Skip to content
Back to search

Cognitive-Core-Skills

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/eli-labz--cognitive-core-skills/badge.svg)](/listings/eli-labz--cognitive-core-skills)

HTML

<a href="/listings/eli-labz--cognitive-core-skills"><img src="/api/listings/eli-labz--cognitive-core-skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Read the taxonomy package docs in `docs/cognitive-core-skills/`. 2. Explore machine-readable data in `data/`. 3. Browse generated skill cards in `Skills/index.md`. 4. Run validation locally.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 178 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Cognitive Core Skills
  2. ![Cognitive Core Skills](cognitive-core-skills.jpeg)
  3. [![CI](https://img.shields.io/badge/CI-taxonomy--ci-blue)](.github/workflows/taxonomy-ci.yml)
  4. [![Skills](https://img.shields.io/badge/skills-159-success)](Skills/index.md)
  5. [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
  6. [![Pages](https://img.shields.io/badge/docs-github%20pages-blueviolet)](.github/workflows/pages-deploy.yml)
  7. [![Stars](https://img.shields.io/github/stars/eli-labz/Cognitive-Core-Skills?style=social)](https://github.com/eli-labz/Cognitive-Core-Skills/stargazers)
  8. [![Forks](https://img.shields.io/github/forks/eli-labz/Cognitive-Core-Skills?style=social)](https://github.com/eli-labz/Cognitive-Core-Skills/network/members)
  9. [![Contributions welcome](https://img.shields.io/badge/contributions-welcome-orange)](CONTRIBUTING.md)
  10. [![Good first issues](https://img.shields.io/github/issues/eli-labz/Cognitive-Core-Skills/good%20first%20issue)](GOOD_FIRST_ISSUE_GUIDE.md)
  11. Cognitive core skills are the mental operating capabilities an LLM or AI Agent needs to move from chat response to useful digital co-worker. An LLM predicts and generates language. An AI Agent wraps that LLM with memory, planning, tools, integrations, verification, and action control so it can pursue goals inside real workflows.
  12. Cognitive core skills are the agent operating brain: perception to know the situation, memory to preserve continuity, reasoning to judge, planning to sequence work, action selection to execute, verification to confirm progress, learning to improve, and governance to stay safe.
  13. ## Repository overview
  14. This repository contains a universal, industry-neutral taxonomy package for:
  15. - LLM capabilities
  16. - SLM capabilities
  17. - AI agent capabilities
  18. - World model capabilities
  19. - Text-based cognitive skills
  20. - Human-action cognitive skills
  21. - Persistent LLM Wiki knowledge operations
  22. - OKF-style knowledge cataloging operations
  23. ## Why star or fork this project
  24. - Practical: ready-to-use taxonomy data, schemas, and validation tests.
  25. - Operational: includes human-action skills and governance-oriented constructs.
  26. - Reusable: JSON, YAML, and markdown skill cards for easy integration.
  27. - Collaborative: contribution templates, roadmap, and CI in place.
  28. ## Quickstart
  29. 1. Read the taxonomy package docs in `docs/cognitive-core-skills/`.
  30. 2. Explore machine-readable data in `data/`.
  31. 3. Browse generated skill cards in `Skills/index.md`.
  32. 4. Run validation locally.
  33. ## Current status
  34. - Taxonomy version: `1.0.0`
  35. - Skill count: `159`
  36. - Domains covered: `13`
  37. - Generated skill files in `Skills/`: `159` skill cards plus `Skills/index.md`
  38. - CI enabled for taxonomy and benchmark fixture tests
  39. ## Capability model differences
  40. | System type | Primary strength | Typical limitation without augmentation |
  41. |---|---|---|
  42. | LLM | Broad language understanding, synthesis, reasoning, drafting | Weak continuity and no autonomous bounded action by default |
  43. | SLM | Low-latency, low-cost, private, constrained inference | Narrower transfer and lower open-domain depth |
  44. | AI Agent | Goal pursuit across memory, planning, tools, and actions | Requires robust verification, control gates, and oversight |
  45. | World Model | State and dynamics modeling, simulation, forecasting | Requires grounded observations and updated environment state |
  46. ## Key package paths
  47. Documentation:
  48. - `docs/cognitive-core-skills/README.md`
  49. - `docs/cognitive-core-skills/taxonomy.md`
  50. - `docs/cognitive-core-skills/text-based-skills.md`
  51. - `docs/cognitive-core-skills/human-action-skills.md`
  52. - `docs/cognitive-core-skills/world-model-skills.md`
  53. - `docs/cognitive-core-skills/llm-wiki-skills.md`
  54. - `docs/cognitive-core-skills/okf-skills.md`
  55. - `docs/cognitive-core-skills/evaluation-rubric.md`
  56. - `docs/cognitive-core-skills/cognitive-debt-index.md`
  57. - `docs/cognitive-core-skills/glossary.md`
  58. - `docs/cognitive-core-skills/CHANGELOG.md`
  59. Machine-readable artifacts:
  60. - `data/cognitive-core-skills.json`
  61. - `data/cognitive-core-skills.yaml`
  62. - `schemas/cognitive-core-skill.schema.json`
  63. - `schemas/cognitive-core-taxonomy.schema.json`
  64. Benchmarks and examples:
  65. - `benchmarks/rubric-task-traces.json`
  66. - `examples/cognitive-core-skill-card.md`
  67. - `examples/agent-skill-assessment.md`
  68. Generated skills directory:
  69. - `Skills/index.md`
  70. - `Skills/<skill_id>.md` (one file per taxonomy skill)
  71. Tests and CI:
  72. - `tests/test_cognitive_core_taxonomy.py`
  73. - `tests/test_rubric_benchmark_fixtures.py`
  74. - `.github/workflows/taxonomy-ci.yml`
  75. Community and project health:
  76. - `CONTRIBUTING.md`
  77. - `GOOD_FIRST_ISSUE_GUIDE.md`
  78. - `RELEASE_CHECKLIST.md`
  79. - `ROADMAP.md`
  80. - `.github/ISSUE_TEMPLATE/bug_report.yml`
  81. - `.github/ISSUE_TEMPLATE/feature_request.yml`
  82. - `.github/pull_request_template.md`
  83. ## Recent taxonomy update
  84. Added human-action skill:
  85. - `ha_consequence_understanding` - Human-Action Consequence Understanding
  86. Purpose: understand likely downstream operational, compliance, and workflow consequences before executing human-action tokens.
  87. Added planning skill:
  88. - `plan_long_horizon_skill` - Long-Horizon Skill
  89. Purpose: maintain coherent long-horizon execution across milestones, dependencies, and replanning triggers.
  90. ## Run validation locally
  91. ```powershell
  92. py -m pytest tests/test_cognitive_core_taxonomy.py tests/test_rubric_benchmark_fixtures.py -q
  93. ```
  94. ## How to add a new skill
  95. 1. Add the skill card to `data/cognitive-core-skills.json`.
  96. 2. Mirror the same skill in `data/cognitive-core-skills.yaml`.
  97. 3. Ensure unique `id` and unique `name`.
  98. 4. Add valid `related_skills` references.
  99. 5. Regenerate the `Skills/` folder markdown cards from taxonomy data.
  100. 6. Update `docs/cognitive-core-skills/CHANGELOG.md` under `Unreleased`.
  101. 7. Run the local pytest command above.
  102. ## Regenerate skill markdown files
  103. When taxonomy data changes, regenerate skill card markdown files in `Skills/` so they remain synchronized with `data/cognitive-core-skills.json`.
  104. Expected result:
  105. - one markdown file per skill id
  106. - one generated index file at `Skills/index.md`
  107. Run:
  108. ```powershell
  109. py scripts/generate_skills.py
  110. ```
  111. ## Attribution and license boundaries
  112. This taxonomy package adapts high-level architecture/documentation patterns from:
  113. - `third-party/autoresearch-master`
  114. - `third-party/knowledge-catalog-main`
  115. - `third-party/knowledge-catalog-main/okf`
  116. No third-party source code is copied into taxonomy artifacts.
  117. ## Star history
  118. If this taxonomy is useful to you, a star helps others discover it and tells us which direction to invest in next.
  119. [![Star History Chart](https://api.star-history.com/svg?repos=eli-labz/Cognitive-Core-Skills&type=Date)](https://star-history.com/#eli-labz/Cognitive-Core-Skills&Date)
  120. ## Support this project
  121. - Star the repo to bookmark it and help with discoverability.
  122. - Fork the repo if you want to adapt the taxonomy, schemas, or skill cards for your own agent stack.
  123. - Open an issue for a missing skill, a schema question, or a benchmark idea. See `GOOD_FIRST_ISSUE_GUIDE.md` for beginner-friendly entry points.
  124. - Share a "Show and tell" write-up if you build something on top of this taxonomy once Discussions are enabled.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.