[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M777EJHS948M899TAJJSZX9E":3,"skill-same:01M777EJHS948M899TAJJSZX9E":47},{"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":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M777EJHS948M899TAJJSZX9E","claude-to-free",null,"Migrate OpenClaw from Claude subscription OAuth to a free or cheap model provider (OpenRouter, Gemini, Ollama). Use when the user says Claude stopped working, gets an auth error, mentions the Anthropic April 2026 subscription ban, or asks to switch models without paying Anthropic more.","Lord1Egypt\u002Fawesome-skill-forge","Lord1Egypt","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F99746359?v=4","01M7592YDNT0XK9WJ0T2MQVPDN","Mohamed Mounir Ali AL Keshita","01M75GRFNHC8VZNWEB8DKDE433",3,"MIT","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fclaude-to-free\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: claude-to-free\ndescription: Migrate OpenClaw from Claude subscription OAuth to a free or cheap model provider (OpenRouter, Gemini, Ollama). Use when the user says Claude stopped working, gets an auth error, mentions the Anthropic April 2026 subscription ban, or asks to switch models without paying Anthropic more.\n---\n\n# Model Migration Skill\n\nHelp the user migrate OpenClaw from Claude subscription OAuth to a free or cheap provider.\n\n## When to use this skill\n\n- User says Claude is blocked, not working, or requires \"extra usage\"\n- User mentions the April 2026 Anthropic harness policy change\n- User wants to switch to Gemini, OpenRouter, Ollama, or any non-Claude provider\n- User asks \"how do I use OpenClaw without Claude?\"\n\n---\n\n## Step 1 — Diagnose\n\nRead the current config and identify what's broken:\n\n```bash\ncat ~\u002F.openclaw\u002Fopenclaw.json | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nauth = d.get('auth',{})\nprofiles = auth.get('profiles',{})\nmodel = d.get('agents',{}).get('defaults',{}).get('model',{}).get('primary','not set')\nprint('Current model:', model)\nfor name, p in profiles.items():\n    print(f'Auth profile: {name} provider={p.get(\\\"provider\\\")} mode={p.get(\\\"mode\\\")}')\n\"\n```\n\nIf you see `provider=anthropic mode=oauth` — that's the blocked profile. Proceed.\n\n---\n\n## Step 2 — Recommend a path\n\nAsk the user one question: **\"Do you want free (no cost) or are you okay with a small per-token charge for better quality?\"**\n\n### Free path (recommended for most users)\n→ OpenRouter free tier — no credit card, no cost\n\nBest free models right now:\n- `openrouter\u002Ffree` — auto-picks the best free model (zero config)\n- `openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct:free` — strong general model\n- `openrouter\u002Fqwen\u002Fqwen3-coder:free` — best free coding model (262k context)\n- `openrouter\u002Fqwen\u002Fqwen3.6-plus:free` — 1M context, free\n\n### Cheap paid path ($0.10\u002FMTok — roughly $1–5\u002Fmonth for typical use)\n- `openrouter\u002Fgoogle\u002Fgemini-2.5-flash-lite` — Google's fast model, 1M context\n- `openrouter\u002Fgoogle\u002Fgemini-2.0-flash-001` — excellent quality\u002Fprice\n- `openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct` — same as free but reliable\n\n### Free + local path (privacy-first)\n→ Ollama — runs on the user's machine, zero cost, fully private\n\n### Free direct (Gemini API)\n→ Google AI Studio free tier — check current limits at aistudio.google.com (varies by account\u002Fregion)\n\n---\n\n## Step 3 — Migrate using OpenClaw CLI (preferred)\n\nUse native OpenClaw commands — `openclaw onboard` creates the auth profile and config in one shot:\n\n```bash\n# 1. Add your provider (example: OpenRouter free)\nopenclaw onboard --non-interactive --accept-risk --auth-choice openrouter-api-key --openrouter-api-key YOUR_OPENROUTER_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui\n\n# 2. Set a free model\nopenclaw models set openrouter\u002Fqwen\u002Fqwen3.6-plus:free\n\n# 3. Restart\nopenclaw gateway restart\n```\n\nOr use the interactive auth helper:\n\n```bash\nopenclaw models auth login --provider openrouter\n# (follow prompts to paste your key)\nopenclaw models set openrouter\u002Fqwen\u002Fqwen3.6-plus:free\nopenclaw gateway restart\n```\n\nGet a free OpenRouter key at https:\u002F\u002Fopenrouter.ai\u002Fkeys (no credit card required).\n\n---\n\n## Step 4 — Manual config (if wizard doesn't work)\n\n### Option A: OpenRouter free (zero cost)\n\n1. Get a free API key at https:\u002F\u002Fopenrouter.ai\u002Fkeys (no credit card)\n2. Run: `openclaw onboard --non-interactive --accept-risk --auth-choice openrouter-api-key --openrouter-api-key YOUR_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui`\n3. Set model: `openclaw models set openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct:free`\n4. Restart: `openclaw gateway restart`\n\n### Option B: Gemini direct (free tier)\n\n1. Get key at https:\u002F\u002Faistudio.google.com → Get API key\n2. Run: `openclaw onboard --non-interactive --accept-risk --auth-choice gemini-api-key --gemini-api-key YOUR_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui`\n3. Set model: `openclaw models set google\u002Fgemini-2.5-flash-lite`\n4. Restart: `openclaw gateway restart`\n\n### Option C: Ollama (local or cloud free tier)\n\n1. Install: `curl -fsSL https:\u002F\u002Follama.com\u002Finstall.sh | sh` (or use cloud: ollama.com)\n2. Pull a model: `ollama pull llama3.2`\n3. Run: `openclaw onboard --non-interactive --auth-choice ollama --accept-risk`\n4. Set model: `openclaw models set ollama\u002Fllama3.2`\n5. Restart: `openclaw gateway restart`\n\n---\n\n## Step 5 — Verify\n\n**First, confirm the auth profile exists for the new provider:**\n\n```bash\nopenclaw models status\n```\n\nCheck that the output lists the expected auth profile (e.g. `openrouter`, `google`, `ollama`). **If it's missing, the gateway will silently fall back to the first working provider (usually Anthropic) — the model set in config doesn't matter without a matching auth profile.**\n\nIf the auth profile is missing → go back to Step 3\u002F4 and run `openclaw onboard` for that provider first. Then re-run `openclaw models set` and restart.\n\nOnly once the auth profile is confirmed, verify the active model:\n\n```bash\nopenclaw models status --plain | grep -i \"primary\\|model\"\n```\n\n`openclaw models status` verifies the configured model\u002Fauth state, not necessarily the live runtime model already attached to an existing Telegram chat session.\n\nTo verify the live runtime model, start a new chat\u002Fsession (or reset the current one) and then check `\u002Fstatus`.\n\nIf the config still looks stale after confirming the auth profile exists, restart the gateway with the portable CLI command:\n\n```bash\nopenclaw gateway restart\n```\n\n---\n\n## Common errors\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `401 Unauthorized` | Invalid API key | Re-enter key, check for typos |\n| `model not found` | Wrong model ID | Check exact ID in guide |\n| `connection refused` | Ollama not running | Run `ollama serve` |\n| `RESOURCE_EXHAUSTED` | Free tier rate limit | Wait or switch to paid tier |\n| Config not applied | Gateway cached old config | Full restart via systemd |\n\n---\n\n## Resources\n\n- Full guides: \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude>\n- Free model list: \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude\u002Fblob\u002Fmain\u002Fguides\u002Fmodel-comparison.md>\n- Model-migration skill (ClawHub source): \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude\u002Ftree\u002Fmain\u002Fskills\u002Fmodel-migration>\n- Need hands-on help: \u003Chttps:\u002F\u002Fbluebirdback.com> (OpenClaw rescue, $99 fixed)\n\n---\n\n## Changelog\n\n- **v1.0.2** (2026-04-04): Add required `--accept-risk` to non-interactive onboarding examples. Add `--skip-health` alongside `--skip-daemon` so the examples work on broken\u002Fstopped local gateways. Clarify that `openclaw models status` verifies configured state, not necessarily the live runtime model in an existing Telegram session. Switch fallback restart guidance back to portable `openclaw gateway restart`.\n- **v1.0.1** (2026-04-04): Fix broken CLI commands — `--auth-choice apiKey --token-provider openrouter` was never valid. Updated to `--auth-choice openrouter-api-key --openrouter-api-key KEY` with `--skip-*` flags for non-interactive flow. Fixed Gemini auth from `google-api-key` to `gemini-api-key`. Added `openclaw models auth login` as alternative flow. Updated verification to use `--plain` flag.\n","# Model Migration Skill\n\nHelp the user migrate OpenClaw from Claude subscription OAuth to a free or cheap provider.\n\n## When to use this skill\n\n- User says Claude is blocked, not working, or requires \"extra usage\"\n- User mentions the April 2026 Anthropic harness policy change\n- User wants to switch to Gemini, OpenRouter, Ollama, or any non-Claude provider\n- User asks \"how do I use OpenClaw without Claude?\"\n\n---\n\n## Step 1 — Diagnose\n\nRead the current config and identify what's broken:\n\n```bash\ncat ~\u002F.openclaw\u002Fopenclaw.json | python3 -c \"\nimport json,sys\nd=json.load(sys.stdin)\nauth = d.get('auth',{})\nprofiles = auth.get('profiles',{})\nmodel = d.get('agents',{}).get('defaults',{}).get('model',{}).get('primary','not set')\nprint('Current model:', model)\nfor name, p in profiles.items():\n    print(f'Auth profile: {name} provider={p.get(\\\"provider\\\")} mode={p.get(\\\"mode\\\")}')\n\"\n```\n\nIf you see `provider=anthropic mode=oauth` — that's the blocked profile. Proceed.\n\n---\n\n## Step 2 — Recommend a path\n\nAsk the user one question: **\"Do you want free (no cost) or are you okay with a small per-token charge for better quality?\"**\n\n### Free path (recommended for most users)\n→ OpenRouter free tier — no credit card, no cost\n\nBest free models right now:\n- `openrouter\u002Ffree` — auto-picks the best free model (zero config)\n- `openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct:free` — strong general model\n- `openrouter\u002Fqwen\u002Fqwen3-coder:free` — best free coding model (262k context)\n- `openrouter\u002Fqwen\u002Fqwen3.6-plus:free` — 1M context, free\n\n### Cheap paid path ($0.10\u002FMTok — roughly $1–5\u002Fmonth for typical use)\n- `openrouter\u002Fgoogle\u002Fgemini-2.5-flash-lite` — Google's fast model, 1M context\n- `openrouter\u002Fgoogle\u002Fgemini-2.0-flash-001` — excellent quality\u002Fprice\n- `openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct` — same as free but reliable\n\n### Free + local path (privacy-first)\n→ Ollama — runs on the user's machine, zero cost, fully private\n\n### Free direct (Gemini API)\n→ Google AI Studio free tier — check current limits at aistudio.google.com (varies by account\u002Fregion)\n\n---\n\n## Step 3 — Migrate using OpenClaw CLI (preferred)\n\nUse native OpenClaw commands — `openclaw onboard` creates the auth profile and config in one shot:\n\n```bash\n# 1. Add your provider (example: OpenRouter free)\nopenclaw onboard --non-interactive --accept-risk --auth-choice openrouter-api-key --openrouter-api-key YOUR_OPENROUTER_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui\n\n# 2. Set a free model\nopenclaw models set openrouter\u002Fqwen\u002Fqwen3.6-plus:free\n\n# 3. Restart\nopenclaw gateway restart\n```\n\nOr use the interactive auth helper:\n\n```bash\nopenclaw models auth login --provider openrouter\n# (follow prompts to paste your key)\nopenclaw models set openrouter\u002Fqwen\u002Fqwen3.6-plus:free\nopenclaw gateway restart\n```\n\nGet a free OpenRouter key at https:\u002F\u002Fopenrouter.ai\u002Fkeys (no credit card required).\n\n---\n\n## Step 4 — Manual config (if wizard doesn't work)\n\n### Option A: OpenRouter free (zero cost)\n\n1. Get a free API key at https:\u002F\u002Fopenrouter.ai\u002Fkeys (no credit card)\n2. Run: `openclaw onboard --non-interactive --accept-risk --auth-choice openrouter-api-key --openrouter-api-key YOUR_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui`\n3. Set model: `openclaw models set openrouter\u002Fmeta-llama\u002Fllama-3.3-70b-instruct:free`\n4. Restart: `openclaw gateway restart`\n\n### Option B: Gemini direct (free tier)\n\n1. Get key at https:\u002F\u002Faistudio.google.com → Get API key\n2. Run: `openclaw onboard --non-interactive --accept-risk --auth-choice gemini-api-key --gemini-api-key YOUR_KEY --skip-channels --skip-skills --skip-search --skip-daemon --skip-health --skip-ui`\n3. Set model: `openclaw models set google\u002Fgemini-2.5-flash-lite`\n4. Restart: `openclaw gateway restart`\n\n### Option C: Ollama (local or cloud free tier)\n\n1. Install: `curl -fsSL https:\u002F\u002Follama.com\u002Finstall.sh | sh` (or use cloud: ollama.com)\n2. Pull a model: `ollama pull llama3.2`\n3. Run: `openclaw onboard --non-interactive --auth-choice ollama --accept-risk`\n4. Set model: `openclaw models set ollama\u002Fllama3.2`\n5. Restart: `openclaw gateway restart`\n\n---\n\n## Step 5 — Verify\n\n**First, confirm the auth profile exists for the new provider:**\n\n```bash\nopenclaw models status\n```\n\nCheck that the output lists the expected auth profile (e.g. `openrouter`, `google`, `ollama`). **If it's missing, the gateway will silently fall back to the first working provider (usually Anthropic) — the model set in config doesn't matter without a matching auth profile.**\n\nIf the auth profile is missing → go back to Step 3\u002F4 and run `openclaw onboard` for that provider first. Then re-run `openclaw models set` and restart.\n\nOnly once the auth profile is confirmed, verify the active model:\n\n```bash\nopenclaw models status --plain | grep -i \"primary\\|model\"\n```\n\n`openclaw models status` verifies the configured model\u002Fauth state, not necessarily the live runtime model already attached to an existing Telegram chat session.\n\nTo verify the live runtime model, start a new chat\u002Fsession (or reset the current one) and then check `\u002Fstatus`.\n\nIf the config still looks stale after confirming the auth profile exists, restart the gateway with the portable CLI command:\n\n```bash\nopenclaw gateway restart\n```\n\n---\n\n## Common errors\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| `401 Unauthorized` | Invalid API key | Re-enter key, check for typos |\n| `model not found` | Wrong model ID | Check exact ID in guide |\n| `connection refused` | Ollama not running | Run `ollama serve` |\n| `RESOURCE_EXHAUSTED` | Free tier rate limit | Wait or switch to paid tier |\n| Config not applied | Gateway cached old config | Full restart via systemd |\n\n---\n\n## Resources\n\n- Full guides: \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude>\n- Free model list: \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude\u002Fblob\u002Fmain\u002Fguides\u002Fmodel-comparison.md>\n- Model-migration skill (ClawHub source): \u003Chttps:\u002F\u002Fgithub.com\u002FBlueBirdBack\u002Fopenclaw-without-claude\u002Ftree\u002Fmain\u002Fskills\u002Fmodel-migration>\n- Need hands-on help: \u003Chttps:\u002F\u002Fbluebirdback.com> (OpenClaw rescue, $99 fixed)\n\n---\n\n## Changelog\n\n- **v1.0.2** (2026-04-04): Add required `--accept-risk` to non-interactive onboarding examples. Add `--skip-health` alongside `--skip-daemon` so the examples work on broken\u002Fstopped local gateways. Clarify that `openclaw models status` verifies configured state, not necessarily the live runtime model in an existing Telegram session. Switch fallback restart guidance back to portable `openclaw gateway restart`.\n- **v1.0.1** (2026-04-04): Fix broken CLI commands — `--auth-choice apiKey --token-provider openrouter` was never valid. Updated to `--auth-choice openrouter-api-key --openrouter-api-key KEY` with `--skip-*` flags for non-interactive flow. Fixed Gemini auth from `google-api-key` to `gemini-api-key`. Added `openclaw models auth login` as alternative flow. Updated verification to use `--plain` flag.\n",{"name":5,"description":7},"master","4aa004da461d820f4ea5499e58eb8d196cf99016","community\u002Fclawhub\u002Fc\u002Fclaude-to-free",0,"https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge","https:\u002F\u002Fskill-explorer-rho.vercel.app","https:\u002F\u002Fgithub.com\u002FLord1Egypt","Unbreakable. Unstoppable. Unmatched⚡.\r\n Speaker of machine tongues 🤖  | World-builder of decentralized dreams 🌐 | Defender of the digital realm🛡️.","2026-06-10 08:21:01",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add Lord1Egypt\u002Fawesome-skill-forge --skill claude-to-free",{"tool":39,"command":40},"bunx","bunx skills add Lord1Egypt\u002Fawesome-skill-forge --skill claude-to-free",{"tool":42,"command":43},"pnpm","pnpm dlx skills add Lord1Egypt\u002Fawesome-skill-forge --skill claude-to-free","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fcommunity\u002Fclawhub\u002Fc\u002Fclaude-to-free\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M785WKJB99G3STR1NF9NRTJW","youtube-content","YouTube transcripts to summaries, threads, blogs.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fyoutube-content\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M785WEFHB0G2S9YA6EPR3H0E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fxurl\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M785W98EDN4EFJXJPMQEHCRC","touchdesigner-mcp","Control a running TouchDesigner instance via twozero MCP — create operators, set parameters, wire connections, execute Python, build real-time visuals. 36 native tools.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftouchdesigner-mcp\u002FSKILL.md",[],[],{"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},"01M785W5S9FP3QBH2V191E025P","test-driven-development","TDD: enforce RED-GREEN-REFACTOR, tests before code.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Ftest-driven-development\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},"01M785W2AS08NSSH9YATCV6FJB","teams-meeting-pipeline","Operate the Teams meeting summary pipeline via Hermes CLI — summarize meetings, inspect pipeline status, replay jobs, manage Microsoft Graph subscriptions.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fteams-meeting-pipeline\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},"01M785VXKW4T34BTP1SCHW1R7F","systematic-debugging","4-phase root cause debugging: understand bugs before fixing.","https:\u002F\u002Fgithub.com\u002FLord1Egypt\u002Fawesome-skill-forge\u002Fblob\u002Fmaster\u002Fskills\u002Fsystematic-debugging\u002FSKILL.md",[],[]]