start
- Repo stars 330
- License MIT
- Author updated Live
- Author repo claude-skill-registry
- Domain
- Other
- 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: start
description: Lean session start. Asks focus area first, then loads only relevant context. Use when "start" is…
category: other
runtime: no special runtime
---
# start output preview
## PART A: Task fit
- Use case: Lean session start. Asks focus area first, then loads only relevant context. Use when "start" is said at session beginning. Minimal session start - ask focus first, load only relevant context. 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. Ask Focus” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Lean session start. Asks focus area first, then loads only relevant context. Use when "start" is said at session beginning. Minimal session start - ask focus first, load only relevant context. 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. Ask Focus” 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. Ask Focus”. 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: start
description: Lean session start. Asks focus area first, then loads only relevant context. Use when "start" is…
category: other
source: majiayu000/claude-skill-registry
---
# start
## When to use
- Lean session start. Asks focus area first, then loads only relevant context. Use when "start" is said at session begin…
- 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. Ask Focus” 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 "start" {
input -> user goal + target files + boundaries + acceptance criteria
context -> When to Activate / Flow / 1. Ask Focus
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
}Start (Lean Session)
Minimal session start - ask focus first, load only relevant context.
When to Activate
- User says: "start"
- Beginning of work session
- When you want focused context
Flow
1. Ask Focus
Ask the user:
- What area are you working on? (creative, technical, content, strategy, system)
- What's the specific task?
2. Quick Context (Optional)
Only if relevant to stated topic:
If mentions "inbox" or "learning":
ls inbox/session-summaries/ 2>/dev/nullIf mentions git:
git status -sbOtherwise: skip context checks.
3. Load Relevant Role
Based on answer, read only the relevant role file from roles/.
4. Begin
[Role] here.
[1-2 sentence acknowledgment]
[First question or action]What NOT to Do
- Don't load ALL roles
- Don't run full context checks unless needed
- Don't greet with wall of text
Comparison
- start: Lean, ask first, minimal context
- help: Deep assessment, suggest priorities
Use start for focused work without setup overhead.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review