{"_id":"@agentsandswarms/skills-loader","_rev":"6-76d969d10c8e5d7ed5621d7d261b95f0","name":"@agentsandswarms/skills-loader","dist-tags":{"latest":"1.2.2"},"versions":{"1.0.0":{"name":"@agentsandswarms/skills-loader","version":"1.0.0","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","_id":"@agentsandswarms/skills-loader@1.0.0","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"homepage":"https://skls.to","bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"dist":{"shasum":"e866a367bf14e90423f2428c7abaea4e9cdcce80","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.0.0.tgz","fileCount":14,"integrity":"sha512-JKk4WKGne2I6TvO9yAP2ave15RwnffFT+MDdV+CI4iIWf9+h7Jj40zmtwsjRXdegsmp0Th6EWNXPGSJh+XS1nw==","signatures":[{"sig":"MEUCIG3ODBG+9fMMJDF6zSOOnXQIkD4kPuwsgq7Im9H7Ql1XAiEAxzTWZbh2RAq+eMWubvF6L8XCKPnQn6Qyp6L6bwO9xn4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":24742},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"}},"scripts":{"test":"vitest run","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"npm run typecheck && npm run build"},"_npmUser":{"name":"rudedog","email":"john@agentsandswarms.ai"},"repository":{"url":"git+https://github.com/rudedoggg/Corbot.git","type":"git","directory":"packages/skills-loader-client"},"_npmVersion":"11.12.1","description":"Thin client for the Agents & Swarms Skills Loader API — skill recommendations, effectiveness tracking, and catalog browsing for AI agents","directories":{},"_nodeVersion":"23.11.0","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.8.3"},"_npmOperationalInternal":{"tmp":"tmp/skills-loader_1.0.0_1776622168761_0.24976111515516486","host":"s3://npm-registry-packages-npm-production"}},"1.1.0":{"name":"@agentsandswarms/skills-loader","version":"1.1.0","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","_id":"@agentsandswarms/skills-loader@1.1.0","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"homepage":"https://skls.to","bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"bin":{"skills-loader":"dist/cli.js"},"dist":{"shasum":"a21c7c9d8dc7c6f5be4a5607d91e401cf92efdae","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.1.0.tgz","fileCount":18,"integrity":"sha512-Bc09nQAe0/UlznGvyN6oXZN040J690S7N/Fi0IXFUI4Zx+XRsw+7D8lyza/l6fS/YSzzu0OUCL6Op3tdxgkf/g==","signatures":[{"sig":"MEUCIFA1xhyNB/C4WDmV2KRqZFTNfb/Ip3GB9XazJonRKjRSAiEAsiYSyJjVnC7do2vCstf7HmSVbFdo7+OmOdAE4SuiOnc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":52231},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./cli":{"types":"./dist/cli.d.ts","import":"./dist/cli.js"}},"gitHead":"758d65348235030cbd7afd0da6de8be5cebf8a6d","scripts":{"test":"vitest run","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"npm run typecheck && npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:6302f5d7-c5d2-405b-8afe-c662c2cf9bd0"}},"repository":{"url":"git+https://github.com/rudedoggg/Corbot.git","type":"git","directory":"packages/skills-loader-client"},"_npmVersion":"11.13.0","description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","directories":{},"_nodeVersion":"20.20.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.8.3"},"_npmOperationalInternal":{"tmp":"tmp/skills-loader_1.1.0_1776901169711_0.6816606595198553","host":"s3://npm-registry-packages-npm-production"}},"1.1.1":{"name":"@agentsandswarms/skills-loader","version":"1.1.1","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","_id":"@agentsandswarms/skills-loader@1.1.1","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"homepage":"https://skls.to","bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"bin":{"skills-loader":"dist/cli.js"},"dist":{"shasum":"92101f5a58bece1d6c9db78e10e87b10937da1fb","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.1.1.tgz","fileCount":18,"integrity":"sha512-p8MJaqLdrrOR7wxzszH2Yv3rBdx9VMAHpihFQ1QCaYwJ/bubTpxpkFCcSaPclQNZH/21z5+IEq92i9X0waESVg==","signatures":[{"sig":"MEUCIQCpB+ZzczSj68A0QjqZ0/4TlAFbELFjvCP42u8x9txobAIgaFF2GRzxGC42oI6UfpVcz2w3Hk/0T3SZUxM1XalkHL0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":53254},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./cli":{"types":"./dist/cli.d.ts","import":"./dist/cli.js"}},"gitHead":"db4a4191b87350311a98fbf9bfd44e539ba406d7","scripts":{"test":"vitest run","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"npm run typecheck && npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:6302f5d7-c5d2-405b-8afe-c662c2cf9bd0"}},"repository":{"url":"git+https://github.com/rudedoggg/Corbot.git","type":"git","directory":"packages/skills-loader-client"},"_npmVersion":"11.13.0","description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","directories":{},"_nodeVersion":"20.20.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.8.3"},"_npmOperationalInternal":{"tmp":"tmp/skills-loader_1.1.1_1776916975533_0.7869140658127685","host":"s3://npm-registry-packages-npm-production"}},"1.1.2":{"name":"@agentsandswarms/skills-loader","version":"1.1.2","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","_id":"@agentsandswarms/skills-loader@1.1.2","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"homepage":"https://skls.to","bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"bin":{"skills-loader":"dist/cli.js"},"dist":{"shasum":"7d5a20e8a1f92448015fa21ab36b8df10409aa15","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.1.2.tgz","fileCount":18,"integrity":"sha512-8QPuYwT12t29sflmVYZSrOWU5E1Rp9ULHOVKWXrr2EyoirvEYy/3GIoyrI6ZYCWFWUZT31U0WEBI8fiL4CjJAA==","signatures":[{"sig":"MEQCIAEh+frkaU6NqArxLLlHHMN/liaDUpbLFJKP70w1U0vqAiBexQ3GgtBgmir4zzOdPZ2kXz+vaAiku/bFTqvBFtLD4g==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":55202},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./cli":{"types":"./dist/cli.d.ts","import":"./dist/cli.js"}},"gitHead":"7c0b0f7acdae8a18971d97ba67974ddd6b18b463","scripts":{"test":"vitest run","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"npm run typecheck && npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:6302f5d7-c5d2-405b-8afe-c662c2cf9bd0"}},"repository":{"url":"git+https://github.com/rudedoggg/Corbot.git","type":"git","directory":"packages/skills-loader-client"},"_npmVersion":"11.13.0","description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","directories":{},"_nodeVersion":"20.20.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.8.3"},"_npmOperationalInternal":{"tmp":"tmp/skills-loader_1.1.2_1777155432617_0.16467967583005483","host":"s3://npm-registry-packages-npm-production"}},"1.2.0":{"name":"@agentsandswarms/skills-loader","version":"1.2.0","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","_id":"@agentsandswarms/skills-loader@1.2.0","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"homepage":"https://skls.to","bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"bin":{"skills-loader":"dist/cli.js"},"dist":{"shasum":"924ce028c88bbac5bf609464e1369f0058121a72","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.2.0.tgz","fileCount":18,"integrity":"sha512-OeNEPk4+KXBe+03zCHOX8XIWglgaYzDukldJ6aNDXreoF0u0RKGeUmWWBFYmMYSnQ8kFHM6Keopo/P/qPq1vfQ==","signatures":[{"sig":"MEMCICfoCH6NPZZraDbmejS79Gzam0bXVzVsmoaCeFIg+wumAh88Bzl+cmVDzhzXVfw+cPeaa4RmHfCGLVl5louzEhGm","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":59964},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","engines":{"node":">=18.0.0"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./cli":{"types":"./dist/cli.d.ts","import":"./dist/cli.js"}},"gitHead":"7056cc44455dad8114b3343b7c8d4e13b1aa4c4a","scripts":{"test":"vitest run","build":"tsc","typecheck":"tsc --noEmit","prepublishOnly":"npm run typecheck && npm run build"},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:6302f5d7-c5d2-405b-8afe-c662c2cf9bd0"}},"repository":{"url":"git+https://github.com/rudedoggg/Corbot.git","type":"git","directory":"packages/skills-loader-client"},"_npmVersion":"11.14.1","description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","directories":{},"_nodeVersion":"20.20.2","publishConfig":{"access":"public"},"_hasShrinkwrap":false,"devDependencies":{"vitest":"^3.0.0","typescript":"^5.8.3"},"_npmOperationalInternal":{"tmp":"tmp/skills-loader_1.2.0_1779131130610_0.7721564014436113","host":"s3://npm-registry-packages-npm-production"}},"1.2.2":{"name":"@agentsandswarms/skills-loader","version":"1.2.2","description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","mcpName":"ai.agentsandswarms/skills-loader","type":"module","main":"dist/index.js","types":"dist/index.d.ts","bin":{"skills-loader":"dist/cli.js"},"exports":{".":{"types":"./dist/index.d.ts","import":"./dist/index.js"},"./cli":{"types":"./dist/cli.d.ts","import":"./dist/cli.js"}},"scripts":{"build":"tsc","typecheck":"tsc --noEmit","test":"vitest run","prepublishOnly":"npm run typecheck && npm run build"},"keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","homepage":"https://skls.to","repository":{"type":"git","url":"git+https://github.com/rudedoggg/Corbot.git","directory":"packages/skills-loader-client"},"bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"publishConfig":{"access":"public"},"devDependencies":{"typescript":"^5.8.3","vitest":"^3.0.0"},"engines":{"node":">=18.0.0"},"dependencies":{"json5":"^2.2.3"},"gitHead":"35212de59dd89f8085adc8ccf93f6199db56f9fc","_id":"@agentsandswarms/skills-loader@1.2.2","_nodeVersion":"22.23.2","_npmVersion":"12.0.2","dist":{"integrity":"sha512-NYhe+HqfgJKzT6Au6wSNuKDkL0QBghKKZjIOWXT6aozCfjftjKtyxUDuC9ATC8HfjHjMqWVGasZBDdihdVim/Q==","shasum":"f6d5cf149fd93ab77f213848fe0613443a92a559","tarball":"https://registry.npmjs.org/@agentsandswarms/skills-loader/-/skills-loader-1.2.2.tgz","fileCount":18,"unpackedSize":77321,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQDO3/0DPAveK1XWGV3rWugtw/ZwQHleS5HEsScKVh9kuAIhANmLS1KlqZn94RoPBfA73BAJkAueNZ/ykcUZ5yjHacej"}]},"_npmUser":{"name":"GitHub Actions","email":"npm-oidc-no-reply@github.com","trustedPublisher":{"id":"github","oidcConfigId":"oidc:6302f5d7-c5d2-405b-8afe-c662c2cf9bd0"}},"directories":{},"maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/skills-loader_1.2.2_1787688192452_0.7449380371797927"},"_hasShrinkwrap":false}},"time":{"created":"2026-04-19T18:09:28.661Z","modified":"2026-08-25T20:03:12.774Z","1.0.0":"2026-04-19T18:09:28.920Z","1.1.0":"2026-04-22T23:39:29.844Z","1.1.1":"2026-04-23T04:02:55.759Z","1.1.2":"2026-04-25T22:17:12.748Z","1.2.0":"2026-05-18T19:05:30.752Z","1.2.2":"2026-08-25T20:03:12.602Z"},"bugs":{"url":"https://github.com/rudedoggg/Corbot/issues"},"author":{"name":"Agents & Swarms","email":"hello@agentsandswarms.ai"},"license":"MIT","homepage":"https://skls.to","keywords":["agent-skills","skill-effectiveness","skill-loader","skill-recommendation","mcp","ai-agent","agent-memory","model-context-protocol","prompt-engineering","agent-composition","skill-tracking","claude-code","cursor","ai-agents","agents-and-swarms"],"repository":{"type":"git","url":"git+https://github.com/rudedoggg/Corbot.git","directory":"packages/skills-loader-client"},"description":"Skills Loader CLI installer + thin client. One command (npx @agentsandswarms/skills-loader install) to connect any MCP-compatible IDE — Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev — to the hosted Skills Loader","maintainers":[{"name":"rudedog","email":"john@agentsandswarms.ai"}],"readme":"# @agentsandswarms/skills-loader\n\n> The knowledge layer your AI is missing. 2,000+ security-reviewed coding skills for any MCP-capable IDE.\n\nThis package is two things in one:\n1. **A CLI installer** that connects Skills Loader to your IDE in one command\n2. **A typed SDK** for direct API access (recommendations, effectiveness tracking, catalog browsing)\n\nFor agents and humans who'd rather use Skills Loader as an MCP server (Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev), the CLI is what you want.\n\n---\n\n## Install\n\nOne command (works keyless — 100 requests/day, no signup needed):\n\n```bash\nnpx @agentsandswarms/skills-loader install\n```\n\nThen restart your IDE. For more options and per-IDE manual setup, see [skls.to](https://skls.to).\n\n---\n\n## 🤖 AI agent installing this for a user?\n\nIf a user asked you to \"install Skills Loader\" and you have shell access, run:\n\n```bash\nnpx @agentsandswarms/skills-loader install\n```\n\nThat auto-detects the user's IDE (Claude Code, Claude Desktop, Cursor, Codex, OpenCode, Gemini CLI, Continue.dev) and writes the right MCP config to the right path. Idempotent — safe to re-run. Then ask the user to **restart their IDE**.\n\nTo target a specific IDE: `--ide claude|claude-desktop|cursor|codex|opencode|gemini|continue`. To preview without writing: `--dry-run`.\n\nAfter install + restart, the user's next session will have the `skills-loader` MCP available. Their agent can then call `skill_loader_recommend` at the start of coding tasks and `skill_loader_record_usage` when done.\n\n---\n\n## 👤 Human installing this for yourself?\n\nSame command — works for everyone:\n\n```bash\nnpx @agentsandswarms/skills-loader@latest install\n```\n\nThen restart your IDE. Done.\n\nFor more options (deep links, manual config snippets per IDE, REST API, etc.) see [skls.to](https://skls.to).\n\n---\n\n## What you get after install\n\nSkills Loader is a hosted MCP server at `https://skills.agentsandswarms.ai/mcp`. Once connected, your IDE's agent gets these tools:\n\n- **`skill_loader_recommend`** — call at the start of coding tasks; returns relevant skills resolved to a context block\n- **`skill_loader_record_usage`** — call when done; feeds the effectiveness ranking\n- **`skill_loader_resolve`** — explicitly load a known skill by ID\n- **`skill_loader_catalog`** — browse all skills\n- **`skill_loader_effectiveness`** — see effectiveness rankings\n- **`skill_loader_provenance`** — full audit trail for any skill (source repo, commit, security-review history)\n\nPlus several others. Full tool list at [skls.to/security](https://skls.to/security).\n\nThe catalog is 2,000+ community skills, each reviewed by an 8-model security panel (7-of-8 supermajority required for \"clean\" status). See [skls.to/security](https://skls.to/security) for the threat model and review process.\n\n---\n\n## SDK usage (advanced)\n\nIf you want direct API access from TypeScript code instead of MCP:\n\n```typescript\nimport { SkillsLoaderClient } from '@agentsandswarms/skills-loader';\n\nconst client = new SkillsLoaderClient({\n  apiKey: process.env.SKILLS_API_KEY!, // required — production rejects unauthenticated /api/skills/*\n});\n\n// Get skill recommendations for a task\nconst recs = await client.recommend({\n  workType: 'dev',\n  taskText: 'add authentication to a Next.js app with Prisma',\n  projectContext: { languages: ['typescript'], frameworks: ['next.js'] },\n});\n\n// Resolve skills into a Claude Code prompt\nconst resolved = await client.resolve({\n  skillIds: recs.discoveredSkills.map(s => s.skillId),\n  format: 'claude-code',\n});\n\n// Record what worked\nawait client.recordUsage({\n  skillId: 'prompt:qa-backend',\n  success: true,\n  context: 'unit test writing',\n  durationMs: 1200,\n});\n\n// Check effectiveness rankings\nconst ranking = await client.ranking({ scope: 'tenant', limit: 10 });\n```\n\n### `new SkillsLoaderClient(config)`\n\n| Option | Type | Default | Description |\n|--------|------|---------|-------------|\n| `apiKey` | `string` | **required** | API key (`SKILLS_API_KEY`). Sent as `Authorization: Bearer …` on every `/api/skills/*` request. |\n| `baseUrl` | `string` | `https://skills.agentsandswarms.ai` | API base URL |\n\nAll SDK methods call `/api/skills/*`, which is protected by API key authentication in production. Requests without a valid Bearer token receive **401**. Obtain a key from [skls.to](https://skls.to) (or your deployment's `SKILLS_API_KEY` / `SKILLS_API_KEYS` config).\n\nFor anonymous, rate-limited access, use the public HTTP API at `/api/public/*` (not covered by this client). When running `skills-loader-service` locally with `NODE_ENV` not set to `production` and no API keys configured, the server allows open access for development only.\n\n### Methods\n\n| Method | Description |\n|--------|-------------|\n| `recommend({ workType, taskText?, projectContext? })` | Get skill recommendations for a task |\n| `resolve({ skillIds?, profileName?, format? })` | Resolve skills into assembled content |\n| `listProfiles()` / `getProfile(name)` | Browse available profiles |\n| `catalog()` / `getSkill(type, name)` | Browse the full skill catalog |\n| `recordUsage({ skillId, success, context?, durationMs? })` | Record a skill usage outcome |\n| `getEffectiveness(type, name)` / `ranking({ scope?, limit? })` | Effectiveness data |\n| `health()` | Service health check |\n\n### Work types\n\n`dev` | `qa` | `grooming` | `monitoring` | `review` | `iterator`\n\n### Output formats\n\n`claude-code` | `cursor-rules` | `codex` | `json` | `markdown`\n\n---\n\n## The feedback loop\n\n```\nrecommend() → agent uses skills → recordUsage() → ranking improves\n     ↑                                                  │\n     └────────── next session uses better data ─────────┘\n```\n\nSkills Loader pairs naturally with [AIS memory](https://www.npmjs.com/package/aismemory) for a closed loop where agents genuinely improve over time across sessions.\n\n---\n\n## Links\n\n- **Site:** [skls.to](https://skls.to) — playground, security explainer, full install docs\n- **Security review:** [skls.to/security](https://skls.to/security) — threat model, 8-model panel, comparison vs dependency scanners\n- **Terms:** [skls.to/terms](https://skls.to/terms) — usage and AI-training opt-out\n- **Platform:** [agentsandswarms.ai](https://agentsandswarms.ai)\n- **AIS (memory + identity):** [aismemory on npm](https://www.npmjs.com/package/aismemory)\n- **GitHub:** [rudedoggg/Corbot](https://github.com/rudedoggg/Corbot) (`packages/skills-loader-client`)\n\n## License\n\nMIT\n","readmeFilename":"README.md"}