collab
- 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
- macOS · Linux · Windows
- Runtime requirements
- Bun
- 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: collab
description: Start or resume a collab session - session management only Entry point for collab workflow. Hand…
category: data
runtime: Bun
---
# collab output preview
## PART A: Task fit
- Use case: Start or resume a collab session - session management only Entry point for collab workflow. Handles session management and delegates to MCP state machine. Tool: mcppluginmermaid-collabmermaidcheckserverhealth runs entirely locally; runs on Bun. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “Step 1: Check Server / Step 2: Find/Create Session / Step 3: Create New Session” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Start or resume a collab session - session management only Entry point for collab workflow. Handles session management and delegates to MCP state machine. Tool: mcppluginmermaid-collabmermaidcheckserverhealth runs entirely locally; runs on Bun. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “Step 1: Check Server / Step 2: Find/Create Session / Step 3: Create New Session” 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. 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 “Step 1: Check Server / Step 2: Find/Create Session / Step 3: Create New Session”. 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: collab
description: Start or resume a collab session - session management only Entry point for collab workflow. Hand…
category: data
source: majiayu000/claude-skill-registry
---
# collab
## When to use
- Start or resume a collab session - session management only Entry point for collab workflow. Handles session management…
- 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 “Step 1: Check Server / Step 2: Find/Create Session / Step 3: Create New Session” 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. 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 "collab" {
input -> user goal + target files + boundaries + acceptance criteria
context -> Step 1: Check Server / Step 2: Find/Create Session / Step 3: Create New Session
rules -> SKILL.md triggers / order / output contract
runtime -> Bun | 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
}Collab Sessions
Entry point for collab workflow. Handles session management and delegates to MCP state machine.
Step 1: Check Server
Tool: mcp__plugin_mermaid-collab_mermaid__check_server_health
Args: {}If not healthy: "Server not running. Start with: bun run bin/mermaid-collab.ts start" STOP if server not running.
Step 2: Find/Create Session
List sessions for this project:
Tool: mcp__plugin_mermaid-collab_mermaid__list_sessions
Args: {}If sessions exist: Present list with "Create new" option If no sessions: Go to Step 3
Step 3: Create New Session
- Generate name:
mcp__plugin_mermaid-collab_mermaid__generate_session_name() - Ask user to confirm or pick own name
- Initialize state:
Tool: mcp__plugin_mermaid-collab_mermaid__update_session_state Args: { "project": "<cwd>", "session": "<name>", "phase": "brainstorming", "currentItem": null } - Get first skill from state machine:
Tool: mcp__plugin_mermaid-collab_mermaid__complete_skill Args: { "project": "<cwd>", "session": "<name>", "skill": "collab-start" } - Invoke: result.next_skill
Step 4: Resume Existing Session
- Get session state:
mcp__plugin_mermaid-collab_mermaid__get_session_state() - Check for snapshot:
- If snapshot exists: Load it, delete it, invoke snapshot.activeSkill
- If no snapshot: Call complete_skill with current phase's skill, invoke result.next_skill
No Manual Routing
This skill does NOT:
- Route by item type (MCP state machine does this)
- Invoke brainstorming/rough-draft directly (complete_skill returns next skill)
- Manage the work item loop (routing nodes handle this)
Decide Fit First
Design Intent
How To Use It
Boundaries And Review