{"id":51708863,"url":"https://github.com/ellmos-ai/skills","last_synced_at":"2026-07-24T01:03:48.680Z","repository":{"id":349879390,"uuid":"1179885063","full_name":"ellmos-ai/skills","owner":"ellmos-ai","description":"Portable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows","archived":false,"fork":false,"pushed_at":"2026-07-11T16:13:06.000Z","size":705,"stargazers_count":1,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"master","last_synced_at":"2026-07-11T18:07:30.764Z","etag":null,"topics":["agent-framework","agent-skills","ai-skills","anthropic","automation","bach","claude-code","claude-skills","codex-skills","llm","llm-agents","llm-tools","local-first","open-source","portable-skills","python","skill-library","skill-md","sqlite"],"latest_commit_sha":null,"homepage":"https://github.com/ellmos-ai/skills#readme","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ellmos-ai.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null},"funding":{"custom":["https://paypal.me/lukasgeiger2507"]}},"created_at":"2026-03-12T13:35:04.000Z","updated_at":"2026-07-11T16:13:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/ellmos-ai/skills","commit_stats":null,"previous_names":["ellmos-ai/skills"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ellmos-ai/skills","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellmos-ai%2Fskills","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellmos-ai%2Fskills/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellmos-ai%2Fskills/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellmos-ai%2Fskills/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ellmos-ai","download_url":"https://codeload.github.com/ellmos-ai/skills/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ellmos-ai%2Fskills/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35822076,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-07-23T02:00:06.683Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-framework","agent-skills","ai-skills","anthropic","automation","bach","claude-code","claude-skills","codex-skills","llm","llm-agents","llm-tools","local-first","open-source","portable-skills","python","skill-library","skill-md","sqlite"],"created_at":"2026-07-16T19:00:21.321Z","updated_at":"2026-07-24T01:03:48.669Z","avatar_url":"https://github.com/ellmos-ai.png","language":"Python","funding_links":["https://paypal.me/lukasgeiger2507"],"categories":["Source Catalog"],"sub_categories":[],"readme":"\u003cimg src=\"assets/banner_v2.svg\" width=\"100%\" alt=\"ellmos skills Banner\"\u003e\n\n# ellmos skills\n\n**[🇩🇪 German version](README_de.md)** · **🇬🇧 English** · [Machine-readable context](llms.txt)\n\n\u003e Portable AI skill library for Claude Code-style `SKILL.md` workflows, Codex-compatible agent setups, BACH, and other local-first LLM agent runtimes.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green)](LICENSE)\n\n**Quick links:** [Start Here](#start-here) · [Featured Skills](#featured-skills) · [Skills](skills/) · [Skills Map](SKILLS-MAP.md) · [Conventions](docs/CONVENTIONS.md) · [Changelog](CHANGELOG.md)\n\nThis repository is the reusable skill catalog of the ellmos ecosystem. It contains standalone process skills, development workflows, research helpers, therapy-oriented methods, infrastructure playbooks, and utility tools in an Anthropic-compatible `SKILL.md` format. Each skill carries its own metadata directly in YAML frontmatter, so runtimes can inspect provenance, compatibility, and dependencies without a central registry.\n\n## Start Here\n\n| Need | File or command |\n|---|---|\n| Browse all public skills | [`skills/`](skills/) |\n| See a tree map of every tracked skill | [`SKILLS-MAP.md`](SKILLS-MAP.md) |\n| Understand the `SKILL.md` schema | [`docs/CONVENTIONS.md`](docs/CONVENTIONS.md) |\n| Machine-readable catalog index | [`registry/components.json`](registry/components.json) |\n| Browse by category | [`skills/`](skills/) (one subfolder per category) |\n| Use a skill | Copy `skills/\u003ccategory\u003e/\u003cname\u003e/` into your agent's skills directory (e.g. `~/.claude/skills/`) |\n| Review public changes | [`CHANGELOG.md`](CHANGELOG.md) |\n| Give crawlers and LLM agents a compact map | [`llms.txt`](llms.txt) |\n\n## Catalog Snapshot\n\nThe current public catalog contains 77 tracked runtime skills:\n\n| Category | Count | Focus |\n|---|---:|---|\n| \u003cimg src=\"assets/icons/cat-assist.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `assist` | 9 | Personal-assistant skills: weather, routing, location search, calendar, news digest, transcription, medical self-tracking, dossier scaffolding, dev assistant |\n| \u003cimg src=\"assets/icons/cat-dev.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `dev` | 13 | Development protocols, debugging, bug sweeps, pipeline renovation, migration, documentation, plugin systems, repository publication |\n| \u003cimg src=\"assets/icons/cat-education.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `education` | 4 | Academic planning, source-based learning, exam preparation, and a support-worksheet generator pointer skill |\n| \u003cimg src=\"assets/icons/cat-game-dev.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `game-dev` | 5 | Blender, Roblox, Rojo, Studio, asset safety, and game-design workflows |\n| \u003cimg src=\"assets/icons/cat-infrastructure.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `infrastructure` | 6 | Portable AI setup, skill landscape management, MCP config sync between agent apps |\n| \u003cimg src=\"assets/icons/cat-production.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `production` | 1 | Text production router: general texts, narrative stories, PR with a local LaTeX press-release compiler |\n| \u003cimg src=\"assets/icons/cat-research.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `research` | 1 | Research-agent workflow support |\n| \u003cimg src=\"assets/icons/cat-therapy.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `therapy` | 19 | German-language psychoeducation and counseling method playbooks |\n| \u003cimg src=\"assets/icons/cat-utilities.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `utilities` | 18 | Batch operations, thinking frameworks, decision briefings, document chunking, encoding repair, video transcripts, private-mail drafting, job-application support, German-law and German-tax first-look pointer skills |\n| \u003cimg src=\"assets/icons/cat-web.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e `web` | 1 | Web-reading protocol support |\n\n## Featured Skills\n\nSome skills are especially useful as entry points because they coordinate other tools, prevent messy agent workflows, or turn local procedures into repeatable playbooks:\n\n| Skill | Why it stands out |\n|---|---|\n| \u003cimg src=\"assets/icons/skill-explorer.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`skill-explorer`](skills/infrastructure/skill-explorer/SKILL.md) | Meta-skill for managing the skill landscape: audits existing skills, clusters them into families, researches external skills/plugins, and installs only after safety review and explicit approval. |\n| \u003cimg src=\"assets/icons/model-strategy.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`model-strategy`](skills/dev/model-strategy/SKILL.md) | Multi-model routing for Claude, Codex, Gemini, and Ollama with score-based selection, delegation paths, escalation triggers, and cost/quality tradeoffs. |\n| \u003cimg src=\"assets/icons/pipeline-optimizer.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`pipeline-optimizer`](skills/dev/pipeline-optimizer/SKILL.md) | Six-step renovation protocol for existing project folders, documentation systems, and software stacks; designed to avoid duplicate standards and broken workflows. |\n| \u003cimg src=\"assets/icons/github-repo-care.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`github-repo-care`](skills/dev/github-repo-care/SKILL.md) | Publication and maintenance gate for GitHub repos: local rules, locks, `.gitignore`, privacy checks, README/i18n, releases, and repository metadata. |\n| \u003cimg src=\"assets/icons/mcp-config-sync.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`mcp-config-sync`](skills/infrastructure/mcp-config-sync/SKILL.md) | Synchronizes MCP server configuration between Claude Code and Claude Desktop with a shared master file and Windows/macOS helper scripts. |\n| \u003cimg src=\"assets/icons/video-transcriber.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`video-transcriber`](skills/utilities/video-transcriber/SKILL.md) | Extracts video subtitles/transcripts plus metadata (supports YouTube sources) into Markdown, JSON, or plain text so video analysis starts from source-backed text. |\n| \u003cimg src=\"assets/icons/rbx-studio.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`rbx-studio`](skills/game-dev/rbx-studio/SKILL.md) | Roblox Studio operation: Explorer/Play-Test workflow, Rojo scene-vs-code hookup, AI control of Studio via MCP, and a mandatory malware scan for Creator Store assets. |\n| \u003cimg src=\"assets/icons/decision-briefing.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`decision-briefing`](skills/utilities/decision-briefing/SKILL.md) | Turns many open decisions into a numbered A/B/C/D briefing with recommendations, accepts batch replies, and records the chosen outcomes. |\n| \u003cimg src=\"assets/icons/bugsweep.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`bugsweep`](skills/dev/bugsweep/SKILL.md) | Systematic bug-sweep protocol with a codebase-scaled target count, doubling escalation, area tracking, and completion verification -- turns ad hoc bug hunting into a repeatable, measurable pass. |\n| \u003cimg src=\"assets/icons/plugin-system.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`plugin-system`](skills/dev/plugin-system/SKILL.md) | Generic auto-discovery plugin system for Python applications: zero dependencies (stdlib only), validation, and fault tolerance for turning your own scripts into a pluggable architecture. |\n| \u003cimg src=\"assets/icons/bilingual-doc-sync.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`bilingual-doc-sync`](skills/utilities/bilingual-doc-sync/SKILL.md) | Keeps parallel-language documents (papers, READMEs, `SKILL.md`/`SKILL.en.md` pairs) in sync: detects missing translations and section drift, plus an expansion audit for whether a document deserves further languages. |\n| \u003cimg src=\"assets/icons/trampelpfadanalyse.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`trampelpfadanalyse`](skills/dev/trampelpfadanalyse/SKILL.md) | Empirical baseline-intervention-retest method for checking whether an agent convention or README rule is actually visible and followed, using isolated sandbox subagents to measure whether a doc change changed behavior. |\n| \u003cimg src=\"assets/icons/law-checker.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`law-checker`](skills/utilities/law-checker/SKILL.md) | Pointer skill to the standalone `ellmos-ai/law-checker` module: source-grounded AI first-look legal assessments for German law with a statute registry and a statute-embodiment agent -- AI orientation only, not a substitute for a lawyer. |\n| \u003cimg src=\"assets/icons/steuer-assistent.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`steuer-assistent`](skills/utilities/steuer-assistent/SKILL.md) | Pointer skill to the standalone `ellmos-ai/steuer-assistent` module: an offline-first local worksheet for German employee income-related expenses (Werbungskosten) -- not tax advice, no tax-return filing. |\n| \u003cimg src=\"assets/icons/worksheet-generator.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`worksheet-generator`](skills/education/worksheet-generator/SKILL.md) | Pointer skill to the standalone `ellmos-ai/worksheet-generator` module: generates individualized worksheets from a support goal, level, and age for educational/therapeutic professionals, with bring-your-own ICF references -- a material generator, not a therapy program. |\n| \u003cimg src=\"assets/icons/research-agent.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`research-agent`](skills/research/research-agent/SKILL.md) | Self-contained scientific literature workflow around PubMed and arXiv (pure Python stdlib) -- turns ad hoc paper hunting into a repeatable, source-backed research pass, fully portable without the ellmos ecosystem. |\n| \u003cimg src=\"assets/icons/agent-config-sync.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`agent-config-sync`](skills/infrastructure/agent-config-sync/SKILL.md) | Synchronizes MCP servers and skills across multiple agent apps from one registry with config templates and cache -- addresses the real painpoint of keeping several agent runtimes configured consistently. |\n| \u003cimg src=\"assets/icons/dev-soft-agent.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`dev-soft-agent`](skills/dev/dev-soft-agent/SKILL.md) | Standalone development-automation pipeline (code analysis, task engine, policies, prompt templates) in zero-dependency Python -- a complete dev-agent workflow without external services. |\n| \u003cimg src=\"assets/icons/llm-text-hygiene.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`llm-text-hygiene`](skills/utilities/llm-text-hygiene/SKILL.md) | Removes AI traces and chat residue from finished texts and handles AI-disclosure levels -- keeps published documents clean of LLM artifacts. |\n| \u003cimg src=\"assets/icons/idea-mining.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`idea-mining`](skills/utilities/idea-mining/SKILL.md) | Distinctive multi-technique method for mining ideas out of stuck problems -- the structured alternative to free-form brainstorming when a project has hit a wall. |\n| \u003cimg src=\"assets/icons/skill-extractor.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`skill-extractor`](skills/infrastructure/skill-extractor/SKILL.md) | Extracts a reusable skill from a chat history (current session or transcript files) -- turns what just worked into a portable playbook, or improves an existing skill from the evidence. |\n| \u003cimg src=\"assets/icons/workflow-extract.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`workflow-extract`](skills/infrastructure/workflow-extract/SKILL.md) | Builds an automation from a chat history or from existing automation prompts of another agent system -- conversations become repeatable workflows. |\n| \u003cimg src=\"assets/icons/ai-portable-setup.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`ai-portable-setup`](skills/infrastructure/ai-portable-setup/SKILL.md) | Creates a portable offline AI working environment on a USB stick or any drive: local LLM models and a RAG pipeline, no cloud required. |\n| \u003cimg src=\"assets/icons/bewerbungsexperte.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`bewerbungsexperte`](skills/utilities/bewerbungsexperte/SKILL.md) | End-to-end job-application support: job-ad analysis, CV/LinkedIn optimization, cover letters, plus a database/folder-driven ASCII CV generator (German-language focus). |\n| \u003cimg src=\"assets/icons/therapy-collection.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`therapy/` collection](skills/therapy/) | The 19-skill therapy family (flagships: [`cognitive-restructuring`](skills/therapy/cognitive-restructuring/SKILL.md), [`motivational-interviewing`](skills/therapy/motivational-interviewing/SKILL.md)) -- evidence-cited, bilingual, ethics-gated psychoeducation and counseling method playbooks; the deepest coherent block of the library. |\n\n## Education Skills\n\nThree institution-neutral skills for academic study. Placeholders (`\u003cINSTITUTION\u003e`, `\u003cLMS\u003e`, `\u003cMODULE_PREFIX\u003e`, etc.) are resolved to the concrete context on first use. All three skills are available in German (base) and English; ES, JA, RU, ZH are planned for Stage 2.\n\n| Skill | What it does |\n|---|---|\n| \u003cimg src=\"assets/icons/academic-study-control.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`academic-study-control`](skills/education/academic-study-control/SKILL.md) | Semester planning, deadline tracking, exam registration, re-enrollment, mail/portal checks, and calendar reminders with source verification and privacy guardrails. |\n| \u003cimg src=\"assets/icons/academic-study-learn.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`academic-study-learn`](skills/education/academic-study-learn/SKILL.md) | Five-phase source-based learning cycle: clarify objective → extract key ideas → build glossary → transfer/apply → retrieval practice with gap tracking. |\n| \u003cimg src=\"assets/icons/academic-study-test.svg\" width=\"20\" height=\"20\" alt=\"\"\u003e [`academic-study-test`](skills/education/academic-study-test/SKILL.md) | Five test modes (quick test, exam block, oral exam, assignment training, error diagnosis) with a rubric-based assessment system and a strict ethics boundary against live-exam support. |\n\n## Repository Structure\n\n```text\nskills/\n  \u003ccategory\u003e/\n    \u003cskill-name\u003e/\n      SKILL.md              # Definition, frontmatter, usage workflow\n      scripts/              # Optional executable helpers\n      references/           # Optional supporting documents\n  _templates/               # Templates for new skills\ndocs/\n  CONVENTIONS.md            # Frontmatter specification\nregistry/components.json    # Machine-readable catalog index\nllms.txt                    # Compact project map for LLM crawlers\n```\n\n## Skill Metadata\n\nEvery `SKILL.md` declares whether it works standalone, whether it is compatible with BACH, and where it came from:\n\n```yaml\nstandalone: true\nbach_compatible: true\nbach_origin: true\nprovenance:\n  origin: \"bach\"\n  origin_path: \"system/skills/therapie/\"\n  origin_version: \"1.0.0\"\n  last_sync_from_origin: \"2026-03-12\"\n  last_sync_to_origin: null\n  local_changes_since_sync: false\n```\n\nSupported skill types are `skill`, `agent`, `expert`, `service`, `protocol`, and `tool`.\n\n## Validation\n\nPull requests and pushes that change a public `SKILL.md` run the complete static\nS-test gate. Run the same tracked-skill check locally with:\n\n```bash\npython testing/skill_tester.py batch --type static --ci\n```\n\nWith [pre-commit](https://pre-commit.com/) installed, enable the repository hook\nonce with `pre-commit install`. It applies the same gate only to changed\n`SKILL.md` files before a commit.\n\n## Search Context\n\nUse this repository when searching for:\n\n- `ellmos skills`\n- `ellmos-ai/skills`\n- `agent skill library`\n- `SKILL.md catalog`\n- `portable AI skills`\n- `Claude Code SKILL.md library`\n- `Codex skills library`\n- `Claude Code and Codex skills`\n- `local-first LLM agent skills`\n- `BACH skill catalog`\n- `Anthropic-compatible skills`\n\nThe name is intentionally generic, so use the canonical repository string `ellmos-ai/skills` when linking or indexing this project. It is a reusable skill catalog, not an MCP server, hosted SaaS marketplace, prompt pack, or private skill installer.\n\n## Related ellmos Projects\n\n| Project | Role |\n|---|---|\n| [BACH](https://github.com/ellmos-ai/bach) | Full text-based LLM operating system |\n| [Rinnsal](https://github.com/ellmos-ai/rinnsal) | Lightweight local-first LLM agent infrastructure |\n| [USMC](https://github.com/ellmos-ai/usmc) | Shared memory primitive for agent systems |\n| [Gardener](https://github.com/ellmos-ai/gardener) | Database-based operating-system counterpart |\n| [MarbleRun / llmauto](https://github.com/ellmos-ai/MarbleRun) | LLM chain-execution framework |\n\n## License\n\nMIT License. See [LICENSE](LICENSE).\n\n## Liability\n\nThis project is an unpaid open-source donation. Liability is limited to intent and gross negligence under Section 521 of the German Civil Code. Use at your own risk. No warranty, maintenance guarantee, availability guarantee, or fitness-for-purpose guarantee is provided.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fellmos-ai%2Fskills","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fellmos-ai%2Fskills","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fellmos-ai%2Fskills/lists"}