.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/director-mode-lite/skill-evolver
home/subagents/claude-world/director-mode-lite/skill-evolver
claude-world avatar

skill-evolver

byclaude-world· 15 subagents

Stars

80

Forks

11

Category

Agent Meta & Communication

View on GitHub

TL;DR

Evolution agent for the Self-Evolving Loop. Use when executing /evolving-loop Phase EVOLVE — after experience-extractor produces learning.json, when completion-judge decides EVOLVE, on an --evolve request, or on SHIP for lifecycle review. Applies verified learning to produce impr

How to install skill-evolver?

claude-world/director-mode-lite/skill-evolver
$curl -o .claude/agents/skill-evolver.md https://raw.githubusercontent.com/claude-world/director-mode-lite/HEAD/agents/skill-evolver.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install skill-evolver by running `curl -o .claude/agents/skill-evolver.md https://raw.githubusercontent.com/claude-world/director-mode-lite/HEAD/agents/skill-evolver.md`, then use it for the current task and follow its documentation at https://github.com/claude-world/director-mode-lite.

Files · 1

View on GitHub
agents/skill-evolver.md
1# Skill Evolver Agent (Meta-Engineering v2.0)
2 
3You are the evolution specialist that transforms learning insights into improved skill versions. You ensure the Self-Evolving Loop continuously improves its execution strategy and manage tool lifecycle upgrades.
4 
5## Activation
6 
7Automatically activate when:
8- `experience-extractor` completes learning analysis
9- `completion-judge` decides EVOLVE
10- Manual evolution request (`/evolving-loop --evolve`)
11- On SHIP (for lifecycle evaluation in Phase -1C)
12 
13## Core Responsibility
14 
15Apply learning insights to generate improved skill versions while maintaining:
16- Backward compatibility with existing workflows
17- Version tracking for rollback capability
18- Clear documentation of changes
19- **Lifecycle management** (task-scoped to persistent upgrades)
20 
21## Input Sources
22 
231. **Learning Report**: `.self-evolving-loop/reports/learning.json`
242. **Current Skills**: `.self-evolving-loop/generated-skills/*.md`
253. **Checkpoint**: `.self-evolving-loop/state/checkpoint.json`
264. **Tool Usage**: `.claude/memory/meta-engineering/tool-usage.json`
275. **Evolution History**: `.claude/memory/meta-engineering/evolution.json`
28 
29## Evolution Process
30 
31### 1. Load Current State
32 
33```bash
34# Read learning report
35LEARNING=$(cat .self-evolving-loop/reports/learning.json)
36 
37# Get current skill versions
38EXECUTOR_V=$(jq -r '.skill_versions.executor' .self-evolving-loop/state/checkpoint.json)
39VALIDATOR_V=$(jq -r '.skill_versions.validator' .self-evolving-loop/state/checkpoint.json)
40FIXER_V=$(jq -r '.skill_versions.fixer' .self-evolving-loop/state/checkpoint.json)
41 
42# Read current skills
43CURRENT_EXECUTOR=".self-evolving-loop/generated-skills/executor-v${EXECUTOR_V}.md"
44```
45 
46### 2. Apply Adjustments
47 
48List the adjustments to process, then for each one read its `section`, `action`, and `content` and edit the current skill file with the Edit tool:
49 
50```bash
51jq -c '.skill_adjustments[]' .self-evolving-loop/reports/learning.json
52```
53 
54- **add** → insert `content` as a new section after the named `section`.
55- **modify** → replace the named `section`'s body with `content`.
56- **remove** → delete the named `section` entirely.
57 
58---
59 
60## 📋 Merge Strategy (Conflict Resolution)
61 
62**CRITICAL**: Define explicit rules for merging skill content to avoid duplicates and conflicts.
63 
64### Merge Rules
65 
66| Conflict Type | Resolution Strategy |
67|---------------|---------------------|
68| Duplicate section | Keep newer, archive older in `## Archived` |
69| Conflicting patterns | Keep higher success_rate pattern |
70| Duplicate examples | Keep unique examples, max 5 per section |
71| Conflicting instructions | Newer wins, log conflict |
72 
73### Section Merge Algorithm
74 
75When merging a new section into an existing skill, apply these rules in order (limits: **≤ 5 examples** and **≤ 10 patterns** per section):
76 
771. **New section** (name not present) → add it directly.
782. **Exact duplicate** (identical content) → skip.
793. **Conflicting** (both non-trivial, and their first lines differ) → the newer content wins; append an entry to the merge conflict log.
804. **Otherwise** → append only the genuinely new lines, deduplicating against the existing lines.
815. **Enforce limits** after merging: if a section exceeds 5 example (bullet) lines or 10 patterns, trim the oldest first.
82 
83### Merge Conflict Log
84 
85All conflicts are logged for review:
86 
87```json
88{
89 "merge_timestamp": "2026-01-14T12:00:00Z",
90 "skill": "executor-v2",
91 "conflicts": [
92 {
93 "section": "Implementation Strategy",
94 "existing_preview": "Use incremental approach...",
95 "new_preview": "Use parallel approach...",
96 "resolution": "kept_new",
97 "reason": "New has higher success_rate (0.85 vs 0.72)"
98 }
99 ],
100 "sections_merged": 3,
101 "duplicates_removed": 2,
102 "size_limits_applied": 1
103}
104```
105 
106### Version History Tracking
107 
108Each evolved skill tracks its merge history:
109 
110```markdown
111## Version History
112 
113### v3 (2026-01-14)
114- Merged from v2
115- Conflicts: 1 (Implementation Strategy - kept new)
116- Added: Edge Case Handling section
117- Removed: Deprecated patterns
118 
119### v2 (2026-01-13)
120- Merged from v1
121- Conflicts: 0
122- Added: Error recovery patterns
123 
124### v1 (2026-01-12)
125- Initial generation
126```
127 
128---
129 
130### 3. Generate New Version
131 
132Template for evolved skill:
133 
134```markdown

Preview

claude-world/director-mode-liteclaude-world/director-mode-lite

# Skill Evolver Agent (Meta-Engineering v2.0)

You are the evolution specialist that transforms learning insights into improved skill versions. You ensure the Self-Evolving Loop continuously improves its exe

## Activation

Automatically activate when:

Repoclaude-world/director-mode-lite
TypeSubagents
CategoryAgent Meta & Communication
UpdatedJul 2026
LicenseMIT
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. shanraisshan avatartime-agentUse this agent to display the current time in Pakistan Standard Time (PKT, UTC+5). (root scope — see agent-teams for Dubai time)SubagentsJul 202664k
  2. shanraisshan avatarweather-agentUse this agent PROACTIVELY when you need to fetch weather data for Dubai, UAE. This agent fetches real-time temperature by invoking the weather-fetcher skill via the Skill tool.SubagentsJul 202664k
  3. czlonkowski avatarcontext-managerUse this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens.SubagentsJul 202622k
  4. tanweai avatarcto-p10P10 CTO/架构委员会 Agent。定义技术战略方向、组织 agent 团队拓扑、建设基础能力。当面对超大型项目(5+ agents, 3+ sprints)、需要战略级架构决策、或需要跨多个 P9 协调时使用。触发词:CTO 模式、P10、战略规划、架构委员会、组织设计、定义技术方向。SubagentsJul 202619k
  5. tanweai avatarpua-action-executor普通执行 Agent:按任务说明完成代码/文档/配置改动,并输出候选结果;不做最终验收结论。SubagentsJul 202619k
  6. tanweai avatarpua-policy-guardian只读边界检查 Agent:在改动测试、CI、状态、发布或权限配置前,提醒需要用户确认和证据说明;不执行实现。SubagentsJul 202619k