DesignSpec
Write a formal design spec from brainstorming output or requirements.
Skill by N4M3Z
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/n4m3z-designspec
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, design, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/designspec
What's inside
- Skill name
DesignSpec- Description
- Write a formal design spec from brainstorming output or requirements. USE WHEN design approved, write spec, formalize design, spec document.
- License
- EUPL-1.2
- Instructions
- 56 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
Files (1)
- SKILL.md
SKILL.md (first lines)
# DesignSpec Produce a formal design specification from approved brainstorming output or direct requirements. The spec is the contract between design and implementation — Plan and DeveloperSprint consume it. 1. **Gather input** — read the approved design (from Brainstorming output or user description) 2. **Write the spec** — structured markdown covering all sections below 3. **Self-review** — run the checklist before presenting 4. **Save** — write to `docs/specs/YYYY-MM-DD-<topic>-design.md` 5. **User review** — present for approval. No implementation until approved. ## Spec Structure Scale sections to complexity. Simple specs skip sections that don't apply. - **Problem Statement** — what exists today, why it's insufficient - **Proposed Approach** — what we're building, key design decisions - **API / Interface Design** — public surface, data shapes, commands - **Data Flow** — how data moves through the system - **Edge Cases** — known boundary conditions and how they're handled - **Test Strategy** — what to test, how to verify correctness - **Out of Scope** — what this spec explicitly does NOT cover ## Self-Review Checklist Before presenting the spec, verify: | Check | Question | | ------------ | ---------------------------------------------------------- | | Completeness | Could someone implement this without asking questions? | | Consistency | Do all sections agree with each other? | | Clarity | Is every term unambiguous? No "should", "might", "maybe"? | | Scope | Does this solve the stated problem without gold-plating? | | YAGNI | Is every feature justified by a stated requirement? | ## Red Flags | Thought | Reality | | -------------------------------------------- | -------------------------------------------------------------- | | "The design is clear enough, skip the spec" | If it's clear, the spec writes fast. If not, you need it more. | | "I'll fill in the details during coding" | That's not a spec, it's a wish list. | | "Edge cases can wait" | Edge cases found during coding cost 10x more to handle. | | "The user already approved the design" | Design approval is not spec approval. Write it down. | | "This spec is too short" | Short specs for simple problems are correct. Don't pad. | ## Constraints - Every section must be concrete — no placeholders, TBD, or TODO - Spec must be saved as a file, not just presented in conversation - User must approve the spec before implementation begins - Hand off to Plan or DeveloperSprint after approval ## Sources - <https://github.com/obra/superpowers>
From N4M3Z/forge-core, EUPL-1.2.
More from N4M3Z/forge-core
- 0.520score
LocalModel
N4M3Z
Run prompts against a local LLM backend (LM Studio, Ollama, or MLX) with privacy-preserving output guardrails — drop reasoning_content, enforce structured…
SkillCFreshness: C★ 4Claude Code +9 - 0.520score
ForgeSkill
N4M3Z
Create, validate, evaluate, and iterate skills for forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
Brainstorming
N4M3Z
Collaborative ideation before implementation — explore context, clarify intent, propose approaches.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildAgent
N4M3Z
Create, validate, or audit agent definitions.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildHook
N4M3Z
Create and validate module hooks.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildModule
N4M3Z
Design, build, and validate forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildPlugin
N4M3Z
Create, validate, and publish Claude Code plugins from forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildRule
N4M3Z
Create, validate, or place behavioral rules in forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildSkill
N4M3Z
Create and validate skills for forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
DesignFrontend
N4M3Z
Build distinctive, production-grade frontend interfaces that avoid generic AI aesthetics.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
ExecutePlan
N4M3Z
Execute an implementation plan inline — task by task in a single session — then finish the work: verify, present integration options (merge, PR, keep…
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
GuardRails
N4M3Z
Safety guardrails: runtime overrides for AI-safety plugin blocks, and per-language security review for python, javascript/typescript, and go.
SkillCFreshness: C★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 3
- Open issues
- 8
- Last commit (this folder)
- Jul 13, 2026 (3 months ago)
- Last release
- Apr 16, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- EUPL-1.2
- Repository
- github.com/N4M3Z/forge-core
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from N4M3Z
- 0.520score
LocalModel
N4M3Z
Run prompts against a local LLM backend (LM Studio, Ollama, or MLX) with privacy-preserving output guardrails — drop reasoning_content, enforce structured…
SkillCFreshness: C★ 4Claude Code +9 - 0.520score
ForgeSkill
N4M3Z
Create, validate, evaluate, and iterate skills for forge modules.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
HtmlPlayground
N4M3Z
Generate single-file HTML demos comparing techniques side-by-side.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildAgent
N4M3Z
Create, validate, or audit agent definitions.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
BuildHook
N4M3Z
Create and validate module hooks.
SkillCFreshness: C★ 4Claude Code +9 - 0.515score
Brainstorming
N4M3Z
Collaborative ideation before implementation — explore context, clarify intent, propose approaches.
SkillCFreshness: C★ 4Claude Code +9
Cite this page
DesignSpec skill. Agent Mart. https://agentmart.dev/skills/n4m3z-designspec (last updated 2026-10-24)