# Mini Spec

> Create a compact SPEC.md that prevents premature agreement by defining intent, non-goals, likely failure modes, and verification evidence.

- **Type:** Skill
- **Install:** `agentstack add skill-tmusser-ai-engineering-skills-mini-spec`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [tmusser](https://agentstack.voostack.com/s/tmusser)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [tmusser](https://github.com/tmusser)
- **Source:** https://github.com/tmusser/ai-engineering-skills/tree/main/skills/mini-spec

## Install

```sh
agentstack add skill-tmusser-ai-engineering-skills-mini-spec
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Mini Spec

## Purpose

Create the smallest useful `SPEC.md` that clarifies intent, names the likely failure mode, and gives the agent a verifiable target before planning or implementation.

## When to use

Use when a project or feature is clear enough to define before implementation.

## Inputs

- Clarified request
- `CONTEXT.md` if available
- Constraints
- Known commands
- Acceptance criteria or desired behavior

## Workflow

1. State the objective.
2. Identify the user or use case.
3. Define observable acceptance criteria.
4. Record non-goals.
5. List likely failure modes and name the primary failure mode for this slice.
6. Record constraints.
7. List run, test, build, and verification commands.
8. Sketch project structure.
9. Define the smallest verification demo.
10. Record open questions.
11. When applicable, name compatibility seams that must remain import-compatible or output-compatible.
12. When applicable, record invalid-if constraints that would make the slice non-viable.

## Outputs

- `SPEC.md`
- Explicit acceptance criteria
- Explicit non-goals
- Likely failure modes
- Verification demo

## Compatibility seams to preserve

When applicable, list behavior that must remain import-compatible or output-compatible.

- Public imports / APIs: _TBD_
- CLI commands / flags: _TBD_
- JSON/schema/output contracts: _TBD_
- Existing tests whose meaning must remain valid: _TBD_
- Data/fixture semantics: _TBD_

## Invalid if

- breaks a named compatibility seam
- weakens or rewrites existing tests merely to fit the implementation
- changes fixture/source data without explicit approval
- preserves behavior only through a new alternate path while breaking the old path
- changes forbidden/protected files
- adds dependencies or framework changes outside scope

## Stop conditions

- The spec is under 100 lines unless risk justifies more.
- The next implementation slice is clear.
- Unresolved questions are recorded instead of hidden.

## Anti-patterns

- Turning a small POC into a full product requirements document.
- Adding speculative future features.
- Writing vague acceptance criteria that cannot be verified.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [tmusser](https://github.com/tmusser)
- **Source:** [tmusser/ai-engineering-skills](https://github.com/tmusser/ai-engineering-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-tmusser-ai-engineering-skills-mini-spec
- Seller: https://agentstack.voostack.com/s/tmusser
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.