite\u002Fscripts\u002Fvalidate.sh",[89,121,135,162,184,205],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":100,"publishedAt":43},"01M71HY2SNXBA9Q00WZDTZQ31Z","skillguard-codex-scanner","Hybrid deterministic+LLM agent-skill security scanner. Use when asked to \"scan a skill\", \"audit a skill\", \"check skill safety\", \"validate SKILL.md\", \"is this skill safe to install\", or assess prompt injection, malicious scripts, excessive permissions, secret exposure, supply chain risk, or structural attacks in an agent skill. Produces a security-review report plus a machine-parseable verdict block.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fsrc\u002Fskillguard\u002Fstatic_scanner\u002Fskillguard-codex-scanner\u002FSKILL.md",[95],{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120],"scanner","skillguard codex scanner","skillguard","codex","chain","skill security","security-review","review report","structural","secret","prompt injection","security scanner","when","review","malicious","permissions","exposure","audit","scripts","safe",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":125,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":131,"publishedAt":43},"01M71HY0SPKTT3S27BC2HPAC5M","data-exfiltrator","Analyzes data files","MIT","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Fsmoke-one-skill\u002Fasset1__cisco-ai-defense--data-exfiltrator\u002FSKILL.md",[128],{"categoryNo":129,"categoryName":130,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000033","数据分析师",[132,133,134],"data","data exfiltrator","files",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":141,"publishedAt":43},"01M71HXVS9EMN44BGDW215FZ72","real-time-collaboration-engine","Build real-time collaborative editing with WebSockets, OT\u002FCRDT conflict resolution, and presence awareness. Implements cursor tracking, optimistic updates, and offline sync. Use for collaborative editors, whiteboards, video editing. Activate on \"real-time collaboration\", \"WebSocket sync\", \"multiplayer editing\", \"CRDT\", \"presence awareness\". NOT for simple chat, request-response APIs, or single-user apps.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--real-time-collaboration-engine\u002FSKILL.md",[],[142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161],"time","real time collaboration engine","real time collaboration","collaboration","engine","real time","Video","reliability","video editing","performance","conflict resolution","presence","access","apps","updates","Bash","activate","optimizer","react","streaming",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":43},"01M71HXP6CTY4KFN0QVMMN0V7J","react-performance-optimizer","Optimize React apps for 60fps performance. Implements memoization, virtualization, code splitting, bundle optimization. Use for slow renders, large lists, bundle bloat. Activate on \"React performance\", \"slow render\", \"useMemo\", \"bundle size\", \"virtualization\". NOT for backend optimization, non-React frameworks, or premature optimization.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--react-performance-optimizer\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000009","前端开发",[151,172,159,160,173,174,175,176,177,178,142,179,180,155,157,181,158,161,182,183],"react performance optimizer","react performance","performance optimizer","app","nextjs","expert","re","render","2025","code","router","strategies",{"skillNo":185,"name":186,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":191,"publishedAt":43},"01M71HXH7QXSQB4QTDZ7SP7YXQ","llm-streaming-response-handler","Build production LLM streaming UIs with Server-Sent Events, real-time token display, cancellation, error recovery. Handles OpenAI\u002FAnthropic\u002FClaude streaming APIs. Use for chatbots, AI assistants, real-time text generation. Activate on \"LLM streaming\", \"SSE\", \"token stream\", \"chat UI\", \"real-time AI\". NOT for batch processing, non-streaming APIs, or WebSocket bidirectional chat.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--llm-streaming-response-handler\u002FSKILL.md",[190],{"categoryNo":169,"categoryName":170,"taxonomyType":98,"taxonomyTypeDesc":99},[192,161,193,194,195,196,151,142,197,198,199,157,158,159,200,160,201,202,203,204],"llm streaming response handler","handler","error","processing","retry","chat ui","error recovery","critical","batch","display","text","server","read",{"skillNo":206,"name":207,"nameZh":6,"description":208,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":209,"categories":210,"keywords":218,"publishedAt":43},"01M71HXCB0E1YRKYW1Y8T0Y106","github-actions-pipeline-builder","Build production CI\u002FCD pipelines with GitHub Actions. Implements matrix builds, caching, deployments, testing, security scanning. Use for automated testing, deployments, release workflows. Activate on \"GitHub Actions\", \"CI\u002FCD\", \"workflow\", \"deployment pipeline\", \"automated testing\". NOT for Jenkins\u002FCircleCI, manual deployments, or non-GitHub repositories.","https:\u002F\u002Fgithub.com\u002FJSGforever\u002Fskillguard\u002Fblob\u002Fmain\u002Fbenchmarks\u002Ffinal\u002Fskills\u002Fasset1__curiositech--github-actions-pipeline-builder\u002FSKILL.md",[211,214,217],{"categoryNo":212,"categoryName":213,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":215,"categoryName":216,"taxonomyType":98,"taxonomyTypeDesc":99},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":96,"categoryName":97,"taxonomyType":98,"taxonomyTypeDesc":99},[219,220,221,222,223,224,225,149,177,226,227,228,158,183,229,204,230,231,232,233],"github actions pipeline builder","actions","github actions","pipeline builder","github","builder","pipeline","testing","ci","workflows","run","release","write","edit","git"]