[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A3R3CDFDTH7AXRHZYQWBM0":3,"skill-same:01M7A3R3CDFDTH7AXRHZYQWBM0":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":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M7A3R3CDFDTH7AXRHZYQWBM0","bumblebee",null,"Run Bumblebee supply-chain inventory and exposure scans on macOS\u002FLinux to detect compromised packages, extensions, and MCP host configs.","MHassan0000\u002FSkills","MHassan0000","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F224296448?v=4","01M7A14DTC1EZCRN04582533RD","Muhammad Hassan Yousaf","01M7A14DV10KTW8NHQTJPD08X0",1,"MIT","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fbumblebee\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bumblebee\ndescription: \"Run Bumblebee supply-chain inventory and exposure scans on macOS\u002FLinux to detect compromised packages, extensions, and MCP host configs.\"\ncategory: security\nrisk: safe\nsource: community\nsource_repo: mycelos-ai\u002Fbumblebee-skill\nsource_type: community\ndate_added: \"2026-05-27\"\nauthor: stefan-kp\ntags: [security, supply-chain, incident-response, npm, pypi, tooling]\ntools: [claude]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fmycelos-ai\u002Fbumblebee-skill\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n\n# Bumblebee Security Scan\n\nBumblebee (https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee) is a read-only inventory collector that surfaces package, extension, and developer-tool metadata on developer endpoints. It answers a focused supply-chain question: when an advisory names a package or version, do any matches exist on this machine right now?\n\nThis skill drives a single Bumblebee scan from start to finish:\n\n1. Verify Go is on the PATH (provide install guidance if not).\n2. Verify or install the `bumblebee` binary.\n3. Run the requested scan profile (`baseline`, `project`, or `deep`).\n4. Save raw NDJSON output plus a Markdown report into the user's workspace.\n5. Summarize findings — especially exposure-catalog matches — in the chat reply.\n\nCommunicate with the user in the language they used (German for Stefan). Code, commit messages, and on-disk file contents stay in English to match existing project conventions.\n\n## When to Use This Skill\n\nUse this skill when an advisory, incident report, or exposure catalog names compromised packages,\ndeveloper tools, browser\u002Feditor extensions, or MCP host configuration that may exist on a local\nmacOS or Linux developer endpoint.\n\nUse it for read-only inventory and exposure checks. Do not use it to patch, uninstall, quarantine,\nor otherwise mutate the scanned machine.\n\n## Step 1 — Clarify the scan request\n\nBefore running anything, confirm two things with the user via `AskUserQuestion`, unless the message already pins them down:\n\n- **Profile**: `baseline` (global package roots), `project` (specific dev folders like `~\u002Fcode`), or `deep` (explicit `--root` paths, including `$HOME` for incident response).\n- **Roots**: For `project` and `deep` profiles, ask which directories to scan. `deep` is the only profile that accepts a bare-home root.\n\nIf the user has an advisory or exposure-catalog file ready, also ask whether they want to pass it via `--exposure-catalog`. The skill does not ship its own catalogs — point them at `threat_intel\u002F` in the Bumblebee repo if they ask where to find ready-made ones.\n\nSkip the questions for one-liner asks like \"lauf mal ne Baseline-Scan\" — just run a baseline.\n\n## Step 2 — Check Go\n\nRun `command -v go && go version` in bash. Three outcomes:\n\n- **Go ≥ 1.25 present** → continue.\n- **Go present but \u003C 1.25** → tell the user the version, explain Bumblebee needs Go 1.25+, and stop until they upgrade.\n- **Go missing** → do not install Go automatically. Show platform-appropriate instructions and stop:\n  - macOS: `brew install go` (or download from https:\u002F\u002Fgo.dev\u002Fdl\u002F).\n  - Debian\u002FUbuntu: prefer the official tarball from https:\u002F\u002Fgo.dev\u002Fdl\u002F because distro repos lag; `sudo apt install golang-go` only as fallback.\n  - Fedora\u002FRHEL: `sudo dnf install golang` or the official tarball.\n\nAfter installation, the user must ensure `$GOBIN` (or `$HOME\u002Fgo\u002Fbin`) is on `$PATH` so `bumblebee` is found later.\n\n## Step 3 — Check or install Bumblebee\n\nRun `command -v bumblebee && bumblebee version`. If missing:\n\n```bash\ngo install github.com\u002Fperplexityai\u002Fbumblebee\u002Fcmd\u002Fbumblebee@latest\n```\n\nThen re-check `bumblebee version`. If the binary still cannot be located, the user's `GOBIN`\u002F`PATH` is likely misconfigured — surface the resolved `go env GOPATH` and `go env GOBIN` so they can fix it. Do not fall back to running the binary by absolute path silently; explain what is happening.\n\nOnce installed, also run `bumblebee selftest` as a sanity check. A non-zero exit means the local install is broken and the scan should not proceed.\n\n## Step 4 — Run the scan\n\nAll scans write NDJSON to a file. Use the workspace folder for output so the user can open the results afterwards.\n\nOutput filenames (use the user's workspace path; the example below assumes `$OUT` is set):\n\n- `bumblebee-\u003Cprofile>-\u003CUTC-timestamp>.ndjson` — raw records.\n- `bumblebee-\u003Cprofile>-\u003CUTC-timestamp>.report.md` — Markdown report (generated in Step 5).\n\nPick a sensible `--max-duration` so a runaway scan does not hang the session. Reasonable defaults:\n\n- `baseline`: 5m\n- `project`: 10m\n- `deep`: 15m (warn the user that scanning `$HOME` can still take longer; offer to raise the limit)\n\nAlways stream stderr to a sibling `.log` file — Bumblebee emits diagnostic NDJSON there that helps explain partial scans.\n\n### Baseline\n\n```bash\nbumblebee scan --profile baseline \\\n  --max-duration 5m \\\n  > \"$OUT\u002Fbumblebee-baseline-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-baseline-$TS.log\"\n```\n\nOptional: scope to specific ecosystems if the user only cares about, say, npm and PyPI:\n\n```bash\nbumblebee scan --profile baseline --ecosystem npm,pypi ...\n```\n\n### Project\n\nEach `--root` must be an existing absolute path. Reject bare `$HOME` for this profile (Bumblebee will reject it too — surface the message clearly).\n\n```bash\nbumblebee scan --profile project \\\n  --root \"$HOME\u002Fcode\" \\\n  --root \"$HOME\u002FDeveloper\" \\\n  --max-duration 10m \\\n  > \"$OUT\u002Fbumblebee-project-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-project-$TS.log\"\n```\n\n### Deep\n\nUsed for incident response — broad roots are allowed but should be paired with an exposure catalog and `--findings-only` whenever possible, so the output stays focused.\n\n```bash\nbumblebee scan --profile deep \\\n  --root \"$HOME\" \\\n  --exposure-catalog \"$CATALOG\" \\\n  --findings-only \\\n  --max-duration 15m \\\n  > \"$OUT\u002Fbumblebee-deep-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-deep-$TS.log\"\n```\n\nIf the user has no catalog, run deep without `--findings-only` but warn them that the NDJSON file can grow large (hundreds of MB on dense developer machines).\n\n## Step 5 — Generate the Markdown report\n\nRun the bundled helper to turn the NDJSON into a human-readable report. Resolve\nthe helper from the installed Bumblebee skill directory; never run a\nworkspace-relative `scripts\u002Frender_report.py` from the scanned project.\n\n```bash\nBUMBLEBEE_SKILL_DIR=\"\u002Fabsolute\u002Fpath\u002Fto\u002Fthe\u002Fbumblebee-skill-directory\"\ntest -f \"$BUMBLEBEE_SKILL_DIR\u002Fscripts\u002Frender_report.py\"\npython3 \"$BUMBLEBEE_SKILL_DIR\u002Fscripts\u002Frender_report.py\" \\\n  \"$OUT\u002Fbumblebee-\u003Cprofile>-$TS.ndjson\" \\\n  \"$OUT\u002Fbumblebee-\u003Cprofile>-$TS.report.md\"\n```\n\nThe helper groups records by type and ecosystem, lists every `finding` record with its catalog entry and severity, and embeds the `scan_summary` for traceability. It is dependency-free Python 3 — no `pip install` needed.\n\nIf `render_report.py` exits non-zero (malformed NDJSON, missing summary), surface stderr to the user instead of silently producing an empty report.\n\n## Step 6 — Present results\n\nEnd the turn with:\n\n- A short summary in chat: profile, root(s), record counts, and — most importantly — any findings with their severity. If there are zero findings, say so explicitly; silence on findings is the kind of thing that gets misread.\n- `computer:\u002F\u002F` links to both the NDJSON and the Markdown report so the user can open them directly.\n- If diagnostics in the `.log` file indicate skipped roots or read errors, mention it and link the log too.\n\nDo not paste large chunks of NDJSON into the chat — it is noisy and not where the user will read it.\n\n## Safety and privacy notes\n\n- Bumblebee is read-only by design. Do not propose patches, deletions, or `npm uninstall` actions from inside this skill; the user runs remediation themselves once they know what is affected.\n- MCP host configs can carry secrets in their `env` blocks. Bumblebee does not emit those values, but the `.log` file may still contain paths to sensitive config files. Treat the output files as containing inventory data and do not upload them to third-party services without the user's explicit consent (DSGVO-relevant).\n- Never run `bumblebee` with elevated privileges (`sudo`). It is meant to inspect the current user's developer environment, not the whole system.\n\n## Failure modes to watch for\n\n- `bumblebee: command not found` after `go install` → almost always a `PATH`\u002F`GOBIN` problem. Show `go env GOPATH GOBIN PATH` to debug.\n- `refusing to scan bare home with profile baseline` → use `deep` for `$HOME`, or pick a subdirectory for `project`.\n- Scan times out → either narrow the `--root` set, scope with `--ecosystem`, or raise `--max-duration`. Do not loop and retry blindly.\n- Exposure catalog rejected → check that the JSON has both `schema_version` and `entries` keys (bare top-level arrays are rejected) and that `schema_version` is one Bumblebee understands.\n\n## Limitations\n\n- This skill only reports local inventory and exposure matches; it does not remediate affected packages, extensions, or configs.\n- Scan coverage depends on Bumblebee's supported ecosystems, the selected roots, and the current user's filesystem permissions.\n- Results are point-in-time evidence and should be re-run after package installs, dependency updates, or incident-response changes.\n\n## Reference\n\nSee `scripts\u002Frender_report.py` for the report layout. Bumblebee's own documentation lives at https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee — consult `docs\u002Finventory-sources.md`, `docs\u002Ftransport.md`, and `docs\u002Fstate-model.md` when a question goes beyond what this skill covers.\n\n## Credit\n\nBumblebee is developed by Perplexity (https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee, Apache-2.0). All scan logic, output formats, and exposure-catalog semantics belong to that project. This repository is just a thin Claude-skill wrapper around the official `bumblebee` CLI; the wrapper itself is MIT-licensed (see `LICENSE`).\n","# Bumblebee Security Scan\n\nBumblebee (https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee) is a read-only inventory collector that surfaces package, extension, and developer-tool metadata on developer endpoints. It answers a focused supply-chain question: when an advisory names a package or version, do any matches exist on this machine right now?\n\nThis skill drives a single Bumblebee scan from start to finish:\n\n1. Verify Go is on the PATH (provide install guidance if not).\n2. Verify or install the `bumblebee` binary.\n3. Run the requested scan profile (`baseline`, `project`, or `deep`).\n4. Save raw NDJSON output plus a Markdown report into the user's workspace.\n5. Summarize findings — especially exposure-catalog matches — in the chat reply.\n\nCommunicate with the user in the language they used (German for Stefan). Code, commit messages, and on-disk file contents stay in English to match existing project conventions.\n\n## When to Use This Skill\n\nUse this skill when an advisory, incident report, or exposure catalog names compromised packages,\ndeveloper tools, browser\u002Feditor extensions, or MCP host configuration that may exist on a local\nmacOS or Linux developer endpoint.\n\nUse it for read-only inventory and exposure checks. Do not use it to patch, uninstall, quarantine,\nor otherwise mutate the scanned machine.\n\n## Step 1 — Clarify the scan request\n\nBefore running anything, confirm two things with the user via `AskUserQuestion`, unless the message already pins them down:\n\n- **Profile**: `baseline` (global package roots), `project` (specific dev folders like `~\u002Fcode`), or `deep` (explicit `--root` paths, including `$HOME` for incident response).\n- **Roots**: For `project` and `deep` profiles, ask which directories to scan. `deep` is the only profile that accepts a bare-home root.\n\nIf the user has an advisory or exposure-catalog file ready, also ask whether they want to pass it via `--exposure-catalog`. The skill does not ship its own catalogs — point them at `threat_intel\u002F` in the Bumblebee repo if they ask where to find ready-made ones.\n\nSkip the questions for one-liner asks like \"lauf mal ne Baseline-Scan\" — just run a baseline.\n\n## Step 2 — Check Go\n\nRun `command -v go && go version` in bash. Three outcomes:\n\n- **Go ≥ 1.25 present** → continue.\n- **Go present but \u003C 1.25** → tell the user the version, explain Bumblebee needs Go 1.25+, and stop until they upgrade.\n- **Go missing** → do not install Go automatically. Show platform-appropriate instructions and stop:\n  - macOS: `brew install go` (or download from https:\u002F\u002Fgo.dev\u002Fdl\u002F).\n  - Debian\u002FUbuntu: prefer the official tarball from https:\u002F\u002Fgo.dev\u002Fdl\u002F because distro repos lag; `sudo apt install golang-go` only as fallback.\n  - Fedora\u002FRHEL: `sudo dnf install golang` or the official tarball.\n\nAfter installation, the user must ensure `$GOBIN` (or `$HOME\u002Fgo\u002Fbin`) is on `$PATH` so `bumblebee` is found later.\n\n## Step 3 — Check or install Bumblebee\n\nRun `command -v bumblebee && bumblebee version`. If missing:\n\n```bash\ngo install github.com\u002Fperplexityai\u002Fbumblebee\u002Fcmd\u002Fbumblebee@latest\n```\n\nThen re-check `bumblebee version`. If the binary still cannot be located, the user's `GOBIN`\u002F`PATH` is likely misconfigured — surface the resolved `go env GOPATH` and `go env GOBIN` so they can fix it. Do not fall back to running the binary by absolute path silently; explain what is happening.\n\nOnce installed, also run `bumblebee selftest` as a sanity check. A non-zero exit means the local install is broken and the scan should not proceed.\n\n## Step 4 — Run the scan\n\nAll scans write NDJSON to a file. Use the workspace folder for output so the user can open the results afterwards.\n\nOutput filenames (use the user's workspace path; the example below assumes `$OUT` is set):\n\n- `bumblebee-\u003Cprofile>-\u003CUTC-timestamp>.ndjson` — raw records.\n- `bumblebee-\u003Cprofile>-\u003CUTC-timestamp>.report.md` — Markdown report (generated in Step 5).\n\nPick a sensible `--max-duration` so a runaway scan does not hang the session. Reasonable defaults:\n\n- `baseline`: 5m\n- `project`: 10m\n- `deep`: 15m (warn the user that scanning `$HOME` can still take longer; offer to raise the limit)\n\nAlways stream stderr to a sibling `.log` file — Bumblebee emits diagnostic NDJSON there that helps explain partial scans.\n\n### Baseline\n\n```bash\nbumblebee scan --profile baseline \\\n  --max-duration 5m \\\n  > \"$OUT\u002Fbumblebee-baseline-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-baseline-$TS.log\"\n```\n\nOptional: scope to specific ecosystems if the user only cares about, say, npm and PyPI:\n\n```bash\nbumblebee scan --profile baseline --ecosystem npm,pypi ...\n```\n\n### Project\n\nEach `--root` must be an existing absolute path. Reject bare `$HOME` for this profile (Bumblebee will reject it too — surface the message clearly).\n\n```bash\nbumblebee scan --profile project \\\n  --root \"$HOME\u002Fcode\" \\\n  --root \"$HOME\u002FDeveloper\" \\\n  --max-duration 10m \\\n  > \"$OUT\u002Fbumblebee-project-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-project-$TS.log\"\n```\n\n### Deep\n\nUsed for incident response — broad roots are allowed but should be paired with an exposure catalog and `--findings-only` whenever possible, so the output stays focused.\n\n```bash\nbumblebee scan --profile deep \\\n  --root \"$HOME\" \\\n  --exposure-catalog \"$CATALOG\" \\\n  --findings-only \\\n  --max-duration 15m \\\n  > \"$OUT\u002Fbumblebee-deep-$TS.ndjson\" \\\n  2> \"$OUT\u002Fbumblebee-deep-$TS.log\"\n```\n\nIf the user has no catalog, run deep without `--findings-only` but warn them that the NDJSON file can grow large (hundreds of MB on dense developer machines).\n\n## Step 5 — Generate the Markdown report\n\nRun the bundled helper to turn the NDJSON into a human-readable report. Resolve\nthe helper from the installed Bumblebee skill directory; never run a\nworkspace-relative `scripts\u002Frender_report.py` from the scanned project.\n\n```bash\nBUMBLEBEE_SKILL_DIR=\"\u002Fabsolute\u002Fpath\u002Fto\u002Fthe\u002Fbumblebee-skill-directory\"\ntest -f \"$BUMBLEBEE_SKILL_DIR\u002Fscripts\u002Frender_report.py\"\npython3 \"$BUMBLEBEE_SKILL_DIR\u002Fscripts\u002Frender_report.py\" \\\n  \"$OUT\u002Fbumblebee-\u003Cprofile>-$TS.ndjson\" \\\n  \"$OUT\u002Fbumblebee-\u003Cprofile>-$TS.report.md\"\n```\n\nThe helper groups records by type and ecosystem, lists every `finding` record with its catalog entry and severity, and embeds the `scan_summary` for traceability. It is dependency-free Python 3 — no `pip install` needed.\n\nIf `render_report.py` exits non-zero (malformed NDJSON, missing summary), surface stderr to the user instead of silently producing an empty report.\n\n## Step 6 — Present results\n\nEnd the turn with:\n\n- A short summary in chat: profile, root(s), record counts, and — most importantly — any findings with their severity. If there are zero findings, say so explicitly; silence on findings is the kind of thing that gets misread.\n- `computer:\u002F\u002F` links to both the NDJSON and the Markdown report so the user can open them directly.\n- If diagnostics in the `.log` file indicate skipped roots or read errors, mention it and link the log too.\n\nDo not paste large chunks of NDJSON into the chat — it is noisy and not where the user will read it.\n\n## Safety and privacy notes\n\n- Bumblebee is read-only by design. Do not propose patches, deletions, or `npm uninstall` actions from inside this skill; the user runs remediation themselves once they know what is affected.\n- MCP host configs can carry secrets in their `env` blocks. Bumblebee does not emit those values, but the `.log` file may still contain paths to sensitive config files. Treat the output files as containing inventory data and do not upload them to third-party services without the user's explicit consent (DSGVO-relevant).\n- Never run `bumblebee` with elevated privileges (`sudo`). It is meant to inspect the current user's developer environment, not the whole system.\n\n## Failure modes to watch for\n\n- `bumblebee: command not found` after `go install` → almost always a `PATH`\u002F`GOBIN` problem. Show `go env GOPATH GOBIN PATH` to debug.\n- `refusing to scan bare home with profile baseline` → use `deep` for `$HOME`, or pick a subdirectory for `project`.\n- Scan times out → either narrow the `--root` set, scope with `--ecosystem`, or raise `--max-duration`. Do not loop and retry blindly.\n- Exposure catalog rejected → check that the JSON has both `schema_version` and `entries` keys (bare top-level arrays are rejected) and that `schema_version` is one Bumblebee understands.\n\n## Limitations\n\n- This skill only reports local inventory and exposure matches; it does not remediate affected packages, extensions, or configs.\n- Scan coverage depends on Bumblebee's supported ecosystems, the selected roots, and the current user's filesystem permissions.\n- Results are point-in-time evidence and should be re-run after package installs, dependency updates, or incident-response changes.\n\n## Reference\n\nSee `scripts\u002Frender_report.py` for the report layout. Bumblebee's own documentation lives at https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee — consult `docs\u002Finventory-sources.md`, `docs\u002Ftransport.md`, and `docs\u002Fstate-model.md` when a question goes beyond what this skill covers.\n\n## Credit\n\nBumblebee is developed by Perplexity (https:\u002F\u002Fgithub.com\u002Fperplexityai\u002Fbumblebee, Apache-2.0). All scan logic, output formats, and exposure-catalog semantics belong to that project. This repository is just a thin Claude-skill wrapper around the official `bumblebee` CLI; the wrapper itself is MIT-licensed (see `LICENSE`).\n",{"name":5,"risk":24,"tags":25,"tools":32,"author":34,"source":35,"license":15,"category":26,"date_added":36,"description":7,"source_repo":37,"source_type":35,"license_source":38},"safe",[26,27,28,29,30,31],"security","supply-chain","incident-response","npm","pypi","tooling",[33],"claude","stefan-kp","community","2026-05-27","mycelos-ai\u002Fbumblebee-skill","https:\u002F\u002Fgithub.com\u002Fmycelos-ai\u002Fbumblebee-skill\u002Fblob\u002Fmain\u002FLICENSE","main","a4404a75dc81d6b7e58c5906b6aaffbcb5e84747","Claude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fbumblebee",0,"https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills","https:\u002F\u002Fgithub.com\u002FMHassan0000","https:\u002F\u002Fhassanyousaf.vercel.app","Full Stack Developer building web apps, SaaS, AI systems, and automations. Passionate about clean code, UI\u002FUX, backend systems, and turning ideas into products.","2026-08-07 20:42:05",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add MHassan0000\u002FSkills --skill bumblebee",{"tool":54,"command":55},"bunx","bunx skills add MHassan0000\u002FSkills --skill bumblebee",{"tool":57,"command":58},"pnpm","pnpm dlx skills add MHassan0000\u002FSkills --skill bumblebee","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fbumblebee\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"scripts\u002Frender_report.py","SCRIPT","脚本",14019,"https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fantigravity skills\u002Fagentic-awesome-skills\u002Fskills\u002Fbumblebee\u002Fscripts\u002Frender_report.py",[69,76,83,90,99,107],{"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},"01M7AGBX58S04DX8DKKME8N311","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fvercel-react-best-practices\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},"01M7AGBREE890608Z7YDMAKH27","stop-slop","Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fstop-slop\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},"01M7AGAS972A2AN7Q5EW8HEAXK","ogilvy-copywriting","Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Fogilvy\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":94,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7AGAF12803G5JPVMK79AYJB","frontend-design","Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML\u002FCSS layouts, or when styling\u002Fbeautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fskills boraztunc github\u002Ffrontend-design\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7AG88WWVWCGJY9WA9CH7EY4","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":94,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7AG7ZTNV7XQCWDQ9674FBYB","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FMHassan0000\u002FSkills\u002Fblob\u002Fmain\u002FClaude\u002Fobra superpower skills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[]]