Is the To Spec skill free?

Yes. The skill itself is free from rengwu/wayfinder-maps. SkillProof publishes the install command and an independent test verdict at no cost.

What is the To Spec SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 3/5, output vs. baseline 9/10, docs & honesty 5/5.

How do I install To Spec?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use To Spec with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

To Spec

Turns the conversation you already had into a repo-aware spec in .plan/

by rengwu · rengwu/wayfinder-maps

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 28, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Jul 30, 2026 · b26d594

⚠ This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 28, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Ran it against a real 25-line Python CLI plus a feature conversation, and diffed the result with a no-skill spec: 21 user stories against zero, and 0 file-path or code references against 4 that would rot on the first refactor. The seam step is where it earns its keep - it drove the test plan onto the existing main(argv) entry point and flagged that the note file has to be redirectable per test, a gap the baseline spec missed and that we confirmed by execution (a test-style call wrote straight into $HOME/.notes.json). It also caught four behaviours the baseline dropped, including what a rename of a non-existent label should do. The catch is the frontmatter carries disable-model-invocation, so it never activates from a phrasing like 'write this up as a spec' - you have to type /to-spec, which the repo's own skills/README documents honestly. It lives under skills/.optional/, a hidden directory you will not spot browsing the repo on GitHub.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 3/5
Output vs. baseline 9/10
Docs & honesty 5/5

What To Spec does

Synthesizes the current conversation and the codebase into a spec (PRD) written to .plan/<slug>/spec.md, with no interview step. It forces a test-seam sketch before writing and a fixed section set: problem, solution, an exhaustive user-story list, implementation decisions, testing decisions and out-of-scope. Invoked by typing /to-spec after you have finished discussing a feature.

How to install To Spec

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger To Spec

/to-spec Turns the conversation you already had into a repo-aware spec in .plan/

It also activates on plain-language prompts like these:

/to-spec turn what we just discussed about tagging into a written PRD
Save a spec to .plan for the notes feature we just finished designing
Write a PRD from this conversation with an exhaustive user story list

Frequently asked questions

Is the To Spec skill free?: Yes. The skill itself is free from rengwu/wayfinder-maps. SkillProof publishes the install command and an independent test verdict at no cost.
Does To Spec work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 28, 2026. Verdict: Works with setup. Ran it against a real 25-line Python CLI plus a feature conversation, and diffed the result with a no-skill spec: 21 user stories against zero, and 0 file-path or code references against 4 that would rot on the first refactor. The seam step is where it earns its keep - it drove the test plan onto the existing main(argv) entry point and flagged that the note file has to be redirectable per test, a gap the baseline spec missed and that we confirmed by execution (a test-style call wrote straight into $HOME/.notes.json). It also caught four behaviours the baseline dropped, including what a rename of a non-existent label should do. The catch is the frontmatter carries disable-model-invocation, so it never activates from a phrasing like 'write this up as a spec' - you have to type /to-spec, which the repo's own skills/README documents honestly. It lives under skills/.optional/, a hidden directory you will not spot browsing the repo on GitHub.
What is the To Spec SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 3/5, output vs. baseline 9/10, docs & honesty 5/5.
How do I install To Spec?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use To Spec with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.