bmad-spec

Distills intent inputs into a five-field SPEC.md kernel with companion files and append-only memlog.

Updated Aug 3, 2026
One-click install
npx skills add https://github.com/shaahy/quicknav-desktop --skill bmad-spec-shaahy
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bmad-spec
Source: https://github.com/shaahy/quicknav-desktop/tree/main/A%20%E6%95%99%E7%A8%8B%E9%9B%86%E5%90%88/BMAD-METHOD%E6%8A%80%E8%83%BD%E9%80%9F%E6%9F%A5/source-v6.10.0/src/core-skills/bmad-spec
Command: npx skills add https://github.com/shaahy/quicknav-desktop --skill bmad-spec-shaahy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve? Turning vague ideas, brain dumps, PRDs, transcripts, or mixed multi-source material into a single canonical machine-readable contract is error-prone, and downstream planning steps drift when the spec is hand-edited by many contributors. This Skill produces a preservation-validated SPEC.md kernel plus companion files that every downstream BMad skill consumes. ## Core Features & Use Cases - Five-field kernel distillation: Extracts Why, Capabilities (with stable CAP-N IDs), Constraints, Non-goals, and Success signal from any intent input into SPEC.md. - Memlog-driven derivation: Records every decision in an append-only .memlog.md and re-derives SPEC.md from it, so updates never cause merge drift and capability IDs stay stable. - Companion management and self-validation: Routes overflow content (glossaries, diagrams, catalogs) into named companion files and runs two-pass validation against eight Spec Law rules. - Use Case: Paste a customer email thread and a rough feature list, and receive a spec folder containing SPEC.md, a glossary companion, and a memlog with open questions flagged for human decision. ## Quick Start Ask the agent to distill the attached product brief into a spec using the bmad-spec workflow and return the spec folder path.

Frequently Asked Questions about bmad-spec

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a spec from a vague idea or brain dump?▼

Provide the raw input and the skill distills it into the five-field kernel: Why, Capabilities, Constraints, Non-goals, and Success signal. Sparse inputs default to express mode, where gaps become open_questions entries rather than invented answers.

How do I update an existing spec without losing capability IDs?▼

Invoke the skill again with the same slug; it lands on the existing spec folder and updates in place. The append-only .memlog.md is the authority, so existing CAP-N IDs are preserved and new capabilities get the next unused number.

What is the difference between SPEC.md and companion files?▼

SPEC.md holds the lean five-field kernel in prose only. Load-bearing content that does not fit, such as glossaries, entity catalogs, and diagrams, lives in companion files listed in the companions frontmatter array for downstream skills to read.

Can bmad-spec run headless from another skill or script?▼

Yes, headless mode triggers when there is no TTY or a programmatic caller supplies all inputs. It returns JSON with status and the list of files written, or a blocked status with error codes like insufficient_intent or missing_slug.

When should I not use bmad-spec?▼

Do not use it when the input is too thin to distill, such as a one-line idea with no context. The skill blocks and suggests running bmad-prd first to draw out the vision before specification.