{"_id":"@daviesayo/rocket-skills","_rev":"2-67b5e19e811bd6ab72b7e29841b7d4f2","name":"@daviesayo/rocket-skills","dist-tags":{"latest":"1.0.1"},"versions":{"1.0.0":{"name":"@daviesayo/rocket-skills","version":"1.0.0","keywords":["cursor","agents","skills","ai"],"license":"MIT","_id":"@daviesayo/rocket-skills@1.0.0","maintainers":[{"name":"daviesayo","email":"dadaviesayo@gmail.com"}],"homepage":"https://github.com/daviesayo/rocket-skills#readme","bugs":{"url":"https://github.com/daviesayo/rocket-skills/issues"},"dist":{"shasum":"ad1a96bdc0d5fb1c599cdbbe42563f38abcca048","tarball":"https://registry.npmjs.org/@daviesayo/rocket-skills/-/rocket-skills-1.0.0.tgz","fileCount":11,"integrity":"sha512-2Um4c28Xt5BvFRShZN+hndj12WlP7wMArJxYPm8AewwSF7/DvCRl4kvb1XUl2tUVA5a675PBoRnb4RQFXuecNQ==","signatures":[{"sig":"MEYCIQDBJnjKRdt9KCtYuutNsh0z772DnNv+/UItdf+PYYH+QQIhAI2FpzRVS+8mF+2TyKMor/RAOao4CjgngfDAKPglQn9J","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":63637},"engines":{"node":">=16"},"gitHead":"eb05751e3e7365de480eb2f7ac06ed5e6ecfd94d","scripts":{"postinstall":"node scripts/postinstall.js"},"_npmUser":{"name":"daviesayo","email":"dadaviesayo@gmail.com"},"repository":{"url":"git+https://github.com/daviesayo/rocket-skills.git","type":"git"},"_npmVersion":"11.6.1","description":"Agent skills for Cursor/Agents — installs into ~/.agents/skills","directories":{},"_nodeVersion":"22.14.0","_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/rocket-skills_1.0.0_1773502467877_0.8205832612197388","host":"s3://npm-registry-packages-npm-production"}},"1.0.1":{"name":"@daviesayo/rocket-skills","version":"1.0.1","description":"Agent skills for Cursor/Agents — installs into ~/.agents/skills","bin":{"rocket-skills":"scripts/postinstall.js"},"scripts":{"postinstall":"node scripts/postinstall.js"},"engines":{"node":">=16"},"repository":{"type":"git","url":"git+https://github.com/daviesayo/rocket-skills.git"},"keywords":["cursor","agents","skills","ai"],"license":"MIT","gitHead":"1582881c6cfeba13d99ad9a5e63ab3c8daac78b7","_id":"@daviesayo/rocket-skills@1.0.1","bugs":{"url":"https://github.com/daviesayo/rocket-skills/issues"},"homepage":"https://github.com/daviesayo/rocket-skills#readme","_nodeVersion":"22.14.0","_npmVersion":"11.6.1","dist":{"integrity":"sha512-G4ooUW6Y00NSVGe66xgyp/s137nYUt0LCw30Hfir+iVHIfQbo0dpE9l6URFo7H1+0lofO//fKZbbx0bqOoSkbA==","shasum":"d965b8151c02b4afe55ffef89372152f8c365574","tarball":"https://registry.npmjs.org/@daviesayo/rocket-skills/-/rocket-skills-1.0.1.tgz","fileCount":11,"unpackedSize":63641,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEQCIA6GLx3ZiSbYmDugOLtyNDZe+HWN3bPYfHOMgW6gcRNdAiAW+f4kGNJVsiWeOANgnZ7sYQ6NfkmVfs1RwyrooG6Hqw=="}]},"_npmUser":{"name":"daviesayo","email":"dadaviesayo@gmail.com"},"directories":{},"maintainers":[{"name":"daviesayo","email":"dadaviesayo@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/rocket-skills_1.0.1_1773503380713_0.02616168953135012"},"_hasShrinkwrap":false}},"time":{"created":"2026-03-14T15:34:27.778Z","modified":"2026-03-14T15:49:40.951Z","1.0.0":"2026-03-14T15:34:28.027Z","1.0.1":"2026-03-14T15:49:40.854Z"},"bugs":{"url":"https://github.com/daviesayo/rocket-skills/issues"},"license":"MIT","homepage":"https://github.com/daviesayo/rocket-skills#readme","keywords":["cursor","agents","skills","ai"],"repository":{"type":"git","url":"git+https://github.com/daviesayo/rocket-skills.git"},"description":"Agent skills for Cursor/Agents — installs into ~/.agents/skills","maintainers":[{"name":"daviesayo","email":"dadaviesayo@gmail.com"}],"readme":"# Skills\n\nA repository of custom agent skills following the [Agent Skills](https://agentskills.io) open format. Each skill packages specialised procedural knowledge — structured instructions, templates, and domain context — that any compatible LLM agent can load on demand.\n\nSkills are LLM-agnostic and agent-agnostic. The same skill works across Claude, GPT, Gemini, and any other agent that supports the Agent Skills format (Cursor, Claude Code, Codex, and others).\n\n## Install (for users)\n\nInstall this package to copy all skills into your local agent skills directory:\n\n```bash\nnpm install @daviesayo/rocket-skills\n```\n\nOr install without adding it to a project:\n\n```bash\nnpx @daviesayo/rocket-skills@latest\n```\n\n### What gets installed where\n\nEach skill is copied into **`~/.agents/skills/`** as its own folder. For example, after installing you get:\n\n- `~/.agents/skills/running-consultant-engagements/` — the skill folder and its contents (e.g. `SKILL.md`, `templates/`)\n\nAgents that read skills from `~/.agents/skills/` (e.g. Cursor with the right config) will then see and use these skills automatically.\n\n### Uninstall\n\nRemoving the npm package does **not** remove the copied files from `~/.agents/skills/`. To remove a skill, delete its folder:\n\n```bash\nrm -rf ~/.agents/skills/running-consultant-engagements\n```\n\n(Repeat for any other skill names you want to remove.)\n\n---\n\n## What is a skill?\n\nA skill is a folder containing a `SKILL.md` file. The file has two required pieces: a short YAML frontmatter block (`name` + `description`) and a Markdown body with the actual instructions. When an agent detects that a user request matches a skill's `description`, it reads the full `SKILL.md` into context and follows the workflow inside.\n\nSkills can also bundle supporting files — templates, reference docs, scripts — which the agent loads on demand as needed. This keeps context lean at startup while making richer resources available during execution.\n\nSee the [Agent Skills specification](https://agentskills.io/specification.md) for the full format reference.\n\n## How the skills in this repo were built\n\nSkills here were authored using the TDD-for-documentation methodology from [Superpowers](https://github.com/obra/superpowers), specifically the [`writing-skills`](https://github.com/obra/superpowers/tree/main/skills/writing-skills) skill.\n\nThe process treats skill creation like test-driven development:\n\n1. **RED** — run a baseline scenario with a subagent and document exactly how it fails or goes wrong without the skill\n2. **GREEN** — write the `SKILL.md` addressing those specific failure modes; verify the agent now complies\n3. **REFACTOR** — find remaining loopholes in the agent's reasoning, close them, re-verify\n\nKey authoring principles from that methodology, applied here:\n\n- **Description = triggering conditions only.** The `description` field tells the agent *when* to load the skill, not *what the skill does*. Summarising the workflow in the description creates a shortcut the agent takes instead of reading the full instructions.\n- **One artifact at a time.** Workflows with sequential dependencies enforce explicit review gates — the agent produces one output, waits for approval, then continues.\n- **Red flags over vague guidance.** Each skill includes a concrete list of failure modes and what the correct behaviour is, so the agent has something specific to check against.\n- **Progressive disclosure.** Heavy reference material lives in separate files under `skill/templates/` or `skill/references/`, loaded only when needed rather than bloating the main `SKILL.md`.\n\n## How this repo is organised\n\n```\nskills/\n└── <skill-name>/\n    ├── SKILL.md       ← required; frontmatter + instructions\n    └── ...            ← supporting files (templates/, references/, etc.)\n```\n\nThe `skills/<skill-name>/` folder is the unit of deployment. When users install via npm, a postinstall script copies each such folder into `~/.agents/skills/<skill-name>/` on their machine.\n\n## Available skills\n\n| Skill | Description |\n|-------|-------------|\n| [running-consultant-engagements](skills/running-consultant-engagements/) | Orchestrates a structured consulting engagement workflow — from raw discovery inputs to 7 cross-referenced artifacts, generated one at a time with review gates between each step |\n\n---\n\n## Maintainer\n\n### Adding a new skill\n\n1. Create `skills/<your-skill-name>/` and add a `SKILL.md` at the root of that folder (see the [spec](https://agentskills.io/specification.md) for the required frontmatter format).\n2. Add any supporting files the skill references (e.g. `templates/`, `references/`) inside `skills/<your-skill-name>/`.\n3. Add a row to the “Available skills” table above.\n4. (Optional) Validate with the [skills-ref](https://github.com/agentskills/agentskills/tree/main/skills-ref) tool: `skills-ref validate ./skills/<your-skill-name>/`.\n\nNo changes to `package.json` are needed. The postinstall script copies every directory under `skills/` that contains a `SKILL.md`.\n\n### Publishing to npm\n\n**One-time:** Create an account at [npmjs.com](https://www.npmjs.com/signup) if needed, then from the repo run:\n\n```bash\nnpm login\n```\n\n**Each release:**\n\n1. Bump the version (e.g. `npm version patch`).\n2. Publish:\n   ```bash\n   npm publish\n   ```\n3. Push and push tags:\n   ```bash\n   git push && git push --tags\n   ```\n\nUsers get updates with `npm install @daviesayo/rocket-skills` or `npm update @daviesayo/rocket-skills`. This package is scoped; publish with `npm publish --access public`.\n","readmeFilename":"README.md"}