{"id":"de65d7a4-46d3-463b-9ba7-7dc04be630cf","slug":"agentlik","kind":"skill","name":"agentlik","summary":"","owner":"swayson","repoUrl":"https://github.com/swayson/agentlik","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":2,"match":null,"fewStars":true,"format":"skill","createdAt":"2026-07-20T03:36:52.000Z","addedAt":"2026-10-21T23:32:57.052Z","logoUrl":"https://avatars.githubusercontent.com/u/1834241?v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["writing"],"tags":[],"runtime":"binary","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-26T00:15:12.021Z","sample":false,"url":"https://conduits.dev/tools/agentlik","language":"","transports":["stdio"],"install":{},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# agentlik\n\nClaude Code skills, grouped into seven packs so each can be enabled independently. 27 skills covering reasoning, foresight, learning, writing, development workflow, local-model delegation, and personal coaching.\n\nEach pack is a Claude Code plugin. You install the packs you want and leave the rest off, so you only pay context for what you use.\n\n## Packs\n\n| Pack | Auto-triggered | Manual only (`/name`) |\n|---|---|---|\n| `reasoning` | causal-reasoning-engine, empirical-schematization, engineering-agent | boi, constructor-schematization, deutsch-explanation, fact-check, luck |\n| `futures` | futures-metacognition | forecast-discipline, foresight-error-correction, position-sizing |\n| `learning` | learn | ELI5, abu-rating, anki-cards, socratic-learn, teach |\n| `writing` | no-ai-slop | write-great-skills |\n| `dev` | docket, simplify | icm-workspace-builder |\n| `local-llm` | gemma4, lfm | — |\n| `personal` | nlp-performance-coaching | wingman |\n\n**Auto-triggered** skills put their description in Claude's context every session, and Claude can invoke them on its own. **Manual only** skills cost nothing until you type `/name` — Claude cannot reach them. See [Skill visibility](#skill-visibility) below.\n\nTwo packs have external requirements: `local-llm` needs a llama.cpp server running, and `dev`'s `docket` skill needs the `docket` CLI installed.\n\n## Install\n\nRequires Claude Code. Both methods below install at user scope, so the packs are available in every project.\n\n### As a marketplace (recommended)\n\n```bash\nclaude plugin marketplace add swayson/agentlik\nclaude plugin install reasoning@agentlik\nclaude plugin install writing@agentlik\n```\n\nInstall only the packs you want. To update later:\n\n```bash\nclaude plugin marketplace update agentlik\nclaude plugin update reasoning@agentlik\n```\n\nNote that `claude plugin install` copies the pack into `~/.claude/plugins/cache/`. Edits you make to a clone will not take effect until you bump the pack's version in `.claude-plugin/plugin.json` and re-run `update`. If you intend to edit the skills, use the method below instead.\n\n### As live-editable clones\n\nThis makes each pack load directly from your clone, so edits apply in the next session with no install or update step.\n\n```bash\ngit clone https://github.com/swayson/agentlik.git\n```\n\nThen link each pack you want into `~/.claude/skills/`. Anything placed there loads automatically as `<name>@skills-dir`.\n\n**macOS / Linux:**\n```bash\nln -s /path/to/agentlik/packs/reasoning ~/.claude/skills/reasoning\n```\n\n**Windows** (PowerShell — `mklink` through Git Bash mangles the paths):\n```powershell\nNew-Item -ItemType Junction -Path \"$HOME/.claude/skills/reasoning\" -Target \"C:/path/to/agentlik/packs/reasoning\"\n```\n\nVerify with `claude plugin list`; each linked pack should report `loaded`.\n\nTo remove a link on Windows, use `[System.IO.Directory]::Delete(\"$HOME/.claude/skills/reasoning\")`. Do **not** use `rm -rf` on a junction — depending on the tool it may follow the link and delete your clone.\n\n## Enabling packs per project\n\nKeep the packs you rarely need switched off globally and turn them on in the repos that want them:\n\n```bash\nclaude plugin disable futures@skills-dir --scope user\ncd ~/some-research-project\nclaude plugin enable futures@skills-dir --scope project\n```\n\nThe second command writes `.claude/settings.json` in that project. Settings precedence is user < project < local < flag < policy, so a project-level `true` overrides a user-level `false`. Use `--scope local` for machine-specific choices you do not want to commit.\n\nCheck what a pack costs before enabling it:\n\n```bash\nclaude plugin details reasoning@agentlik\n```\n\nThis reports always-on tokens (paid every session) and on-invoke tokens (paid each time a skill fires), broken down per skill.\n\n## Skill visibility\n\nA skill with `disable-model-invocation: true` in its frontmatter is hidden from the model: its description is never loaded, and Claude cannot invoke it. You reach it by typing `/name`. Skills that benefit from firing automatically — `simplify` after writing code, `causal-reasoning-engine` on a \"why did this happen\" question — leave the field off and pay the always-on cost.\n\nSet visibility in the SKILL.md itself, not in the `skillOverrides` setting. The frontmatter field travels with the skill and is version-controlled.\n\n## Writing and editing skills\n\n`writing/skills/write-great-skills` documents the conventions these packs follow — invocation choice, the information hierarchy, progressive disclosure, and the failure modes to prune for. Read it before adding a skill. `packs/reasoning/skills/luck` is a worked example of progressive disclosure: a compact `SKILL.md` with four reference files behind context pointers.\n\nTo add a pack, create `packs/<name>/.claude-plugin/plugin.json` and `packs/<name>/skills/<skill>/SKILL.md`, then add the pack to `plugins` in `.claude-plugin/marketplace.json`.\n\n## Other contents\n\n`prompts/` holds standalone prompt files, and `claude-settings/` a reference `settings.json`. Neither is loaded by the plugin system.\n\n## Licence\n\nApache 2.0. See [LICENSE](LICENSE).\n"}