skills
- Repo stars 216
- Author updated Live
- Author repo kagenti
- Domain
- Engineering
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @kagenti · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skills
description: Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{…
category: engineering
runtime: no special runtime
---
# skills output preview
## PART A: Task fit
- Use case: Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{"What do you need?"} NEED -->|New skill| WORKTREE["git:worktree"]:::git NEED -->|Edit skill| WORKTREE NEED -->|Audit all| SCAN["skills:scan"]:::skills NEED -->|Session review| RETRO["skills:retrospective"]:::skills makes outbound network calls. Works with Claud….
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Worktree-First Gate / Available Skills / Related Skills” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{"What do you need?"} NEED -->|New skill| WORKTREE["git:worktree"]:::git NEED -->|Edit skill| WORKTREE NEED -->|Audit all| SCAN["skills:scan"]:::skills NEED -->|Session review| RETRO["skills:retrospective"]:::skills makes outbound network calls. Works with Claud…”.
- **02** When the source has headings, the agent prioritizes “Worktree-First Gate / Available Skills / Related Skills” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “Worktree-First Gate / Available Skills / Related Skills”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: skills
description: Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{…
category: engineering
source: kagenti/kagenti
---
# skills
## When to use
- Skill management - create, validate, and improve Claude Code skills START(["/skills"]) --> NEED{"What do you need?"} N…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “Worktree-First Gate / Available Skills / Related Skills” and keep inference separate from source facts.
- read files, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "skills" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Worktree-First Gate / Available Skills / Related Skills
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}flowchart TD
START(["/skills"]) --> NEED{"What do you need?"}
NEED -->|New skill| WORKTREE["git:worktree"]:::git
NEED -->|Edit skill| WORKTREE
NEED -->|Audit all| SCAN["skills:scan"]:::skills
NEED -->|Session review| RETRO["skills:retrospective"]:::skills
WORKTREE --> WRITE["skills:write"]:::skills
WRITE --> VALIDATE["skills:validate"]:::skills
VALIDATE -->|Issues| WRITE
VALIDATE -->|Pass| PR["Create PR"]:::git
SCAN -->|Gaps found| WORKTREE
RETRO -->|Improvements| WORKTREE
classDef skills fill:#607D8B,stroke:#333,color:white
classDef git fill:#FF9800,stroke:#333,color:white
Follow this diagram as the workflow.
Skills Management
Skills for managing the skill system itself. All skill development starts in a worktree — never edit skills directly on main.
Worktree-First Gate
Before creating or editing any skill, create a worktree:
git fetch upstream maingit worktree add .worktrees/skills-<topic> -b docs/skills-<topic> upstream/mainThen work in the worktree, validate, and create a PR.
Available Skills
| Skill | Purpose |
|---|---|
skills:write |
Create new skills or edit existing ones following the standard template |
skills:validate |
Validate skill format, naming, and structure |
skills:scan |
Audit repository skills — gaps, quality, connections, diagrams |
skills:retrospective |
End-of-session review to identify skill gaps and improvements |
Related Skills
git:worktree- Create worktrees for skill developmenttdd:ci- TDD workflow that uses skill patternsrca:ci- RCA workflow that uses skill patternsmeta:write-docs- Documentation writing guidelines
Developer Guide
See docs/developer/claude-code-skills.md for the full guide on why skills exist, how the system works, and best practices.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review