to-spec SKILL.md skillA

to-spec from frankxai/claude-skills-library is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add frankxai/claude-skills-library/to-spec@git:20261112.651c2dc

Pins git:20261112.651c2dc in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
frankxai/claude-skills-library
Path
absorbed/engineering/to-spec/SKILL.md
Versions recorded
1
Latest version
git:20261112.651c2dc, committed Nov 12, 2026
Size
2,916 bytes
Repository stars
47
License
MIT

Turn what has already been discussed into a spec and file it as a GitHub issue on the product repo, without interviewing the user again. Use when the user says write this up as a spec, open an issue for this, or turn this into a ticket, after the decisions are made.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# To spec

The conversation already holds the decisions. This skill writes them down once, in the product repo's issue tracker, so the next agent picks up a spec instead of a transcript. It does not ask new questions; if a decision is missing, it is listed as open.

## Before writing

1. **Pick the repo.** The product repo that will change, verified by path, `git rev-parse --show-toplevel` and origin. Never the estate root. Linear is archive unless the user asks for it.
2. **Check for an existing issue.** `gh issue list -R <owner/repo> --search "<keywords>"`. If one tracks this slice, comment the spec there instead of opening a duplicate.
3. **Read the area.** Use the repo's own vocabulary and respect any ADR that covers it.
4. **Name the test seam.** Prefer an existing seam, as high as possible, ideally one. Say it back to the user in one line and continue unless they object.

## The issue body

```
## Problem
What the user faces, in their words.

## Outcome
What is true when this ships, from the user's side.

## User stories
1. As a <actor>, I want <capability>, so that <benefit>.
(Enough to cover the feature, including the failure and empty states.)

## Decisions
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_rdkdemufevg4yik4/18de6b9342b02eef1eb27baf43b8fe10d3c8ddc6495f331f485c94670e42d76f.json

Then /plugin install to-spec@markdownregistry-rdkdemufevg4yik4 in Claude Code. It installs git:20261112.651c2dc, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add frankxai/claude-skills-library/to-spec@sha256:18de6b9342b02eef

The line at the top of this page pins the label git:20261112.651c2dc, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_rdkdemufevg4yik4.svg)](https://markdownregistry.com/a/art_rdkdemufevg4yik4)

3 badge image fetches in 30 days. What the badge shows.

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in frankxai/claude-skills-library/to-spec since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of to-spec from somewhere else? Ask it: where did my to-spec come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 1 version of this file, committed on Nov 12, 2026.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20261112.651c2dc latest2026-11-12 651c2dc 2,916 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2916 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

frankxai/claude-skills-library · 47 stars · license MIT · pushed 2026-11-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_rdkdemufevg4yik4
GET https://markdownregistry.com/api/v1/resolve?ref=frankxai/claude-skills-library/to-spec
GET https://markdownregistry.com/api/v1/blob/18de6b9342b02eef1eb27baf43b8fe10d3c8ddc6495f331f485c94670e42d76f

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from frankxai/claude-skills-library

excellence-review SKILL.md skill
frankxai/claude-skills-library · .grok/skills/excellence-review/SKILL.md · Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso…
git:20260820.5d4ee7a · audit A · 47 stars
harness-integration SKILL.md skill
frankxai/claude-skills-library · .grok/skills/harness-integration/SKILL.md · ACOS Grok bridge. SessionStart loads repo-mastery + excellence gates. PreToolUse enforces rules read + suggests harness…
git:20261014.6571e8d · audit A · 47 stars
multi-harness-orchestrator SKILL.md skill
frankxai/claude-skills-library · .grok/skills/multi-harness-orchestrator/SKILL.md · Automatically detect tasks suited for delegation to other agent harnesses (Claude Code as canonical, agy/antigravity…
git:20260820.5d4ee7a · audit A · 47 stars
repo-mastery SKILL.md skill
frankxai/claude-skills-library · .grok/skills/repo-mastery/SKILL.md · Master ACOS, FrankX, Starlight-Intelligence-System, arcanea, claude-code-config and full starlight/repos ecosystem…
git:20261014.6571e8d · audit A · 47 stars
AGENTS.md AGENTS.md file
frankxai/claude-skills-library · AGENTS.md
git:20261026.78c1e18 · audit F · 47 stars
CLAUDE.md CLAUDE.md file
frankxai/claude-skills-library · CLAUDE.md
git:20261024.cc3ca00 · audit A · 47 stars
diagnosing-bugs SKILL.md skill
frankxai/claude-skills-library · absorbed/engineering/diagnosing-bugs/SKILL.md · Find the cause of a hard bug, outage or slowdown by building a red-capable feedback loop before forming any theory. Use…
git:20261112.651c2dc · audit B · 47 stars
doubt-driven-development SKILL.md skill
frankxai/claude-skills-library · absorbed/engineering/doubt-driven-development/SKILL.md · Cross-examine a non-trivial decision with a fresh, adversarial reviewer before it stands, ideally a different model…
git:20261112.651c2dc · audit A · 47 stars
source-driven-development SKILL.md skill
frankxai/claude-skills-library · absorbed/engineering/source-driven-development/SKILL.md · Ground framework, SDK and API code in the current official docs before writing it, and cite them. Use before code…
git:20261112.651c2dc · audit A · 47 stars
agent-harness-construction SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/agent-harness-construction/SKILL.md · Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a…
git:20261010.682b2ce · audit A · 47 stars
context-budget SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/context-budget/SKILL.md · Count what a session loads before adding another skill or MCP server. Use when the default prompt is heavy, a new…
git:20261010.682b2ce · audit A · 47 stars
cost-aware-llm-pipeline SKILL.md skill
frankxai/claude-skills-library · absorbed/harness/cost-aware-llm-pipeline/SKILL.md · Pick the smallest model that can finish the task, and record the class of work. Use when routing a search, a multi-file…
git:20261010.682b2ce · audit A · 47 stars

Every file in frankxai/claude-skills-library

Other files named to-spec

to-spec SKILL.md skill
mattpocock/skills · skills/engineering/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20260819.5c89081 · audit A · 327,521 stars
to-spec SKILL.md skill
vinvcn/mattpocock-skills-zh-cn · skills/engineering/to-spec/SKILL.md · 把当前对话转成 spec 并发布到项目 issue tracker:不做访谈,只综合已经讨论的内容。
git:20261008.5be0dc1 · audit A · 5,886 stars
to-spec SKILL.md skill
kunolu/640-skills · sbtd-workflow-onboard/assets/external-skills/stable/skills/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20260827.561ec6a · audit A · 559 stars
to-spec SKILL.md skill
asymmetric-al/core · .agents/skills/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20261023.f970aa0 · audit A · 370 stars
to-spec SKILL.md skill
hitesit/real-scientist-skills · skills/engineering/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20260819.5c89081 · audit A · 38 stars
to-spec SKILL.md skill
svyatov/supermatt · skills/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20261018.f19c25a · audit A · 30 stars
to-spec SKILL.md skill
vodailocz/kilo-kit-mcp · skills/engineering/to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20260821.05c0d52 · audit A · 28 stars
to-spec SKILL.md skill
j-star-films-studios/vibecode-protocol-suite · assets/.agent/skills/agent-engineering/conversation-to-spec/SKILL.md · Turn the current conversation into a spec and publish it to the project issue tracker: no interview, just synthesis of…
git:20260821.1b830a3 · audit A · 27 stars

Browse by kind, by grade A, or by owner.