Repository
kayba-ai/agentic-context-engine agent skills
- skills
- 8
- GitHub stars
- 2.6k
GitHub description: “🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai ”
- Stars
- 2,587 (312 forks)
- Licence
- Apache-2.0
- Last push
- Sep 2026
- Created
- Oct 2025
- Homepage
- kayba.ai
- ai-agents
- ai-tools
- context-engineering
- llm
- python
- agent-memory
- agents
- ai
- memory
- agent-learning
- machine-learning
Install all skills
npx skills add kayba-ai/agentic-context-engineAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in kayba-ai/agentic-context-engine, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | End-to-end agent evaluation and improvement pipeline. An agent skill from kayba-ai/agentic-context-engine. | kayba-ai/ | 2.6k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 2 | Fetch pre-computed insights from the Kayba API and build a structured summary. | kayba-ai/ | 2.6k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 3 | Gather domain context about the repository and agent — system prompt, tool definitions, domain docs, and behavior patterns from traces. | kayba-ai/ | 2.6k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 4 | Define metrics from Kayba insights, implement them as Python measurement code, run against traces, and iterate until the metrics are clean and meaningful. | kayba-ai/ | 2.6k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 5 | Organize computed metrics into a tiered evaluation rubric with leading, lagging, and quality indicators. | kayba-ai/ | 2.6k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 6 | Triage each insight into discard/code-fix/prompt-fix and produce a prioritized action plan with specific recommendations. | kayba-ai/ | 2.6k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 7 | Human-In-The-Loop gate that presents the action plan with full context, collects an informed approval/modification/rejection decision, and records the outcome. | kayba-ai/ | 2.6k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
| 8 | Implement the approved fixes from the action plan and log all changes. | kayba-ai/ | 2.6k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 13 days ago |
Questions, answered from the data.
What is the best skill in kayba-ai/agentic-context-engine?
Kayba Pipeline from kayba-ai/agentic-context-engine ranks first of the 8 skills in kayba-ai/agentic-context-engine listed here, with the highest score: its repository has 2.6k GitHub stars, its SKILL.md loads about 1.4k tokens and it passes the automated safety check with no findings. Next come Kayba Stage 1 API Analysis and Kayba Stage 2 Domain Context.
Are the skills in kayba-ai/agentic-context-engine official?
None yet. All 8 skills in kayba-ai/agentic-context-engine listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from kayba-ai/agentic-context-engine?
Run npx skills add kayba-ai/agentic-context-engine in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.