Agent skill

04 Spec

by ai-driven-dev in ai-driven-dev/framework

Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings.

MITAuto-check passedProduct & Project Management

Install 04 Spec

skills CLI
$ npx skills add ai-driven-dev/framework --skill 04-spec -a claude-code

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

GitHub CLI
$ gh skill install ai-driven-dev/framework 04-spec --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/ai-driven-dev/framework.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/aidd-pm/skills/04-spec .claude/skills/04-spec && 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
04-spec
GitHub stars
513
Token cost
~271 tokens
SKILL.md length
73 words
Files
6 (incl. references, assets)
Skills in repo
46
Repo updated
First seen
Licence
MIT

At a glance

Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings.

  • The user wants to draft
  • SKILL.md covers Actions and Transversal rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Tasks that involve PRD writing

What it does

04 Spec is an agent skill from ai-driven-dev/framework. Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings. Use when the user wants to draft or refine a spec. Not for writing code, a full PRD, or changing a locked spec.

Its SKILL.md is about 270 tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files and assets (for example `actions/01-build.md`, `actions/02-refine.md` and `assets/spec-template.md`).

It sits in Product & Project Management, covering PRD writing and Code review. The repository describes itself as: Marketplace Framework AI-Driven Dev : Context Engineering, Plugins, Agents, Skills, Hooks, Templates, SDLC. The licence is MIT.

When your agent uses it

  • The user wants to draft
  • Tasks that involve PRD writing
  • Tasks that involve Code review

Example prompts

  • “/04-spec”

What it can do on your machine

Read from SKILL.md and the folder at commit 6e30640. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid).

    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

04 Spec loads about 271 tokens when it runs, and up to ~281 if it reads all its reference files. Until then it costs about 55 tokens; SKILL.md has 73 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~55
When it runs · the whole SKILL.md, loaded when a task matches
~271
With references · SKILL.md plus every file in references/, read only if the agent opens them
~281

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 ai-driven-dev/framework at commit 6e30640, republished under its MIT licence (© ai-driven-dev). 73 words, ~271 tokens.

Download SKILL.mdSave it as .claude/skills/04-spec/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
04-spec
description
Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings. Use when the user wants to draft or refine a spec. Not for writing code, a full PRD, or changing a locked spec.
argument-hint
request | prd | spec

Spec

mermaid
flowchart LR
  request([request or PRD path]) --> build --> done([spec.md])
  target([spec path + findings]) --> refine --> done

Actions

Run the flow above. Read only the next action file.

ActionDoes
builddraft a fresh spec from a request or PRD
refinerewrite an existing spec to address findings

Transversal rules

  • Never invent; mark every gap instead of guessing.
  • Never explore the codebase.
  • Hold intent, never implementation: solution-agnostic, no how, few acceptance criteria.
  • Keep it readable: clear headers, bulleted criteria, explicit non-goals.
  • Immutable once validated: never rewrite a locked spec.

© ai-driven-dev, 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 5 other files (references, assets) in plugins/aidd-pm/skills/04-spec of ai-driven-dev/framework.

  • SKILL.md
  • actions/01-build.md
  • actions/02-refine.md
  • assets/spec-template.md
  • assets/spec-validator.yml
  • references/tbd-marker.md

Open the folder on GitHubat commit 6e30640

Compare with similar skills

04 Spec 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.

04 Spec compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
04 Spec this skillai-driven-dev/framework513—~271Automated safety check: PassMIT
Code ReviewAUTO-MAS-Project/AUTO-MAS7081 repos~797Automated safety check: PassAGPL-3.0
Code Review Completenesseric-tramel/moraine117—~404Automated safety check: PassApache-2.0
Spec App Consistency Auditleo-kuang-ai/spec-first107—~4.6kAutomated safety check: PassMIT
Ad ReviewCorridorTech/PoseCap224—~2.4kAutomated safety check: NotesApache-2.0
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT

Similar skills

  • Code Review

    AUTO-MAS-Project/AUTO-MAS

    从固定点(commit、branch、tag 或 merge-base)开始,沿两条轴线审查变更——规范(代码是否遵循仓库文档化的编码规范?)和规格(代码是否与原始 issue/PRD 的要求一致?)。两条审查线在并行子 agent 中运行,并以并排方式报告结果。当用户想审查一个分支、PR、进行中的变更,或要求"从 X 开始审查"时使用。

    708 GitHub starsUsed in 1 repo~797 tokens
    Product & Project ManagementAuto-check passed
  • Code Review Completeness

    eric-tramel/moraine

    Review a PR through the CodeReviewCompleteness persona. An agent skill from eric-tramel/moraine.

    117 GitHub stars~404 tokensUpdated 3 days ago
    Product & Project ManagementAuto-check passed
  • 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 14 days ago
    DevelopmentAuto-check passed
  • Ad Review

    CorridorTech/PoseCap

    Two-axis fresh-context code review per WORKFLOW §10. An agent skill from CorridorTech/PoseCap.

    224 GitHub stars~2.4k tokensUpdated yesterday
    DevelopmentAuto-check: notes
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Ralph Tui Create Beads

    subsy/ralph-tui

    Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.

    2.5k GitHub starsUsed in 1 repo~2.6k tokens
    Product & Project ManagementAuto-check passed

More from ai-driven-dev/framework

All 46 skills in this repo
  • 00 Async Dev

    ai-driven-dev/framework

    Drive the async-dev pipeline from one entry point, whether setup, run, or review.

    513 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • 01 Plan

    ai-driven-dev/framework

    Turn a request, ticket, or file into a phased implementation plan.

    513 GitHub stars~517 tokensUpdated today
    Auto-check passed
  • 01 Sdlc

    ai-driven-dev/framework

    Autonomously orchestrates a request from framing to a draft pull request, isolating implementation, independent review, and final outcome challenge.

    513 GitHub stars~583 tokensUpdated today
    Auto-check passed
  • 02 Backlog

    ai-driven-dev/framework

    Orchestrates a product backlog end to end. An agent skill from ai-driven-dev/framework.

    513 GitHub stars~613 tokensUpdated today
    Auto-check passed
  • 00 Onboard

    ai-driven-dev/framework

    Guide a project's journey through AIDD, from first setup to shipping a feature.

    513 GitHub stars~242 tokensUpdated today
    Auto-check passed
  • 01 Acceptance QA

    ai-driven-dev/framework

    Validate a reviewed candidate's observable behavior against its acceptance criteria and record short named videos as reviewer evidence.

    513 GitHub stars~434 tokensUpdated today
    Auto-check passed

Questions about 04 Spec

What does 04 Spec do?

Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings. 04 Spec is an agent skill from ai-driven-dev/framework. Generate or refine a spec, a feature's immutable contract, from a request, a PRD, or review findings.

When should I use 04 Spec?

04 Spec fits situations like: the user wants to draft; tasks that involve PRD writing; tasks that involve Code review.

How do I install 04 Spec in Claude Code?

Run `npx skills add ai-driven-dev/framework --skill 04-spec -a claude-code`. Or copy the skill folder (plugins/aidd-pm/skills/04-spec in ai-driven-dev/framework) into .claude/skills/04-spec in your project. Claude Code loads it when a task matches its description.

How do I install 04 Spec in Codex?

Run `npx skills add ai-driven-dev/framework --skill 04-spec -a codex`. Or copy the skill folder (plugins/aidd-pm/skills/04-spec in ai-driven-dev/framework) into .agents/skills/04-spec in your project. Codex loads it when a task matches its description.

Can I use 04 Spec 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 ai-driven-dev/framework --skill 04-spec -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/04-spec, .gemini/skills/04-spec, .github/skills/04-spec and .opencode/skills/04-spec in your project.

What does 04 Spec need to run?

SKILL.md names no scripts, command-line tools or credentials: 04 Spec is instructions for the agent only.

Does 04 Spec 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 04 Spec 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 04 Spec use?

04 Spec 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 04 Spec use?

About 271 tokens (SKILL.md is roughly 1.1k 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 10 tokens, read only when the agent opens those files.

What are the alternatives to 04 Spec?

Skills that share tags, products or a category with 04 Spec: Code Review (AUTO-MAS-Project/AUTO-MAS, 708 stars), Code Review Completeness (eric-tramel/moraine, 117 stars), Spec App Consistency Audit (leo-kuang-ai/spec-first, 107 stars) and Ad Review (CorridorTech/PoseCap, 224 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains 04 Spec?

ai-driven-dev (a GitHub organization) maintains it in ai-driven-dev/framework, which has 513 GitHub stars. The repository holds 46 skills in this directory. The repository was last updated on October 8, 2026.

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