[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77S9RGCNSVVB37CB5VM68SP":3,"skill-same:01M77S9RGCNSVVB37CB5VM68SP":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M77S9RGCNSVVB37CB5VM68SP","github-actions-hardening",null,"Security hardening reviewer for GitHub Actions workflow files (.github\u002Fworkflows\u002F*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like \"is this workflow safe?\", \"review my CI for security issues\", \"why is pull_request_target dangerous here?\", \"pin my actions\", or \"lock down GITHUB_TOKEN permissions\". Covers script injection via ${{ }} interpolation, pull_request_target \u002F workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV\u002FGITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.","Reihantt6\u002Fsns-myagent","Reihantt6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F219822095?v=4","01M77KK94PV8B7C2D9XWXNS8DJ","Mohamad Reihan tegar prasetya","01M77KK958QFMTHYXGXFV7KZ79",2,"MIT","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\ndescription: \"Security hardening reviewer for GitHub Actions workflow files (.github\u002Fworkflows\u002F*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like \\\"is this workflow safe?\\\", \\\"review my CI for security issues\\\", \\\"why is pull_request_target dangerous here?\\\", \\\"pin my actions\\\", or \\\"lock down GITHUB_TOKEN permissions\\\". Covers script injection via ${{ }} interpolation, pull_request_target \u002F workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV\u002FGITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.\"\n---\n# GitHub Actions Hardening\n\nA focused security reviewer for GitHub Actions workflows. It reasons about the *Actions-specific*\nthreat model — where trust boundaries live in trigger types, token scopes, and string\ninterpolation — rather than the application-code vulnerabilities a general security scanner looks\nfor. Most workflow risks are invisible to language linters because the dangerous code is the YAML\nitself and the way GitHub expands `${{ }}` expressions into a shell before your script runs.\n\n## When to Use This Skill\n\nUse this skill when the request involves:\n\n* Reviewing, auditing, or hardening any file under `.github\u002Fworkflows\u002F`\n* Authoring a new workflow and wanting it secure by default\n* A workflow that uses `pull_request_target`, `workflow_run`, or `issue_comment` triggers\n* Questions about `GITHUB_TOKEN` permissions or the `permissions:` key\n* Pinning actions to commit SHAs vs tags vs branches\n* Handling untrusted input (issue titles, PR bodies, branch names, commit messages) in `run:` steps\n* OIDC \u002F cloud authentication from Actions, or secret handling in CI\n* Self-hosted runners on public repositories\n* Any request like \"is this workflow safe?\", \"secure my CI\", or \"review this GitHub Action\"\n\n## The Core Insight\n\nIn a workflow, **`${{ \u003Cexpr> }}` is expanded by the runner into the script *before* the shell\nexecutes it.** So a step like:\n\n```yaml\n- run: echo \"Title: ${{ github.event.issue.title }}\"\n```\n\nis not passing a variable — it is *pasting attacker-controlled text directly into your shell\ncommand*. An issue titled `\"; \u003Cattacker-command> #` is concatenated into the script and executed.\nThis single mechanism is the most common real-world Actions vulnerability, and models routinely\ngenerate it. Treat every\n`${{ }}` that contains data an outside contributor can influence as a code-injection sink.\n\n## Execution Workflow\n\nFollow these steps **in order** for every workflow reviewed.\n\n### Step 1 — Map the Triggers and Trust Level\n\nRead every `on:` trigger and classify the workflow's privilege:\n\n* `push`, `pull_request` (from same repo) → runs with the contributor's own trust\n* `pull_request` from a **fork** → runs with a **read-only** token, **no secrets** (safe by design)\n* `pull_request_target`, `workflow_run`, `issue_comment`, `issues` → run in the context of the\n  **base repository** with a **read\u002Fwrite token and full access to secrets**, but can be\n  **triggered by outside contributors**. These are the dangerous triggers.\n\nRead `references\u002Ftriggers-and-privilege.md` for the full trust matrix.\n\n### Step 2 — Hunt for Script Injection\n\nFor every `run:` block, every `script:` in `actions\u002Fgithub-script`, and every input to a custom\naction, list the `${{ }}` expressions and check whether any resolve to attacker-controllable data.\nHigh-risk contexts include:\n\n* `github.event.issue.title`, `github.event.issue.body`\n* `github.event.pull_request.title`, `github.event.pull_request.body`, `.head.ref`, `.head.label`\n* `github.event.comment.body`, `github.event.review.body`\n* `github.event.pages.*.page_name`, `github.event.commits.*.message`, `github.event.head_commit.*`\n* `github.head_ref` and any `github.event.*` field a fork author can set\n\nRead `references\u002Finjection.md` for the complete sink list and the safe-pattern fixes.\n\n### Step 3 — Check Privileged Triggers Don't Execute Untrusted Code\n\nIf a `pull_request_target` or `workflow_run` workflow checks out PR\u002Ffork code\n(`ref: ${{ github.event.pull_request.head.sha }}`) **and then runs it** (build, test, install\nscripts, `npm install` with lifecycle scripts, etc.), that is remote code execution against a\nprivileged token. Flag it as CRITICAL. The safe pattern is to split into two workflows: an\nunprivileged `pull_request` workflow that runs the untrusted code, and a privileged\n`workflow_run` workflow that only consumes its results.\n\n### Step 4 — Audit `permissions:`\n\n* If there is **no** `permissions:` block, the workflow inherits the repository default, which may\n  be read\u002Fwrite to everything. Flag it.\n* Recommend a top-level `permissions: {}` (deny-all) or `contents: read`, then grant the minimum\n  per job (e.g. `pull-requests: write` only on the job that comments).\n* Flag any `permissions: write-all` or broad `write` scopes that the steps don't actually need.\n\nRead `references\u002Fpermissions-and-tokens.md` for the per-scope guidance and OIDC setup.\n\n### Step 5 — Audit Action References (Supply Chain)\n\nFor every `uses:`:\n\n* **Third-party actions** (not `actions\u002F*` or `github\u002F*`) MUST be pinned to a full 40-character\n  commit SHA, not a tag or branch. Tags and branches are mutable; a compromised upstream action\n  can rewrite `v1` to malicious code that runs with your token and secrets.\n* First-party `actions\u002F*` are lower risk but SHA-pinning is still the hardened recommendation.\n* Flag `@main`, `@master`, or any branch reference as HIGH — that is \"latest\" and can change under\n  you at any time.\n* Note the human-readable version in a trailing comment: `uses: foo\u002Fbar@\u003Csha> # v2.1.0`.\n\nRead `references\u002Fsupply-chain.md` for pinning, Dependabot for actions, and artifact\u002Fcache risks.\n\n### Step 6 — Check Secret and Output Handling\n\n* No secrets echoed, printed, or written to logs; no `set -x` \u002F `bash -x` in steps that touch\n  secrets.\n* Secrets must not be passed to steps that run untrusted code or to untrusted third-party actions.\n* Untrusted multiline data written to `$GITHUB_ENV` or `$GITHUB_OUTPUT` can inject environment\n  variables or step outputs — use the random-delimiter heredoc form and never write raw user input.\n* `actions\u002Fcheckout` leaves a token on disk by default; set `persist-credentials: false` when the\n  job later runs untrusted code.\n\n### Step 7 — Produce the Report\n\nOutput findings using the format in `references\u002Freport-format.md`: a severity summary table first,\nthen grouped findings with file, the exact offending YAML, the risk in plain English, and a\nconcrete before\u002Fafter fix. Never auto-apply changes — present them for review.\n\n## Severity Guide\n\n| Severity | Meaning | Example |\n| --- | --- | --- |\n| 🔴 CRITICAL | Token\u002Fsecret theft or RCE reachable by an outside contributor | `pull_request_target` checking out and running fork code; `${{ github.event.* }}` in a `run:` on a privileged trigger |\n| 🟠 HIGH | Exploitable supply-chain or scope problem | Third-party action on a mutable tag\u002Fbranch; `write-all` permissions; injection sink on `issue_comment` |\n| 🟡 MEDIUM | Risk under conditions or chaining | Missing `permissions:` block; secret reachable by a non-fork PR author |\n| 🔵 LOW | Hardening gap, low direct risk | First-party action not SHA-pinned; `persist-credentials` left default on a non-privileged job |\n| ⚪ INFO | Observation, not a vulnerability | Version comment missing next to a pinned SHA |\n\n## Output Rules\n\n* **Always** show a findings summary table (counts by severity) first.\n* **Group by issue type**, not by file.\n* **Be exact** — quote the offending line and give the line location.\n* **Always** pair every CRITICAL\u002FHIGH with a concrete corrected YAML snippet.\n* **Never** claim a fork `pull_request` is dangerous just because it runs untrusted code — it has\n  no secrets and a read-only token. Reserve CRITICAL for the privileged triggers.\n* If the workflow is already hardened, say so and list what was checked.\n\n## Reference Files\n\nLoad these as needed:\n\n* `references\u002Ftriggers-and-privilege.md` — Trust matrix for every trigger, why `pull_request_target`\n  and `workflow_run` are privileged, and the two-workflow safe pattern.\n  + Search patterns: `pull_request_target`, `workflow_run`, `issue_comment`, `fork`, `secrets`, `read-only token`, `trust boundary`\n* `references\u002Finjection.md` — Full list of attacker-controllable `${{ }}` contexts and the\n  `env:`-variable safe pattern for each sink (`run`, `github-script`, action inputs).\n  + Search patterns: `script injection`, `github.event`, `head_ref`, `issue title`, `env`, `intermediate variable`, `actions\u002Fgithub-script`\n* `references\u002Fpermissions-and-tokens.md` — `GITHUB_TOKEN` scopes, least-privilege `permissions:`\n  recipes per job type, and OIDC for cloud auth instead of long-lived secrets.\n  + Search patterns: `permissions`, `GITHUB_TOKEN`, `write-all`, `contents: read`, `id-token`, `OIDC`, `least privilege`\n* `references\u002Fsupply-chain.md` — SHA-pinning third-party actions, Dependabot for `github-actions`,\n  artifact and cache poisoning across `workflow_run`, and self-hosted runner exposure.\n  + Search patterns: `SHA pin`, `uses`, `mutable tag`, `Dependabot`, `download-artifact`, `cache`, `self-hosted runner`\n* `references\u002Freport-format.md` — Output template: summary table, finding cards, and before\u002Fafter\n  remediation blocks.\n  + Search patterns: `report`, `format`, `finding`, `summary`, `remediation`, `before`, `after`\n","# GitHub Actions Hardening\n\nA focused security reviewer for GitHub Actions workflows. It reasons about the *Actions-specific*\nthreat model — where trust boundaries live in trigger types, token scopes, and string\ninterpolation — rather than the application-code vulnerabilities a general security scanner looks\nfor. Most workflow risks are invisible to language linters because the dangerous code is the YAML\nitself and the way GitHub expands `${{ }}` expressions into a shell before your script runs.\n\n## When to Use This Skill\n\nUse this skill when the request involves:\n\n* Reviewing, auditing, or hardening any file under `.github\u002Fworkflows\u002F`\n* Authoring a new workflow and wanting it secure by default\n* A workflow that uses `pull_request_target`, `workflow_run`, or `issue_comment` triggers\n* Questions about `GITHUB_TOKEN` permissions or the `permissions:` key\n* Pinning actions to commit SHAs vs tags vs branches\n* Handling untrusted input (issue titles, PR bodies, branch names, commit messages) in `run:` steps\n* OIDC \u002F cloud authentication from Actions, or secret handling in CI\n* Self-hosted runners on public repositories\n* Any request like \"is this workflow safe?\", \"secure my CI\", or \"review this GitHub Action\"\n\n## The Core Insight\n\nIn a workflow, **`${{ \u003Cexpr> }}` is expanded by the runner into the script *before* the shell\nexecutes it.** So a step like:\n\n```yaml\n- run: echo \"Title: ${{ github.event.issue.title }}\"\n```\n\nis not passing a variable — it is *pasting attacker-controlled text directly into your shell\ncommand*. An issue titled `\"; \u003Cattacker-command> #` is concatenated into the script and executed.\nThis single mechanism is the most common real-world Actions vulnerability, and models routinely\ngenerate it. Treat every\n`${{ }}` that contains data an outside contributor can influence as a code-injection sink.\n\n## Execution Workflow\n\nFollow these steps **in order** for every workflow reviewed.\n\n### Step 1 — Map the Triggers and Trust Level\n\nRead every `on:` trigger and classify the workflow's privilege:\n\n* `push`, `pull_request` (from same repo) → runs with the contributor's own trust\n* `pull_request` from a **fork** → runs with a **read-only** token, **no secrets** (safe by design)\n* `pull_request_target`, `workflow_run`, `issue_comment`, `issues` → run in the context of the\n  **base repository** with a **read\u002Fwrite token and full access to secrets**, but can be\n  **triggered by outside contributors**. These are the dangerous triggers.\n\nRead `references\u002Ftriggers-and-privilege.md` for the full trust matrix.\n\n### Step 2 — Hunt for Script Injection\n\nFor every `run:` block, every `script:` in `actions\u002Fgithub-script`, and every input to a custom\naction, list the `${{ }}` expressions and check whether any resolve to attacker-controllable data.\nHigh-risk contexts include:\n\n* `github.event.issue.title`, `github.event.issue.body`\n* `github.event.pull_request.title`, `github.event.pull_request.body`, `.head.ref`, `.head.label`\n* `github.event.comment.body`, `github.event.review.body`\n* `github.event.pages.*.page_name`, `github.event.commits.*.message`, `github.event.head_commit.*`\n* `github.head_ref` and any `github.event.*` field a fork author can set\n\nRead `references\u002Finjection.md` for the complete sink list and the safe-pattern fixes.\n\n### Step 3 — Check Privileged Triggers Don't Execute Untrusted Code\n\nIf a `pull_request_target` or `workflow_run` workflow checks out PR\u002Ffork code\n(`ref: ${{ github.event.pull_request.head.sha }}`) **and then runs it** (build, test, install\nscripts, `npm install` with lifecycle scripts, etc.), that is remote code execution against a\nprivileged token. Flag it as CRITICAL. The safe pattern is to split into two workflows: an\nunprivileged `pull_request` workflow that runs the untrusted code, and a privileged\n`workflow_run` workflow that only consumes its results.\n\n### Step 4 — Audit `permissions:`\n\n* If there is **no** `permissions:` block, the workflow inherits the repository default, which may\n  be read\u002Fwrite to everything. Flag it.\n* Recommend a top-level `permissions: {}` (deny-all) or `contents: read`, then grant the minimum\n  per job (e.g. `pull-requests: write` only on the job that comments).\n* Flag any `permissions: write-all` or broad `write` scopes that the steps don't actually need.\n\nRead `references\u002Fpermissions-and-tokens.md` for the per-scope guidance and OIDC setup.\n\n### Step 5 — Audit Action References (Supply Chain)\n\nFor every `uses:`:\n\n* **Third-party actions** (not `actions\u002F*` or `github\u002F*`) MUST be pinned to a full 40-character\n  commit SHA, not a tag or branch. Tags and branches are mutable; a compromised upstream action\n  can rewrite `v1` to malicious code that runs with your token and secrets.\n* First-party `actions\u002F*` are lower risk but SHA-pinning is still the hardened recommendation.\n* Flag `@main`, `@master`, or any branch reference as HIGH — that is \"latest\" and can change under\n  you at any time.\n* Note the human-readable version in a trailing comment: `uses: foo\u002Fbar@\u003Csha> # v2.1.0`.\n\nRead `references\u002Fsupply-chain.md` for pinning, Dependabot for actions, and artifact\u002Fcache risks.\n\n### Step 6 — Check Secret and Output Handling\n\n* No secrets echoed, printed, or written to logs; no `set -x` \u002F `bash -x` in steps that touch\n  secrets.\n* Secrets must not be passed to steps that run untrusted code or to untrusted third-party actions.\n* Untrusted multiline data written to `$GITHUB_ENV` or `$GITHUB_OUTPUT` can inject environment\n  variables or step outputs — use the random-delimiter heredoc form and never write raw user input.\n* `actions\u002Fcheckout` leaves a token on disk by default; set `persist-credentials: false` when the\n  job later runs untrusted code.\n\n### Step 7 — Produce the Report\n\nOutput findings using the format in `references\u002Freport-format.md`: a severity summary table first,\nthen grouped findings with file, the exact offending YAML, the risk in plain English, and a\nconcrete before\u002Fafter fix. Never auto-apply changes — present them for review.\n\n## Severity Guide\n\n| Severity | Meaning | Example |\n| --- | --- | --- |\n| 🔴 CRITICAL | Token\u002Fsecret theft or RCE reachable by an outside contributor | `pull_request_target` checking out and running fork code; `${{ github.event.* }}` in a `run:` on a privileged trigger |\n| 🟠 HIGH | Exploitable supply-chain or scope problem | Third-party action on a mutable tag\u002Fbranch; `write-all` permissions; injection sink on `issue_comment` |\n| 🟡 MEDIUM | Risk under conditions or chaining | Missing `permissions:` block; secret reachable by a non-fork PR author |\n| 🔵 LOW | Hardening gap, low direct risk | First-party action not SHA-pinned; `persist-credentials` left default on a non-privileged job |\n| ⚪ INFO | Observation, not a vulnerability | Version comment missing next to a pinned SHA |\n\n## Output Rules\n\n* **Always** show a findings summary table (counts by severity) first.\n* **Group by issue type**, not by file.\n* **Be exact** — quote the offending line and give the line location.\n* **Always** pair every CRITICAL\u002FHIGH with a concrete corrected YAML snippet.\n* **Never** claim a fork `pull_request` is dangerous just because it runs untrusted code — it has\n  no secrets and a read-only token. Reserve CRITICAL for the privileged triggers.\n* If the workflow is already hardened, say so and list what was checked.\n\n## Reference Files\n\nLoad these as needed:\n\n* `references\u002Ftriggers-and-privilege.md` — Trust matrix for every trigger, why `pull_request_target`\n  and `workflow_run` are privileged, and the two-workflow safe pattern.\n  + Search patterns: `pull_request_target`, `workflow_run`, `issue_comment`, `fork`, `secrets`, `read-only token`, `trust boundary`\n* `references\u002Finjection.md` — Full list of attacker-controllable `${{ }}` contexts and the\n  `env:`-variable safe pattern for each sink (`run`, `github-script`, action inputs).\n  + Search patterns: `script injection`, `github.event`, `head_ref`, `issue title`, `env`, `intermediate variable`, `actions\u002Fgithub-script`\n* `references\u002Fpermissions-and-tokens.md` — `GITHUB_TOKEN` scopes, least-privilege `permissions:`\n  recipes per job type, and OIDC for cloud auth instead of long-lived secrets.\n  + Search patterns: `permissions`, `GITHUB_TOKEN`, `write-all`, `contents: read`, `id-token`, `OIDC`, `least privilege`\n* `references\u002Fsupply-chain.md` — SHA-pinning third-party actions, Dependabot for `github-actions`,\n  artifact and cache poisoning across `workflow_run`, and self-hosted runner exposure.\n  + Search patterns: `SHA pin`, `uses`, `mutable tag`, `Dependabot`, `download-artifact`, `cache`, `self-hosted runner`\n* `references\u002Freport-format.md` — Output template: summary table, finding cards, and before\u002Fafter\n  remediation blocks.\n  + Search patterns: `report`, `format`, `finding`, `summary`, `remediation`, `before`, `after`\n",{"description":7},"main","58843b159d7a4050d6b785a98b908cce505c0b92","agent\u002Fskills\u002Fgithub-actions-hardening",0,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent","https:\u002F\u002Fgithub.com\u002FReihantt6","reihsns.web.id","2026-08-19 20:08:18",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Reihantt6\u002Fsns-myagent --skill github-actions-hardening",{"tool":38,"command":39},"bunx","bunx skills add Reihantt6\u002Fsns-myagent --skill github-actions-hardening",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Reihantt6\u002Fsns-myagent --skill github-actions-hardening","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002FSKILL.md",true,[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Finjection.md","REFERENCE","参考文档",3035,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002Freferences\u002Finjection.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fpermissions-and-tokens.md",2743,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002Freferences\u002Fpermissions-and-tokens.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Freport-format.md",1920,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002Freferences\u002Freport-format.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fsupply-chain.md",2938,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002Freferences\u002Fsupply-chain.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Ftriggers-and-privilege.md",3397,"https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fgithub-actions-hardening\u002Freferences\u002Ftriggers-and-privilege.md",[69,76,83,90,97,104],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M77XDCYZ407XYMF2T4P6F7VT","youtube-transcript","Extract transcripts from YouTube videos. Use when the user asks for a transcript, subtitles, or captions of a YouTube video and provides a YouTube URL (youtube.com\u002Fwatch?v=, youtu.be\u002F, or similar). Supports output with or without timestamps.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-transcript\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M77XD7PBC98J6MXGJJ2TJ8DX","youtube-thumbnail-design","YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A\u002FB testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-thumbnail-design\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M77XD2541C8HXJ6RHYZP4NGJ","youtube-short-maker","Make YouTube Shorts that hold attention with Pexo — vertical 9:16, fast-paced, hook in the first 3 seconds. Describe your topic and Pexo writes the script, generates the shots, picks the models, and assembles a finished Short with music and captions. Use for YouTube Shorts: \"youtube short\", \"make a youtube short\", \"shorts video\", \"short-form video\". NOT for long-form or landscape video.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fyoutube-short-maker\u002FSKILL.md",[],[],{"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":96,"publishedAt":19},"01M77XCXKVSYK7KTZ3PQBVVGFD","xcode-project-setup","Safely modifies Xcode projects (.pbxproj) to add Swift Packages and link files. Use this skill whenever an iOS project needs dependencies installed (e.g. Firebase, Alamofire).","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fxcode-project-setup\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"publishedAt":19},"01M77XCR1DV8ZQK2NHWKVY4EWX","x402","Set up Browser Use Cloud payments with x402 — pay per request from a crypto wallet (USDC on Base mainnet), no signup or API key. Two setups it works out up front — \"just use it\" (set up a wallet so you or Claude Code can run cloud browser tasks paid from the wallet — Claude writes and runs throwaway scripts, nothing touches your codebase) or \"build it in\" (install the SDK and write the key + code into your project). Walks through wallet setup, funding, .env, and a ~$1 test run. Use when the user asks about x402, pay-per-use, USDC payments, or wants Browser Use Cloud without an API key. For the free-tier signup (reverse-CAPTCHA → API key), use `browser-use cloud signup` or the `cloud` skill instead.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx402\u002FSKILL.md",[],[],{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":19},"01M77XCMD3R3ZBZQQSW6E0793B","x-twitter-scraper","Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, hosted Apify Actor runs, MCP tools, TweetClaw OpenClaw plugin installs, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.","https:\u002F\u002Fgithub.com\u002FReihantt6\u002Fsns-myagent\u002Fblob\u002Fmain\u002Fagent\u002Fskills\u002Fx-twitter-scraper\u002FSKILL.md",[],[]]