[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71AXKTC2T8PB2QMR3TV6XA0":3,"skill-same:01M71AXKTC2T8PB2QMR3TV6XA0":89},{"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":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M71AXKTC2T8PB2QMR3TV6XA0","iac-scan",null,"Infrastructure-as-Code security scan for changed deploy config — Dockerfiles,\ndocker-compose, Terraform, Kubernetes\u002FHelm, and CI\u002FCD workflows. Flags\nmisconfigurations and exposed secrets (root containers, open ingress, wildcard\nIAM, privileged pods, untrusted CI triggers). Static diff-scoped analysis (safe\nto auto-run); uses tfsec\u002Fcheckov\u002Fhadolint\u002Factionlint when present. Use when asked\nto \"scan infra\", \"IaC scan\", \"check the Dockerfile\u002Fterraform\u002Fk8s\", \"CI security\",\nor after changing deploy\u002Finfra config.","ariadoss\u002Fsuperskills","ariadoss","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F414341?v=4","01M71AC7383PT6JCRZSQJ4AVTM","Danilo Stern-Sapad","01M71AC73Y7NTBTJ9KQYNENRRE",12,"MIT","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fiac-scan\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],"scan","iac","iac scan","security review","iam","review","code","analysis","Bash","security scan","when","workflows","auto","files","open","infrastructure-as","dockerfile","ci","static","scope","2026-11-10 10:12:30",false,"---\nname: iac-scan\nversion: 1.0.0\ndescription: |\n  Infrastructure-as-Code security scan for changed deploy config — Dockerfiles,\n  docker-compose, Terraform, Kubernetes\u002FHelm, and CI\u002FCD workflows. Flags\n  misconfigurations and exposed secrets (root containers, open ingress, wildcard\n  IAM, privileged pods, untrusted CI triggers). Static diff-scoped analysis (safe\n  to auto-run); uses tfsec\u002Fcheckov\u002Fhadolint\u002Factionlint when present. Use when asked\n  to \"scan infra\", \"IaC scan\", \"check the Dockerfile\u002Fterraform\u002Fk8s\", \"CI security\",\n  or after changing deploy\u002Finfra config.\ntriggers:\n  - iac scan\n  - scan infra\n  - infrastructure scan\n  - check the dockerfile\n  - terraform security\n  - kubernetes security\n  - ci security review\nargument-hint: '\u003Coptional: paths\u002Fglobs to scope (defaults to changed infra files)>'\nallowed-tools:\n  - Bash\n  - Read\n  - Grep\n  - Glob\n  - Task\n  - WebFetch\n---\n\n# \u002Fiac-scan\n\nScan changed infrastructure\u002Fdeploy config for security misconfigurations and\nexposed secrets. **Static and read-only** — analyzes the files directly.\n\n**Auto-run safety envelope:** the auto-run path uses only **local static linters**\nthat need no network and no auth — `hadolint`, `tfsec`, `checkov` (offline\u002Flocal\npolicy only), `kube-score`, `actionlint`, `zizmor`. That's why it's safe to\nauto-run, unlike `\u002Fpentest` (an interactive check gated on an authorization\nconfirmation, whose opt-in clearwing modes are networked scanners that bill\ntheir own LLM provider — its default in-harness source hunt touches no network\nbut still waits for authorization). Anything that reaches the network — e.g. `trivy` pulling vulnerability\nDBs, or `checkov` fetching remote policies — is **opt-in \u002F recommend-only**, never\npart of the auto-run. If only networked tools are available, run the signature\nchecks instead and recommend the networked scan separately.\n\n## Hard rules\n\n- **Evidence-grounded:** file:line, the offending directive, the rule\u002FCWE, and the\n  concrete risk (\"container runs as root\", \"0.0.0.0\u002F0 on port 22\", \"secret baked\n  into image layer\").\n- **Severity by blast radius:** internet-exposed, privilege-escalating, or\n  secret-leaking misconfigs are CRITICAL\u002FHIGH; style\u002Fpinning nits are LOW.\n- **Smallest correct fix**, shown as a diff; do not apply it.\n- **Scope to the changed infra files.** Don't re-scan the whole tree.\n- **Prefer real scanners when present.** Local static linters (`hadolint`,\n  `tfsec`, `kube-score`, `actionlint`, `zizmor`, offline `checkov`) are part of\n  the auto-run path; networked scanners (`trivy` DB pulls, remote-policy `checkov`)\n  are recommend-only. Fall back to the signature checks below when none are\n  present — and always say which mode ran (which tools, or signature mode).\n\n## Trigger (what counts as infra\u002Fdeploy config)\n\n- Containers: `Dockerfile`, `*.dockerfile`, `docker-compose*.y*ml`, `.dockerignore`\n- Terraform: `*.tf`, `*.tfvars`\n- Kubernetes \u002F Helm: `*.y*ml` with `kind:` under `k8s\u002F`, `manifests\u002F`, `charts\u002F`,\n  `helm\u002F`, or `deploy\u002F`\n- CI\u002FCD: `.github\u002Fworkflows\u002F**`, `.gitlab-ci.yml`, `Jenkinsfile`, `*.circleci\u002F*`\n- Web\u002Fproxy\u002Fcloud: `nginx.conf`, `Caddyfile`, `*.tf` cloud resources, `serverless.yml`\n\nIf none of these changed, say so and stop.\n\n## What to check\n\n**Docker** — non-root `USER`; pinned base image (no `:latest`); no secrets in\n`ENV`\u002F`ARG`\u002Flayers; no `ADD http:\u002F\u002F…`; minimal surface; `HEALTHCHECK`; no\nunnecessary `EXPOSE`; `--no-install-recommends`\u002Fcleaned caches. *(hadolint)*\n\n**docker-compose** — no `privileged: true`; no `network_mode: host`; never bind\n`\u002Fvar\u002Frun\u002Fdocker.sock`; secrets via `secrets:` not `environment:`; pinned image tags.\n\n**Terraform** — no security-group\u002Ffirewall `0.0.0.0\u002F0` on sensitive ports\n(22\u002F3389\u002FDB); no public buckets\u002Fblobs; no IAM `Action: \"*\"` \u002F `Resource: \"*\"`;\nencryption at rest + in transit enabled; no hardcoded secrets\u002Fkeys; remote state\nwith locking; logging\u002Fversioning on. *(tfsec \u002F checkov)*\n\n**Kubernetes \u002F Helm** — `runAsNonRoot`, drop `privileged`\u002F`allowPrivilegeEscalation`;\nno `hostPath`\u002F`hostNetwork`\u002F`hostPID`; resource `limits`\u002F`requests` set;\n`readOnlyRootFilesystem`; no `default` ServiceAccount with broad RBAC \u002F `cluster-admin`;\npinned image digests; NetworkPolicy present; no secrets in plain env. *(kube-score \u002F kubesec)*\n\n**CI\u002FCD (GitHub Actions et al.)** — no `pull_request_target` running untrusted PR\ncode; least-privilege top-level `permissions:`; third-party actions pinned to a\n**full commit SHA** (not a moving tag); no script injection via unsanitized\n`${{ github.event.* }}` in `run:`; secrets never `echo`ed; no `persist-credentials`\nleft on when not needed. *(actionlint + zizmor)*\n\n**Web\u002Fproxy** — TLS enforced; security headers (HSTS, CSP, X-Content-Type-Options);\nno directory listing; no server tokens leaking versions.\n\n## Steps\n\n1. **Scope** — resolve changed infra files (or `$ARGUMENTS`). None → stop.\n2. **Tool pass** — for each file type, if the matching scanner is installed, run it\n   scoped to the changed files and capture findings verbatim. Note which tools ran.\n3. **Signature pass** — for file types with no installed scanner, Grep\u002FRead for the\n   patterns above. Mark these **Observed** (clear match) vs **Suspected**.\n4. **Secrets sweep** — across all changed infra files, flag high-entropy strings,\n   `AKIA…`, private keys, tokens, `password=`\u002F`secret=` literals. (Complements\n   `\u002Fdefense`'s app-code secret scan.)\n5. **Report** — group by severity; smallest fix per finding as a diff.\n\n## Report format\n\n```markdown\n# IaC scan — \u003Cscope> @ \u003Cdate>\n\nScanners run: hadolint ✓ \u002F tfsec ✗ (signature mode) \u002F actionlint ✓ …\n\n## CRITICAL \u002F HIGH\n- \u003Cfile:line> — \u003Cdirective> — \u003Crule\u002FCWE> — \u003Crisk> — \u003Cfix>\n\n## MEDIUM \u002F LOW\n- …\n\n## Secrets\n- \u003Cfile:line> — \u003Ckind> — rotate + move to a secret manager\n```\n\n## Anti-patterns (do not do)\n\n- Claiming a misconfig without quoting the directive and naming the risk.\n- Scanning the whole repo instead of the changed infra files.\n- Applying fixes or rewriting manifests — this scans and drafts; the user applies.\n- Treating a pinning\u002Fstyle nit as CRITICAL, or burying an open-to-the-world port.\n\n## Related commands\n\n- `\u002Fdefense` — app-code OWASP\u002Fsecrets sweep; `\u002Fiac-scan` is its infra counterpart.\n- `\u002Fpentest` — deeper security hunt (in-harness pipeline by default; network probing drives clearwing's MCP machinery — authorization-gated — and its hunt\u002FSARIF pipeline runs agent-driven on the session via the bundled bridge, with provider-driven runs billed and ask-first); recommend after `\u002Fiac-scan` finds HIGH\u002FCRITICAL\n  or when a live environment needs probing.\n- `\u002Fcso` — threat-model the deployment topology at design time (`\u002Fwrite-plan`).\n","# \u002Fiac-scan\n\nScan changed infrastructure\u002Fdeploy config for security misconfigurations and\nexposed secrets. **Static and read-only** — analyzes the files directly.\n\n**Auto-run safety envelope:** the auto-run path uses only **local static linters**\nthat need no network and no auth — `hadolint`, `tfsec`, `checkov` (offline\u002Flocal\npolicy only), `kube-score`, `actionlint`, `zizmor`. That's why it's safe to\nauto-run, unlike `\u002Fpentest` (an interactive check gated on an authorization\nconfirmation, whose opt-in clearwing modes are networked scanners that bill\ntheir own LLM provider — its default in-harness source hunt touches no network\nbut still waits for authorization). Anything that reaches the network — e.g. `trivy` pulling vulnerability\nDBs, or `checkov` fetching remote policies — is **opt-in \u002F recommend-only**, never\npart of the auto-run. If only networked tools are available, run the signature\nchecks instead and recommend the networked scan separately.\n\n## Hard rules\n\n- **Evidence-grounded:** file:line, the offending directive, the rule\u002FCWE, and the\n  concrete risk (\"container runs as root\", \"0.0.0.0\u002F0 on port 22\", \"secret baked\n  into image layer\").\n- **Severity by blast radius:** internet-exposed, privilege-escalating, or\n  secret-leaking misconfigs are CRITICAL\u002FHIGH; style\u002Fpinning nits are LOW.\n- **Smallest correct fix**, shown as a diff; do not apply it.\n- **Scope to the changed infra files.** Don't re-scan the whole tree.\n- **Prefer real scanners when present.** Local static linters (`hadolint`,\n  `tfsec`, `kube-score`, `actionlint`, `zizmor`, offline `checkov`) are part of\n  the auto-run path; networked scanners (`trivy` DB pulls, remote-policy `checkov`)\n  are recommend-only. Fall back to the signature checks below when none are\n  present — and always say which mode ran (which tools, or signature mode).\n\n## Trigger (what counts as infra\u002Fdeploy config)\n\n- Containers: `Dockerfile`, `*.dockerfile`, `docker-compose*.y*ml`, `.dockerignore`\n- Terraform: `*.tf`, `*.tfvars`\n- Kubernetes \u002F Helm: `*.y*ml` with `kind:` under `k8s\u002F`, `manifests\u002F`, `charts\u002F`,\n  `helm\u002F`, or `deploy\u002F`\n- CI\u002FCD: `.github\u002Fworkflows\u002F**`, `.gitlab-ci.yml`, `Jenkinsfile`, `*.circleci\u002F*`\n- Web\u002Fproxy\u002Fcloud: `nginx.conf`, `Caddyfile`, `*.tf` cloud resources, `serverless.yml`\n\nIf none of these changed, say so and stop.\n\n## What to check\n\n**Docker** — non-root `USER`; pinned base image (no `:latest`); no secrets in\n`ENV`\u002F`ARG`\u002Flayers; no `ADD http:\u002F\u002F…`; minimal surface; `HEALTHCHECK`; no\nunnecessary `EXPOSE`; `--no-install-recommends`\u002Fcleaned caches. *(hadolint)*\n\n**docker-compose** — no `privileged: true`; no `network_mode: host`; never bind\n`\u002Fvar\u002Frun\u002Fdocker.sock`; secrets via `secrets:` not `environment:`; pinned image tags.\n\n**Terraform** — no security-group\u002Ffirewall `0.0.0.0\u002F0` on sensitive ports\n(22\u002F3389\u002FDB); no public buckets\u002Fblobs; no IAM `Action: \"*\"` \u002F `Resource: \"*\"`;\nencryption at rest + in transit enabled; no hardcoded secrets\u002Fkeys; remote state\nwith locking; logging\u002Fversioning on. *(tfsec \u002F checkov)*\n\n**Kubernetes \u002F Helm** — `runAsNonRoot`, drop `privileged`\u002F`allowPrivilegeEscalation`;\nno `hostPath`\u002F`hostNetwork`\u002F`hostPID`; resource `limits`\u002F`requests` set;\n`readOnlyRootFilesystem`; no `default` ServiceAccount with broad RBAC \u002F `cluster-admin`;\npinned image digests; NetworkPolicy present; no secrets in plain env. *(kube-score \u002F kubesec)*\n\n**CI\u002FCD (GitHub Actions et al.)** — no `pull_request_target` running untrusted PR\ncode; least-privilege top-level `permissions:`; third-party actions pinned to a\n**full commit SHA** (not a moving tag); no script injection via unsanitized\n`${{ github.event.* }}` in `run:`; secrets never `echo`ed; no `persist-credentials`\nleft on when not needed. *(actionlint + zizmor)*\n\n**Web\u002Fproxy** — TLS enforced; security headers (HSTS, CSP, X-Content-Type-Options);\nno directory listing; no server tokens leaking versions.\n\n## Steps\n\n1. **Scope** — resolve changed infra files (or `$ARGUMENTS`). None → stop.\n2. **Tool pass** — for each file type, if the matching scanner is installed, run it\n   scoped to the changed files and capture findings verbatim. Note which tools ran.\n3. **Signature pass** — for file types with no installed scanner, Grep\u002FRead for the\n   patterns above. Mark these **Observed** (clear match) vs **Suspected**.\n4. **Secrets sweep** — across all changed infra files, flag high-entropy strings,\n   `AKIA…`, private keys, tokens, `password=`\u002F`secret=` literals. (Complements\n   `\u002Fdefense`'s app-code secret scan.)\n5. **Report** — group by severity; smallest fix per finding as a diff.\n\n## Report format\n\n```markdown\n# IaC scan — \u003Cscope> @ \u003Cdate>\n\nScanners run: hadolint ✓ \u002F tfsec ✗ (signature mode) \u002F actionlint ✓ …\n\n## CRITICAL \u002F HIGH\n- \u003Cfile:line> — \u003Cdirective> — \u003Crule\u002FCWE> — \u003Crisk> — \u003Cfix>\n\n## MEDIUM \u002F LOW\n- …\n\n## Secrets\n- \u003Cfile:line> — \u003Ckind> — rotate + move to a secret manager\n```\n\n## Anti-patterns (do not do)\n\n- Claiming a misconfig without quoting the directive and naming the risk.\n- Scanning the whole repo instead of the changed infra files.\n- Applying fixes or rewriting manifests — this scans and drafts; the user applies.\n- Treating a pinning\u002Fstyle nit as CRITICAL, or burying an open-to-the-world port.\n\n## Related commands\n\n- `\u002Fdefense` — app-code OWASP\u002Fsecrets sweep; `\u002Fiac-scan` is its infra counterpart.\n- `\u002Fpentest` — deeper security hunt (in-harness pipeline by default; network probing drives clearwing's MCP machinery — authorization-gated — and its hunt\u002FSARIF pipeline runs agent-driven on the session via the bundled bridge, with provider-driven runs billed and ask-first); recommend after `\u002Fiac-scan` finds HIGH\u002FCRITICAL\n  or when a live environment needs probing.\n- `\u002Fcso` — threat-model the deployment topology at design time (`\u002Fwrite-plan`).\n",{"name":5,"version":49,"triggers":50,"description":57,"allowed-tools":58,"argument-hint":64},"1.0.0",[26,51,52,53,54,55,56],"scan infra","infrastructure scan","check the dockerfile","terraform security","kubernetes security","ci security review","Infrastructure-as-Code security scan for changed deploy config — Dockerfiles,\ndocker-compose, Terraform, Kubernetes\u002FHelm, and CI\u002FCD workflows. Flags\nmisconfigurations and exposed secrets (root containers, open ingress, wildcard\nIAM, privileged pods, untrusted CI triggers). Static diff-scoped analysis (safe\nto auto-run); uses tfsec\u002Fcheckov\u002Fhadolint\u002Factionlint when present. Use when asked\nto \"scan infra\", \"IaC scan\", \"check the Dockerfile\u002Fterraform\u002Fk8s\", \"CI security\",\nor after changing deploy\u002Finfra config.\n",[32,59,60,61,62,63],"Read","Grep","Glob","Task","WebFetch","\u003Coptional: paths\u002Fglobs to scope (defaults to changed infra files)>","main","c7ec8d78e5dc37484c2cfe90ab04de163d97dd41","skills\u002Fiac-scan",0,"https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills","https:\u002F\u002Fhyperion360.com\u002Fblog\u002Fparallel-ai-agents-engineering-workflow\u002F","https:\u002F\u002Fgithub.com\u002Fariadoss","https:\u002F\u002Fdanilosapad.com\u002F","CEO & Founder of @Hyperion360","2026-11-13 04:11:07",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add ariadoss\u002Fsuperskills --skill iac-scan",{"tool":81,"command":82},"bunx","bunx skills add ariadoss\u002Fsuperskills --skill iac-scan",{"tool":84,"command":85},"pnpm","pnpm dlx skills add ariadoss\u002Fsuperskills --skill iac-scan","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fiac-scan\u002FSKILL.md",true,[],[90,115,137,156,185,201],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"publishedAt":44},"01M71AZE3MPF891RM354EMRYA1","youtube","Download YouTube video transcripts when user provides a YouTube URL or asks to download\u002Fget\u002Ffetch a transcript from YouTube. Also use when user wants to transcribe or get captions\u002Fsubtitles from a YouTube video.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[92,100,101,102,103,104,105,32,106,34,107,108,109,110,111,112,113,114],"user","download","transcribe","write","transcript","video transcripts","URL","Captions","get","fetch","Video","read","use","subtitles","transcripts",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":44},"01M71AZAYR85PW6BJGSQXS4BN2","write-plan","Use when you have a spec or requirements for a multi-step task, before touching code. Produces an engineering plan complete with TDD tasks, DRY\u002FSOLID\u002FYAGNI principles, a required Test Plan & Verification section, and a coverage target — then auto-runs \u002Fplan-eng-review as an independent double-check before execution.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-plan\u002FSKILL.md",[],[122,123,103,124,125,29,126,30,127,34,36,128,129,130,131,132,133,134,135,136],"write plan","plan","dry","verification","tasks","you","eng","coverage","complete","section","for","test plan","target","as","yagni",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":143,"publishedAt":44},"01M71AZ8NDDP5ZMGEE6FSC4FKR","worktrees","Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fworktrees\u002FSKILL.md",[],[139,144,145,146,112,147,148,149,150,151,152,125,153,34,154,155],"implementation","workspace","with","plans","feature","isolation","git","directory","work","git worktrees","selection","Safety",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":165,"publishedAt":44},"01M71AZ4ZQHTNWFRZVYHKQFP08","web-perf","Analyzes web performance using Chrome DevTools MCP. Measures Core Web Vitals (LCP, INP, CLS) and supplementary metrics (FCP, TBT, Speed Index), identifies render-blocking resources, network dependency chains, layout shifts, caching issues, and accessibility gaps. Use when asked to audit, profile, debug, or optimize page load performance, Lighthouse scores, or site speed. Biases towards retrieval from current documentation over pre-trained knowledge.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fweb-perf\u002FSKILL.md",[162],{"categoryNo":163,"categoryName":164,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[166,167,168,169,170,171,172,173,174,34,175,176,177,178,179,180,181,182,183,184],"web","perf","web perf","resources","MCP","layout","optimize","documentation","caching","qa","knowledge","devtools","issues","render","re","performance","chrome devtools","vitals","never",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":44},"01M71AZ2KZNWYEGKKRMJH8PYG2","verify","Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[187,130,192,193,152,125,194,195,34,196,112,197,198,199,200],"commands","about","claims","output","assertions","claim","prs","evidence","running",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":207,"publishedAt":44},"01M71AZ0ACCK7N1QMWQK1FV2HJ","validate-idea","Validate a business idea using the minimalist entrepreneur framework. Use when someone has a business idea and wants to test if it's worth pursuing before building anything.","https:\u002F\u002Fgithub.com\u002Fariadoss\u002Fsuperskills\u002Fblob\u002Fmain\u002Fskills\u002Fvalidate-idea\u002FSKILL.md",[],[208,209,210,211,212,213,214,34,215,112,216],"validate","idea","validate idea","framework","it","minimalist","test","business","before building"]