Skip to content
Agentmart
Submit a tool

steroid-specify

This skill should be used after steroid-vibe-capture has written .memory/changes/<feature>/vibe.md.

Skill by nzkbuild

IndexedMIT★ 3
Write a review

Chalk Labs

Need help deploying steroid-specify?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/nzkbuild-steroid-specify

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.

We use your email only for this newsletter. Privacy

About

This skill should be used after steroid-vibe-capture has written .memory/changes/<feature>/vibe.md. It converts the vibe into a formal specification with prioritized user stories and acceptance criteria, written to .memory/changes/<feature>/spec.md.

No 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/steroid-specify

What's inside

Skill name
steroid-specify
Description
This skill should be used after steroid-vibe-capture has written .memory/changes/<feature>/vibe.md. It converts the vibe into a formal specification with prioritized user stories and acceptance criteria, written to .memory/changes/<feature>/spec.md.
License
MIT
Instructions
277 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Steroid Specify (Specification Generator)

This skill reads the user's vibe from `.memory/changes/<feature>/vibe.md` and, when available, `.memory/changes/<feature>/prompt.json`, then produces a formal specification with testable acceptance criteria.

## Governed Baseline

The live governed authority for this phase is:

- `Steroid runtime contract`
- `Steroid runtime contract`
- `Steroid runtime contract`
- `Steroid runtime contract`

In the live repo, this skill implements the `spec_md` part of the governed `steroid-spec-system`. The downstream `plan_md` part is implemented by `skills/steroid-architect/SKILL.md`.

Internal reference: `Steroid internal reference` (GitHub Steroid, MIT License)

## When To Use

Activate immediately after `@steroid-vibe-capture` completes. Do not wait for user invocation. The vibe.md file must already exist in `.memory/changes/<feature>/`.

## Instructions

### 1. Phase Gate (Physical Enforcement)

Before doing anything, run the gate check:
```
node steroid-run.cjs gate specify <feature>
```
If this command fails, STOP. The vibe capture phase is not complete.

### 2. No User Interaction

Do not ask the user any questions. Read `.memory/changes/<feature>/vibe.md` and translate the vibe into a formal spec. If `.memory/changes/<feature>/prompt.json` exists, use it to preserve prompt intelligence fields like assumptions, non-goals, complexity, and recommended route. Make all decisions silently.

### 3. Anti-Summarization Directive

NEVER write vague acceptance criteria like "it should work" or "the app looks good". Every criterion must be a binary pass/fail test that a TDD engine can validate.

NEVER summarize existing code. Writing "...rest of the code here..." is a critical failure.

### 4. Circuit Breaker Mandate

If at any point you need to run a terminal command, you MUST use:
`node steroid-run.cjs '<command>'`
Direct terminal execution is strictly forbidden.

### 5. Schema Obedience

Write the output to `.memory/changes/<feature>/spec.md` using this exact format:

```markdown
# Specification: <Feature Name>

**Created**: <date>
**Source**: .memory/changes/<feature>/vibe.md
**Status**: Ready for Research

## Scope Boundary

### In Scope (v1)
- [explicit feature 1]
- [explicit feature 2]

### Out of Scope (not v1)
- [explicitly excluded thing 1]
- [explicitly excluded thing 2]

## User Stories

### Story 1: [Brief Title] (Priority: P1)

[Describe this user journey in plain, non-technical language]

**Acceptance Criteria:**

1. **Given** [initial state], **When** [user action], **Then** [expected outcome]
2. **Given** [initial state], **When** [user action], **Then** [expected outcome]

---

### Story 2: [Brief Title] (Priority: P2)

[Describe this user journey in plain, non-technical language]

**Acceptance Criteria:**

1. **Given** [initial state], **When** [user action], **Then** [expected outcome]

---

### Story 3: [Brief Title] (Priority: P3)

[Continue for all stories derived from the vibe]

---

## Edge Cases

- What happens when [boundary condition]?
- How does the system handle [error scenario]?

## Success Criteria

- **SC-001**: [Measurable outcome, e.g., "User can complete primary flow in under 30 seconds"]
- **SC-002**: [Measurable outcome]
- **SC-003**: [Measurable outcome]

## Hard Constraints (from vibe.md)
- [Copy ALL hard constraints from vibe.md verbatim]
- [These are non-negotiable requirements that override all other decisions]

## Prompt Intelligence Notes
- **Primary Intent**: [Copy from prompt.json or vibe.md]
- **Complexity / Risk**: [Copy from prompt.json or vibe.md]
- **Recommended Route**: [Copy from prompt.json or vibe.md]
- **Assumptions Carried Forward**:
  - [Copy assumptions from vibe.md / prompt.json that shape scope]
- **Non-Goals Carried Forward**:

From nzkbuild/steroid-workflow, MIT.

More from nzkbuild/steroid-workflow

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Mar 26, 2026 (7 months ago)
Last release
Mar 16, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from nzkbuild

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get steroid-specify running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying steroid-specify?

CallGet help
Cite this page

steroid-specify skill. Agent Mart. https://agentmart.dev/skills/nzkbuild-steroid-specify (last updated 2026-10-24)