[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-92311":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":15,"stars7d":15,"stars30d":16,"stars90d":15,"forks30d":15,"starsTrendScore":15,"compositeScore":17,"rankGlobal":10,"rankLanguage":10,"license":18,"archived":19,"fork":19,"defaultBranch":20,"hasWiki":21,"hasPages":19,"topics":22,"createdAt":10,"pushedAt":10,"updatedAt":39,"readmeContent":40,"aiSummary":41,"trendingCount":15,"starSnapshotCount":15,"syncStatus":16,"lastSyncTime":42,"discoverSource":43},92311,"Cognitive-Core-Skills","eli-labz\u002FCognitive-Core-Skills","eli-labz","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.","",null,"Python",273,77,270,0,2,45.88,"MIT License",false,"main",true,[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"agent-skills","agentic-ai","ai-agents","ai-safety","artificial-intelligence","benchmarks","cognitive-architecture","json-schema","knowledge-graph","llm","machine-learning","prompt-engineering","schema","slm","taxonomy","world-models","2026-07-22 04:02:05","# Cognitive Core Skills\n\n![Cognitive Core Skills](cognitive-core-skills.jpeg)\n\n[![CI](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCI-taxonomy--ci-blue)](.github\u002Fworkflows\u002Ftaxonomy-ci.yml)\n[![Skills](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fskills-159-success)](Skills\u002Findex.md)\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-MIT-green)](LICENSE)\n[![Pages](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdocs-github%20pages-blueviolet)](.github\u002Fworkflows\u002Fpages-deploy.yml)\n[![Stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Feli-labz\u002FCognitive-Core-Skills?style=social)](https:\u002F\u002Fgithub.com\u002Feli-labz\u002FCognitive-Core-Skills\u002Fstargazers)\n[![Forks](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Feli-labz\u002FCognitive-Core-Skills?style=social)](https:\u002F\u002Fgithub.com\u002Feli-labz\u002FCognitive-Core-Skills\u002Fnetwork\u002Fmembers)\n[![Contributions welcome](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fcontributions-welcome-orange)](CONTRIBUTING.md)\n[![Good first issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Feli-labz\u002FCognitive-Core-Skills\u002Fgood%20first%20issue)](GOOD_FIRST_ISSUE_GUIDE.md)\n\nCognitive 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.\n\nCognitive 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.\n\n## Repository overview\n\nThis repository contains a universal, industry-neutral taxonomy package for:\n\n- LLM capabilities\n- SLM capabilities\n- AI agent capabilities\n- World model capabilities\n- Text-based cognitive skills\n- Human-action cognitive skills\n- Persistent LLM Wiki knowledge operations\n- OKF-style knowledge cataloging operations\n\n## Why star or fork this project\n\n- Practical: ready-to-use taxonomy data, schemas, and validation tests.\n- Operational: includes human-action skills and governance-oriented constructs.\n- Reusable: JSON, YAML, and markdown skill cards for easy integration.\n- Collaborative: contribution templates, roadmap, and CI in place.\n\n## Quickstart\n\n1. Read the taxonomy package docs in `docs\u002Fcognitive-core-skills\u002F`.\n2. Explore machine-readable data in `data\u002F`.\n3. Browse generated skill cards in `Skills\u002Findex.md`.\n4. Run validation locally.\n\n## Current status\n\n- Taxonomy version: `1.0.0`\n- Skill count: `159`\n- Domains covered: `13`\n- Generated skill files in `Skills\u002F`: `159` skill cards plus `Skills\u002Findex.md`\n- CI enabled for taxonomy and benchmark fixture tests\n\n## Capability model differences\n\n| System type | Primary strength | Typical limitation without augmentation |\n|---|---|---|\n| LLM | Broad language understanding, synthesis, reasoning, drafting | Weak continuity and no autonomous bounded action by default |\n| SLM | Low-latency, low-cost, private, constrained inference | Narrower transfer and lower open-domain depth |\n| AI Agent | Goal pursuit across memory, planning, tools, and actions | Requires robust verification, control gates, and oversight |\n| World Model | State and dynamics modeling, simulation, forecasting | Requires grounded observations and updated environment state |\n\n## Key package paths\n\nDocumentation:\n\n- `docs\u002Fcognitive-core-skills\u002FREADME.md`\n- `docs\u002Fcognitive-core-skills\u002Ftaxonomy.md`\n- `docs\u002Fcognitive-core-skills\u002Ftext-based-skills.md`\n- `docs\u002Fcognitive-core-skills\u002Fhuman-action-skills.md`\n- `docs\u002Fcognitive-core-skills\u002Fworld-model-skills.md`\n- `docs\u002Fcognitive-core-skills\u002Fllm-wiki-skills.md`\n- `docs\u002Fcognitive-core-skills\u002Fokf-skills.md`\n- `docs\u002Fcognitive-core-skills\u002Fevaluation-rubric.md`\n- `docs\u002Fcognitive-core-skills\u002Fcognitive-debt-index.md`\n- `docs\u002Fcognitive-core-skills\u002Fglossary.md`\n- `docs\u002Fcognitive-core-skills\u002FCHANGELOG.md`\n\nMachine-readable artifacts:\n\n- `data\u002Fcognitive-core-skills.json`\n- `data\u002Fcognitive-core-skills.yaml`\n- `schemas\u002Fcognitive-core-skill.schema.json`\n- `schemas\u002Fcognitive-core-taxonomy.schema.json`\n\nBenchmarks and examples:\n\n- `benchmarks\u002Frubric-task-traces.json`\n- `examples\u002Fcognitive-core-skill-card.md`\n- `examples\u002Fagent-skill-assessment.md`\n\nGenerated skills directory:\n\n- `Skills\u002Findex.md`\n- `Skills\u002F\u003Cskill_id>.md` (one file per taxonomy skill)\n\nTests and CI:\n\n- `tests\u002Ftest_cognitive_core_taxonomy.py`\n- `tests\u002Ftest_rubric_benchmark_fixtures.py`\n- `.github\u002Fworkflows\u002Ftaxonomy-ci.yml`\n\nCommunity and project health:\n\n- `CONTRIBUTING.md`\n- `GOOD_FIRST_ISSUE_GUIDE.md`\n- `RELEASE_CHECKLIST.md`\n- `ROADMAP.md`\n- `.github\u002FISSUE_TEMPLATE\u002Fbug_report.yml`\n- `.github\u002FISSUE_TEMPLATE\u002Ffeature_request.yml`\n- `.github\u002Fpull_request_template.md`\n\n## Recent taxonomy update\n\nAdded human-action skill:\n\n- `ha_consequence_understanding` - Human-Action Consequence Understanding\n\nPurpose: understand likely downstream operational, compliance, and workflow consequences before executing human-action tokens.\n\nAdded planning skill:\n\n- `plan_long_horizon_skill` - Long-Horizon Skill\n\nPurpose: maintain coherent long-horizon execution across milestones, dependencies, and replanning triggers.\n\n## Run validation locally\n\n```powershell\npy -m pytest tests\u002Ftest_cognitive_core_taxonomy.py tests\u002Ftest_rubric_benchmark_fixtures.py -q\n```\n\n## How to add a new skill\n\n1. Add the skill card to `data\u002Fcognitive-core-skills.json`.\n2. Mirror the same skill in `data\u002Fcognitive-core-skills.yaml`.\n3. Ensure unique `id` and unique `name`.\n4. Add valid `related_skills` references.\n5. Regenerate the `Skills\u002F` folder markdown cards from taxonomy data.\n6. Update `docs\u002Fcognitive-core-skills\u002FCHANGELOG.md` under `Unreleased`.\n7. Run the local pytest command above.\n\n## Regenerate skill markdown files\n\nWhen taxonomy data changes, regenerate skill card markdown files in `Skills\u002F` so they remain synchronized with `data\u002Fcognitive-core-skills.json`.\n\nExpected result:\n\n- one markdown file per skill id\n- one generated index file at `Skills\u002Findex.md`\n\nRun:\n\n```powershell\npy scripts\u002Fgenerate_skills.py\n```\n\n## Attribution and license boundaries\n\nThis taxonomy package adapts high-level architecture\u002Fdocumentation patterns from:\n\n- `third-party\u002Fautoresearch-master`\n- `third-party\u002Fknowledge-catalog-main`\n- `third-party\u002Fknowledge-catalog-main\u002Fokf`\n\nNo third-party source code is copied into taxonomy artifacts.\n\n## Star history\n\nIf this taxonomy is useful to you, a star helps others discover it and tells us which direction to invest in next.\n\n[![Star History Chart](https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=eli-labz\u002FCognitive-Core-Skills&type=Date)](https:\u002F\u002Fstar-history.com\u002F#eli-labz\u002FCognitive-Core-Skills&Date)\n\n## Support this project\n\n- Star the repo to bookmark it and help with discoverability.\n- Fork the repo if you want to adapt the taxonomy, schemas, or skill cards for your own agent stack.\n- 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.\n- Share a \"Show and tell\" write-up if you build something on top of this taxonomy once Discussions are enabled.\n","该项目构建了一个通用、跨行业的认知核心技能分类体系，系统定义了AI系统（包括大语言模型、小型语言模型、AI智能体和世界模型）所需的八大基础认知能力：感知、记忆、推理、规划、行动、验证、学习与治理。项目提供结构化Schema（JSON\u002FYAML）、159张标准化技能卡片、可复用的基准测试集及持续集成验证机制，所有数据以机器可读格式组织，支持快速集成与能力对齐分析。适用于AI智能体架构设计、模型能力评估、安全治理框架构建及认知架构研究等场景。","2026-07-08 04:30:04","CREATED_QUERY"]