Agent skill

Using Spec First

by leo-kuang-ai in leo-kuang-ai/spec-first

Standalone entry governor for spec-first. An agent skill from leo-kuang-ai/spec-first.

MITAuto-check passedDevelopment

Install Using Spec First

skills CLI
$ npx skills add leo-kuang-ai/spec-first --skill using-spec-first -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install leo-kuang-ai/spec-first using-spec-first --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/using-spec-first .claude/skills/using-spec-first && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
using-spec-first
GitHub stars
107
Token cost
~1k tokens
SKILL.md length
421 words
Files
11 (incl. references)
Skills in repo
35
Repo updated
First seen
Licence
MIT

At a glance

Standalone entry governor for spec-first. An agent skill from leo-kuang-ai/spec-first.

  • Asks what to run next
  • SKILL.md covers Workflow Contract Summary, Fast Paths, Route Selection and Exit Boundaries
  • Runs Shell scripts from its folder
  • Choose one public spec- workflow

What it does

Using Spec First is an agent skill from leo-kuang-ai/spec-first. 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.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 15 other files, including reference files (for example `evals/cases/direct-lane-simple-howto.yaml`, `evals/cases/failure-priority-single-entry.yaml` and `evals/cases/r2-low-confidence-one-question.yaml`).

It sits in Development, covering Spec-driven development. The repository describes itself as: 仓库原生 AI Coding Harness —— 把一次性 AI 对话变成可治理、可验证、可沉淀的工程闭环 · spec-first.cn. The licence is MIT.

When your agent uses it

  • Asks what to run next
  • Choose one public spec- workflow
  • Standalone skill
  • Terminal command

Example prompts

  • “/using-spec-first”

Requirements

  • A Bash shell

What it can do on your machine

Read from SKILL.md and the folder at commit 74655dc. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Using Spec First loads about 1k tokens when it runs, and up to ~3.3k if it reads all its reference files. Until then it costs about 112 tokens; SKILL.md has 421 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~112
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from leo-kuang-ai/spec-first at commit 74655dc, republished under its MIT licence (© leo-kuang-ai). 421 words, ~1,005 tokens.

Download SKILL.mdSave it as .claude/skills/using-spec-first/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
using-spec-first
description
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.

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.
Show full SKILL.md (225 more words)Show less

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.

© leo-kuang-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in skills/using-spec-first of leo-kuang-ai/spec-first.

  • SKILL.md
  • evals/cases/direct-lane-simple-howto.yaml
  • evals/cases/failure-priority-single-entry.yaml
  • evals/cases/r2-low-confidence-one-question.yaml
  • evals/cases/recommendation-only-format.yaml
  • evals/cases/route-failure-to-spec-debug.yaml
  • evals/cases/route-vague-idea-to-spec-brainstorm.yaml
  • evals/eval.yaml
  • evals/fixtures/scripts/check-r2-asks.sh
  • references/conditional-routing-boundaries.md
  • references/public-route-map.md

Open the folder on GitHubat commit 74655dc

Compare with similar skills

Using Spec First next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Using Spec First compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Using Spec First this skillleo-kuang-ai/spec-first107—~1kAutomated safety check: PassMIT
OpenSpec Bulk Change ArchiverFission-AI/OpenSpec72k2 repos~5.6kAutomated safety check: PassMIT
Speckit ConstitutionWeihanLi/WeihanLi.Common24211 repos~2.1kAutomated safety check: PassApache-2.0
Speckit Plankunstmusik/blue15418 repos~2.1kAutomated safety check: PassGPL-3.0
Speckit Specifykunstmusik/blue15418 repos~4.7kAutomated safety check: PassGPL-3.0
Review Spdzhu1090093659/spec_driven_develop987—~1.5kAutomated safety check: PassMIT

Similar skills

  • Archives several completed OpenSpec changes in one operation, checking the codebase to resolve spec conflicts rather than archiving blindly.

    72k GitHub starsUsed in 2 repos~5.6k tokens
    DevelopmentAuto-check passed
  • Speckit Constitution

    WeihanLi/WeihanLi.Common

    Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.

    242 GitHub starsUsed in 11 repos~2.1k tokens
    DevelopmentAuto-check passed
  • Speckit Plan

    kunstmusik/blue

    Execute the implementation planning workflow using the plan template to generate design artifacts.

    154 GitHub starsUsed in 18 repos~2.1k tokens
    DevelopmentAuto-check passed
  • Speckit Specify

    kunstmusik/blue

    Create or update the feature specification from a natural language feature description.

    154 GitHub starsUsed in 18 repos~4.7k tokens
    DevelopmentAuto-check passed
  • Review Spd

    zhu1090093659/spec_driven_develop

    Findings-first code review workflow for AI coding agents. An agent skill from zhu1090093659/spec_driven_develop.

    987 GitHub stars~1.5k tokensUpdated 2 mo ago
    DevelopmentAuto-check passed
  • Speckit Tasks

    kunstmusik/blue

    Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.

    154 GitHub starsUsed in 18 repos~3k tokens
    DevelopmentAuto-check passed

More from leo-kuang-ai/spec-first

All 35 skills in this repo
  • Spec App Consistency Audit

    leo-kuang-ai/spec-first

    Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use…

    107 GitHub stars~4.6k tokensUpdated 2 days ago
    Auto-check passed
  • Spec Handoff

    leo-kuang-ai/spec-first

    Create a durable cross-session handoff or resume from a user-selected continuity source.

    107 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check passed
  • Spec Pov

    leo-kuang-ai/spec-first

    Give a decisive, project-grounded verdict on an external input — judged against the current project, not in the abstract.

    107 GitHub stars~4.5k tokensUpdated 2 days ago
    Auto-check passed
  • Spec Resolve PR Feedback

    leo-kuang-ai/spec-first

    Resolve PR review feedback by evaluating validity and fixing issues with conflict-aware resolver dispatch.

    107 GitHub stars~1.8k tokensUpdated 2 days ago
    Auto-check: notes
  • Spec Riffrec Feedback Analysis

    leo-kuang-ai/spec-first

    Analyze explicit Riffrec product-feedback captures, including riffrec-.zip, the Riffrec session.json + events.json + recording.webm + voice.webm bundle, or media/notes the user identifies as a…

    107 GitHub stars~1.4k tokensUpdated 2 days ago
    Auto-check passed
  • Spec Compound

    leo-kuang-ai/spec-first

    Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md.

    107 GitHub stars~18k tokensUpdated 2 days ago
    Auto-check passed

Categories

Questions about Using Spec First

What does Using Spec First do?

Standalone entry governor for spec-first. An agent skill from leo-kuang-ai/spec-first. Using Spec First is an agent skill from leo-kuang-ai/spec-first. Standalone entry governor for spec-first.

When should I use Using Spec First?

Using Spec First fits situations like: asks what to run next; choose one public spec- workflow; standalone skill; terminal command.

How do I install Using Spec First in Claude Code?

Run `npx skills add leo-kuang-ai/spec-first --skill using-spec-first -a claude-code`. Or copy the skill folder (skills/using-spec-first in leo-kuang-ai/spec-first) into .claude/skills/using-spec-first in your project. Claude Code loads it when a task matches its description.

How do I install Using Spec First in Codex?

Run `npx skills add leo-kuang-ai/spec-first --skill using-spec-first -a codex`. Or copy the skill folder (skills/using-spec-first in leo-kuang-ai/spec-first) into .agents/skills/using-spec-first in your project. Codex loads it when a task matches its description.

Can I use Using Spec First in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add leo-kuang-ai/spec-first --skill using-spec-first -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/using-spec-first, .gemini/skills/using-spec-first, .github/skills/using-spec-first and .opencode/skills/using-spec-first in your project.

What does Using Spec First need to run?

Going by SKILL.md and its folder, Using Spec First needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Using Spec First access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Using Spec First safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Using Spec First use?

Using Spec First is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Using Spec First use?

About 1k tokens (SKILL.md is roughly 4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.3k tokens, read only when the agent opens those files.

What are the alternatives to Using Spec First?

Skills that share tags, products or a category with Using Spec First: OpenSpec Bulk Change Archiver (Fission-AI/OpenSpec, 72k stars), Speckit Constitution (WeihanLi/WeihanLi.Common, 242 stars), Speckit Plan (kunstmusik/blue, 154 stars) and Speckit Specify (kunstmusik/blue, 154 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Using Spec First?

leo-kuang-ai (a GitHub user) maintains it in leo-kuang-ai/spec-first, which has 107 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 8, 2026.

Source: leo-kuang-ai/spec-first on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.