role
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Data
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 94 / 100 · audit passed
- Author / version / license
- @majiayu000 · MIT
- 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
- Local-only
- 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: role
description: Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with s…
category: data
runtime: no special runtime
---
# role output preview
## PART A: Task fit
- Use case: Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with specific roles. Supports single or multiple roles. Match requested role name to file. Common patterns: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “When to Activate / Flow / 1. Parse Request” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with specific roles. Supports single or multiple roles. Match requested role name to file. Common patterns: runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “When to Activate / Flow / 1. Parse Request” 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; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options.The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
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.
Start with a small task and check whether the result follows “When to Activate / Flow / 1. Parse Request”. Inspect diffs, logs, previews, or tests before expanding scope.
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: role
description: Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with s…
category: data
source: majiayu000/claude-skill-registry
---
# role
## When to use
- Load specific role(s) for focused work. Use when user says "role [name]" or wants to work with specific roles. Support…
- 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 “When to Activate / Flow / 1. Parse Request” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; 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.The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "role" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to Activate / Flow / 1. Parse Request
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Role (Dynamic Role Loading)
Load specific role(s) for focused work.
When to Activate
- User says: "role [name]", "take on [role]"
- User requests specific role by name
- Mid-session role switching
Flow
1. Parse Request
Single: "role architect" → load architect role Multiple: "role content and technical" → load both
2. Find Role Files
ls roles/*.mdMatch requested role name to file. Common patterns:
- Role name in filename (e.g.,
architect.md,01-creative-lead.md) - Check role title in frontmatter if unclear
3. Load Role
cat roles/[matched-file].md4. Activate
Single role:
[Role Name] here.
[1 sentence acknowledgment]
[First question or action]Multiple roles:
[Primary Role] here, with [Secondary Role].
[How roles work together]
[First question]Role Switching
User can say "switch to [role]" mid-session:
[Current]: Transitioning to [New Role].
[New Role]: [Pick up context from conversation]Unknown Roles
If role not found:
I don't recognize that role. Available roles:
[List from roles/ directory]
Which role do you want?Comparison
- role: Load specific role on demand
- start: Ask what to work on, then load relevant role
- help: Assess system, suggest priorities
Use role when you know exactly which role you need.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review