agentleFS
Sign inStart free
lynchypinlynchypin/project-onboard/skills/to-spec/SKILL.md

to-spec

Skill0 starsChanged 3 months agoMITView on GitHub

Synthesize a specification from the completed wayfinder map. Never runs its own interview — it only writes down what wayfinder's grilling tickets already established, at a depth proportional to the project's documentation tier.

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 10 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

  • +2 more from aws

The file

We split this skill into the rules it gives an agent

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 182 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Use domain vocabulary from CONTEXT.md and respect existing ADRs.

    line 21
  2. Very specific:

    Use /codebase-design seam discipline: place seams at volatile boundaries, not at every boundary.

    line 25
  3. Very specific:

    Script tier: no separate spec file. The CONTEXT.md summary from wayfinder grilling is enough.

    line 30
  4. Distinctive:

    No file paths (those belong in tickets).

    line 46
  5. Distinctive:

    Do not add scope that wasn't discussed: If something seems like an obvious gap, flag it as a question back to the user.

    line 50
  6. Distinctive:

    Evidence gate: every implementation decision in the spec must trace to a resolved decision on the map — quote or reference it.

    line 53
  7. Distinctive:

    Never conduct new interview questions — that's wayfinder's job.

    line 65
  8. Distinctive:

    Never produce a spec for script-tier projects.

    line 66
  9. Distinctive:

    Never add scope beyond what was discussed on the wayfinder map.

    line 67

“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

Synthesis only. Takes the accumulated decisions from a completed wayfinder map and writes them into a formal spec. If the map hasn't actually answered something this needs, that's a sign the map wasn't complete — go back to wayfinder and add a ticket rather than inventing an answer.

Process

  1. Read .agent/state.json to get the doc_tier and confirm status is "mapping" with all map tickets resolved. Read the wayfinder map at map_ref.
  2. Explore the repository to understand the current codebase state. Use domain vocabulary from CONTEXT.md and respect existing ADRs.
  3. Identify testing seams — prefer existing public boundaries. If new seams are needed, propose them at the highest architectural level. Use /codebase-design seam discipline: place seams at volatile boundaries, not at every boundary. One adapter = hypothetical seam; two adapters = real seam.

  4. Write the spec at a depth matching the tier (reference/doc-tiers.md):

    • Script tier: no separate spec file. The CONTEXT.md summary from wayfinder grilling is enough; skip straight to skills/to-tickets/SKILL.md.
    • Tool tier: a short spec (~half page) covering problem statement, solution, and 3-6 acceptance criteria.
    • App / system tier: full spec using the template below.

    Spec template (app/system tier)

    • Problem statement — what the user is experiencing.
    • Solution — what the user will experience once done.
    • User stories — numbered, "As a [role], I want [action], so that [outcome]" format.
    • Implementation decisions — modules, interfaces, architectural choices. Use /codebase-design vocabulary (depth, seam, module, adapter, locality) when describing boundaries and interfaces. No file paths (those belong in tickets).
    • Testing decisions — seams, modules needing tests, prior art.
    • Out of scope — explicitly excluded items.

  5. Do not add scope that wasn't discussed. If something seems like an obvious gap, flag it as a question back to the user.

    Evidence gate: every implementation decision in the spec must trace to a resolved decision on the map — quote or reference it. If a decision the spec needs isn't on the map, that's incomplete fog: go back to wayfinder and add a ticket. Do not invent the answer here.

  6. Save to docs/agents/spec.md and update .agent/state.json status to "implementing".
  7. Hand off to skills/to-tickets/SKILL.md directly.

What this skill must never do

  • Never conduct new interview questions — that's wayfinder's job.
  • Never produce a spec for script-tier projects.
  • Never add scope beyond what was discussed on the wayfinder map.

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.

Check your setup, free