sunrain520/spec-first/using-spec-first

Claude Code and agent skill by sunrain520/spec-first

Trust tier 2
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Standalone entry governor for spec-first. Use before substantial work in a spec-first repo or when the user asks what to run next; choose one public `spec-*` workflow, standalone skill, terminal command, or Direct Lane. Do not use to reroute active public workflows or bounded workers, or for lightweight facts, current-context explanations, narrow lookups, user-supplied single-document cleanup, or clearly scoped low-risk edits.

Install

npx vskill@latest install sunrain520/spec-first/using-spec-first

SKILL.md

Using Spec-First

using-spec-first is a standalone entry governor, not a command-backed workflow. It selects one next entrypoint and yields control; it creates no workflow artifact. It is a semantic map, not a rigid state machine.

Workflow Contract Summary

  • 输入: 当前用户意图、已有 workflow 状态、artifact 类型、失败/环境信号与项目级路由规则。
  • 输出: 恰好一个 public spec-* workflow、standalone skill、terminal command 或 Direct Lane 入口;进入后立即把控制权交给该 owner。
  • 硬出口: 入口选择不授权 mutation、verification claim、runtime maintenance、handoff、knowledge promotion、commit 或 landing;低置信且会改变 route 时最多询问一个问题。
  • 权威: 用户意图与项目 source rules 决定 route;本 skill 只做语义路由,不创建 workflow state 或执行下游工作。
  • 消费者: 当前用户、所有 public workflow、standalone skill 与 host runtime entrypoint。

Fast Paths

  • Continue an active public workflow or bounded worker; do not restart routing.
  • Use the Direct Lane only for current-context explanations, lightweight facts, one-off how-to explanations, command-output explanations, narrow lookups, one user-supplied document, or a single low-risk edit whose target, change, and root cause are already clear.
  • Do not use the Direct Lane when the request includes document review/critique, a failure/error/stack trace, environment/setup/runtime concerns, an explicit workflow name, handoff/context reset, knowledge promotion, or an unresolved build goal, target user, success/acceptance criterion, or mutually exclusive implementation direction. If a Direct Lane task expands to multi-file behavior, architecture, governance, runtime, an unknown root cause, or a sensitive surface, stop and route again.

Route Selection

For every request outside the fast paths, and to validate an explicit public route or answer “what next?”, read Public Route Map. Select exactly one entrypoint; do not automatically chain the flow. Prefer readiness, failure, or review routes when they match; otherwise use immediate intent and artifact type. Checkpoint — ask: at low confidence, ask at most one route-changing question, then stop and wait for the answer before routing further.

For active work, announce one localized line equivalent to Entering <entrypoint>: <one concrete reason>, then follow the selected route. If a standalone skill is user-invoked only, recommend it and wait. For recommendation-only requests, return exactly one recommendation and wait:

text
Recommended entrypoint: <spec-*, standalone skill, or terminal command>
Reason: <one concrete reason>
Next action: <one action the user can take now>

Use the repository's configured user language. Checkpoint — wait: after any recommendation, stop and yield; enter the recommended entrypoint only after the user asks to continue.

Exit Boundaries

Hard exit gates cover mutation, verification claims, source/runtime, handoff/context reset, and knowledge promotion. A route match never authorizes an exit. Never claim verification or completion without traceable evidence, and never fabricate tests, refreshes, evals, or routing evidence. Modify source-of-truth surfaces, never generated host runtime; scripts/tools prepare deterministic facts while LLMs judge semantic adequacy.

Before runtime maintenance, scenario-fingerprint interpretation, worker dispatch, the Codex startup reminder, ordinary-context exclusions, handoff/context reset, knowledge promotion, or any parent multi-repo write, test, autofix, or commit, read Conditional Routing Boundaries and apply the matching section.

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
97
Repository forks
12
7-day trend score
23

Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 18 Aug 2026, 2 months ago.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/sunrain520/spec-first/using-spec-first/badge)](https://verified-skill.com/skills/sunrain520/spec-first/using-spec-first)

Something wrong with this skill or its page? Tell us.