to-spec · Skill Details

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger: User-invoked when discussion has progressed enough to formalise into a spec. In /ask-matt's main flow, /grill-with-docs is followed by /to-spec, then /to-tickets, then /implement for larger efforts.
Mechanism: (1) Explore current codebase state (if not already done), using domain glossary vocabulary; (2) Identify testing seams — propose seam boundaries, preferring existing ones and the highest seam possible, aiming for one, confirm with user; (3) Generate spec using template: Problem Statement → Solution → User Stories (extensive numbered list) → Implementation Decisions (module interfaces, architecture decisions, no specific file paths or code snippets) → Testing Decisions (what makes a good test, which modules, prior art) → Out of Scope → Further Notes. Publish to Issue Tracker with ready-for-agent label.
Output: A structured spec document published to the Issue Tracker, labelled ready-for-agent. Avoids specific file paths and code snippets to prevent staleness, but allows inlining key decision code snippets from prototypes.

Use Cases

Two Typical Use Cases

Scenario 01

Turning discussion outcomes into a formal spec

After a deep discussion via `/grill-with-docs`, the PM and developer have aligned on a new feature. They invoke `/to-spec` to formalise the discussion. The skill doesn't re-interview but directly distills the agreed-upon points into a structured document with Problem Statement, User Stories, Implementation Decisions, etc., publishes it to GitHub Issues marked ready-for-agent for downstream `/to-tickets` and `/implement`.

Scenario 02

Quickly documenting an impromptu discussion

An impromptu meeting produces a solution for an urgent requirement with verbal consensus but no written documentation. A developer invokes `/to-spec`, the skill uses existing conversation context (no re-interview needed), automatically generates a spec, identifies testing seams and asks for confirmation, then publishes directly to the Issue Tracker. The entire process from discussion to documented spec takes minutes.

Skill Relationships

Which Skills I Use · Which Skills Use Me

Dependency relationships read as "the upper tier points to the lower tier." The current Skill sits in the middle tier — above are Skills that depend on it, below are Skills it depends on.

Tier 1 · These Skills Use Me

ask-mattWorkflow

Tier 2 · Current Skill

to-specWorkflow

Tier 3 · I Use These Skills

No explicit dependency on other Skills

Full Relationship Graph

Browse this skill's relationships within its skillset. Click a node to switch the side panel; use the search box to jump to any skill.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md50.0%
other50.0%

▸skills/to-spec/
▸to-spec
- ·SKILL.md
- ▸agents
  - ·openai.yaml

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

Related in Skillset

You May Also Need These Skills

ask-matt

A router skill for the entire skillset: when the user can't remember which skill to use or which flow fits their situation, they invoke this to get a recommendation. It describes the main "idea → ship" flow (grill-with-docs → to-spec/to-tickets → implement), plus on-ramps (triage, diagnosing-bugs, wayfinder), codebase health (improve-codebase-architecture), vocabulary layers (domain-modeling, codebase-design), and standalone skills (grill-me, prototype, research, teach). Following its map leads users to the correct workflow entry point.

Workflow

code-review

A two-axis code review skill: reviews a diff (from a fixed point to HEAD) along both Standards (coding standards + Fowler smell baseline) and Spec (faithful implementation of the originating issue/PRD). Both axes run as parallel sub-agents to avoid context pollution. The report aggregates findings without merging conclusions, ensuring "passes standards but implements the wrong thing" and "implements the right thing but breaks conventions" are both surfaced independently.

Workflow

codebase-design

A shared vocabulary skill for deep module design: provides a precise set of design terms (Module, Interface, Depth, Seam, Adapter, Leverage, Locality) guiding agents and developers to design "deep modules" — a lot of behaviour behind a small interface. Includes design principles (the deletion test, the interface is the test surface) and testability guidelines. A reference skill consumed by other skills (e.g., improve-codebase-architecture, tdd) and invoked directly by engineers.

Style Guide

diagnosing-bugs

A disciplined diagnosis loop for hard bugs and performance regressions. The core idea is to first build a tight feedback loop — no hypothesis phase without one. Six phases: build feedback loop → reproduce + minimise → generate 3-5 falsifiable hypotheses → instrument by prediction → fix + regression test → cleanup + post-mortem. If the codebase architecture can't lock down the bug, it recommends handing off to the improve-codebase-architecture skill.

Workflow