# Spec

> Scaffold a spec-driven prompt before non-trivial implementation. Forces Context/Objective/Boundaries/Validation framing so the agent ships reviewable code in one pass instead of refactoring files it was never asked to touch. Triggers "/spec", "spec this out", "write a spec prompt", "scope this task".

- **Type:** Skill
- **Install:** `agentstack add skill-ao92265-claude-code-playbook-spec`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ao92265](https://agentstack.voostack.com/s/ao92265)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ao92265](https://github.com/ao92265)
- **Source:** https://github.com/ao92265/claude-code-playbook/tree/main/skills/spec

## Install

```sh
agentstack add skill-ao92265-claude-code-playbook-spec
```

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

## About

# Spec

Turns a vague request into a four-part specification before any code is written. Prevents the two recurring failures: vague scope (agent rewrites working modules) and missing validation (green CI theater).

## When to use

- Before non-trivial implementation (multi-file, refactor, new feature).
- When a request reads like a conversation ("improve the API") instead of a spec.

Skip for: one-line fixes, lookups, trivial edits.

## The four parts (ALL required)

Fill every section. A blank section means STOP and ask — do not guess.

1. **Context** — What exists right now. Exact file paths, current behavior, relevant constraints. No "the codebase" — name the files.
2. **Objective** — What the change must *accomplish*, NOT what the code should look like. Describe the outcome, let the implementation follow.
3. **Boundaries** — What must NOT change. Files off-limits, behaviors to preserve, external interfaces/schemas frozen. Always include an explicit "do not modify outside X" line.
4. **Validation** — How to confirm it works. Exact test/build command + expected result. New behavior requires new tests.

## Template

```
Context: 

Objective: 

Boundaries: Do not modify . Do not change .

Validation: Run . . Add tests for .
```

## Rules

- Objective describes outcome, never implementation detail ("validate disposable emails", not "add a regex").
- Boundaries names real paths from the repo — verify they exist before listing them.
- Validation command must be runnable and its pass/fail observable. No "make sure it works".
- Respects existing repo caps (e.g. bugfix ~50-line / one-concern limits) — fold them into Boundaries.

## Output

The filled spec, ready to hand to an executor or run inline. No preamble. If a section can't be filled from available context → single batched question, then fill and proceed.

## Source & license

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

- **Author:** [ao92265](https://github.com/ao92265)
- **Source:** [ao92265/claude-code-playbook](https://github.com/ao92265/claude-code-playbook)
- **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-ao92265-claude-code-playbook-spec
- Seller: https://agentstack.voostack.com/s/ao92265
- 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%.