skill-evolution
Skill Evolution monitors how your skills perform across sessions by analyzing user edits and success metrics, then suggests targeted improvements with confidence scores. Apply changes safely with automatic version snapshots and rollback capability, or use the holdout-promotion gate to validate candidates against a sealed eval set before graduating them.
Skill Evolution tracks usage patterns and success rates to suggest improvements with safe version rollback.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-28
Skill Evolution tracks usage patterns and success rates to suggest improvements with safe version rollback. Skill Evolution monitors how your skills perform across sessions by analyzing user edits and success metrics, then suggests targeted improvements with confidence scores. Apply changes safely with automatic version snapshots and rollback capability, or use the holdout-promotion gate to validate candidates against a sealed eval set before graduating them.
Use it when
- Skill Evolution automatically creates version snapshots of your skills, letting you safely rollback problematic changes.
- Yes.
Verify before relying
Read SKILL.md below before installing (11 files). Open directory: indexed for reading, not audited.
Install
yonatangross/orchestkit/skill-evolution · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How does Skill Evolution track skill performance and usage patterns?
Skill Evolution monitors your skills across sessions by analyzing user edits, success rates, and usage metrics. It captures performance data to identify patterns in how your skills are being used and where they succeed or struggle, giving you visibility into real-world skill behavior.
What versioning and rollback management does Skill Evolution provide?
Skill Evolution automatically creates version snapshots of your skills, letting you safely rollback problematic changes. The version history management feature preserves past iterations so you can revert to earlier versions if a skill update causes issues.
Can Skill Evolution auto-improve skills based on user edits?
Yes. Skill Evolution analyzes edit patterns and confidence scores to generate auto-suggested skill optimizations. You can review these recommendations and apply changes directly, or let the system learn from user edits to propose targeted improvements.
How does Skill Evolution's champion-challenger evaluation work?
Skill Evolution runs champion-challenger testing to validate skill candidates against a sealed baseline eval set. Skills are promoted only if they beat the baseline, ensuring quality gates protect your production skills from degradation.
What improvement recommendations does Skill Evolution provide?
Skill Evolution analyzes edit patterns, confidence scores, and success metrics to surface skill improvement recommendations. It combines usage analytics with performance data to suggest where and how to optimize your skills for better outcomes.
How does Skill Evolution ensure safe skill updates?
Skill Evolution uses confidence scoring, automatic version snapshots, and a holdout-promotion gate to validate candidates before graduation. These safety mechanisms let you apply changes confidently while maintaining rollback capability if needed.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Skill Evolution Manager
Enables skills to automatically improve based on usage patterns, user edits, and success rates. Provides version control with safe rollback capability.
Overview
- Reviewing how skills are performing across sessions
- Identifying patterns in user edits to skill outputs
- Applying learned improvements to skill templates
- Rolling back problematic skill changes
- Tracking skill version history and success
(truncated - see the full file via the links below)
File tree — 11 files
src/skills/skill-evolution/SKILL.md
src/skills/skill-evolution/references/evolution-analysis.md
src/skills/skill-evolution/references/evolution-commands.md
src/skills/skill-evolution/references/holdout-promotion-gate.md
src/skills/skill-evolution/references/storage-patterns.md
src/skills/skill-evolution/references/version-management.md
src/skills/skill-evolution/rules/_sections.md
src/skills/skill-evolution/rules/auto-evolution-triggers.md
src/skills/skill-evolution/rules/confidence-scoring.md
src/skills/skill-evolution/rules/pattern-detection-heuristics.md
src/skills/skill-evolution/test-cases.json
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Track skill usage patterns and success rates to identify improvement opportunities”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
This skill has been split into five specialized sub-skills, each addressing a distinct testing need. Choose testing-unit for isolated logic, testing-e2e for browser automation, testing-integration for cross-boundary APIs and databases, testing-llm for AI evaluation, or testing-perf for load and performance work.
This skill provides templates and guidance for creating Architecture Decision Records—lightweight documents that preserve the reasoning behind major technical choices. It walks you through the Nygard format, covering context, decision, consequences, and alternatives, plus best practices for lifecycle management and team review. Use it when evaluating trade-offs or recording decisions that shape your system's future.
testing-e2e enables you to craft comprehensive end-to-end tests leveraging Playwright's semantic locators and page object model architecture. This skill simplifies test automation by providing structured patterns for reliable, maintainable test suites that scale across complex applications.
This orchestrator skill teaches core game development principles and intelligently directs you to the right sub-skill based on your platform (web, mobile, PC, VR) and project type (2D, 3D, design, multiplayer, art, audio). It covers universal patterns like the game loop, input abstraction, performance budgeting, and collision strategies to ground your work before specializing.
This skill analyzes your project's tech stack and workflow to recommend the best-matching skills, then installs them to a project-relative path only after you confirm. It detects languages, frameworks, build tools, and testing setups to surface relevant skill options, while delegating skill creation to specialized writers.
Master TypeScript development with this skill designed to guide you through building robust, type-safe applications. Leverage modern tooling patterns and industry best practices to write cleaner, more maintainable code. Perfect for developers looking to deepen their TypeScript expertise and apply professional-grade techniques to real-world projects.