agentleFS
helderbertohelderberto/agent-skills/skills/to-spec/SKILL.md

to-spec

Skill19 starsChanged 32 days agoMITView on GitHub

Turn the settled conversation into a spec (PRD), published through the repo's tracker: `.specs/specs/<slug>.md` by default.

194 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-ts-deep-modules, to-questionnaire and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • liufeng1976Skill

    setup-ts-deep-modules

    Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.

    Also in 43 projects that use this

  • AWSSkill

    to-questionnaire

    Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

    Also in 90 projects that use this

  • RoentekSkill

    loop-me

    Grill me about specs for the workflows I want to build, within this workspace.

    Also in 49 projects that use this

  • AWSSkill

    wizard

    Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.

    Also in 116 projects that use this

  • ryotaroh180105Skill

    claude-handoff

    Hand the current conversation off to a fresh background agent that picks up the work immediately.

    Also in 39 projects that use this

  • LesaniSkill

    writing-beats

    Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

    Also in 51 projects that use this

  • +1 more from aws

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 182 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Tracker: follow .specs/issue-tracker.md, else the local default, for where specs and tickets live and when a ticket is done.

    line 15

“Common” is measured: kept by at least 6 in 10 of the 182 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

To Spec

Idea: $ARGUMENTS (if empty, ask for the problem and any solution ideas first).

Derive a kebab-case <slug> from the text before the first —/– (≤4 meaningful words, no command verbs or filler). Output: the spec, in the tracker.

Tracker: follow .specs/issue-tracker.md, else the local default, for where specs and tickets live and when a ticket is done.

Workflow

1. Explore codebase

Map current state: data models, services, API routes, frontend, tests. Note exists vs. must build. Codebase first, then docs. Unverifiable claims → flag as uncertain, never fabricate.

2. Check the branches

Never interview here. Check each branch below against the conversation and the code: settled → synthesize it. Open branches → one confirm round at most, each question with your recommended answer. Still open after that → stop with Next: /hb:grill <slug>. A domain term that settles here → call the Skill tool with domain-modeling to write it into the glossary, so spec and glossary agree.

BranchKey questionsSkip when
Scope & SurfaceWhere? New page or integrated? Roles?CLI/library, no new entry points
Data & ConceptsDefinitions, existing vs missing dataNever skip
BehaviorInteraction patterns, filtering, searchNo user-facing behavior
DisplayNumbers, tables, charts, exportsNo UI
Access & PrivacyWho sees what? Sensitive data?Single-user, no auth
BoundariesOut of scope, deferred featuresNever skip
IntegrationSchema, services, external depsSelf-contained change

Gray areas — ambiguities, contradictions, unstated assumptions — join that same round, each with a proposed resolution.

3. Design modules

Sketch modules. Favor deep modules — simple interface (1–3 entry points) hiding large implementation. Shallow signals: many 1:1 functions, callers compose multiple calls, feature changes require interface changes. Mark which modules need tests.

4. Write spec

Draft it. Omit empty sections. No file paths or code snippets. A related ticket (a key or #42 in the conversation, the argument, or the branch name) → record it in frontmatter; no ticket → no frontmatter.

---
ticket: <key>
---
# Feature Name
## Problem Statement
## Current State (skip if greenfield)
## Solution (user experience, not architecture)
## User Stories (numbered, cover happy + edge + error)
## Implementation Decisions
### New Modules (name, purpose, interface signatures)
### Architectural Decisions (definitions, data flow, state)
### Schema Changes
### API Contracts
### Navigation
## Testing Decisions (behavior tests, key cases, prior art)
## Out of Scope (be specific)

5. Publish

Publish the spec to the tracker. GitHub or Jira → name the target and confirm once. The argument names an existing spec → update it instead.

Next: /hb:to-tickets <spec ref>

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.