spec SKILL.md skillA

spec from rjmurillo/ai-agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rjmurillo/ai-agents/spec@v1.0.0

Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rjmurillo/ai-agents
Path
src/claude/skills/spec/SKILL.md
Versions recorded
5
Latest version
v1.0.0, committed Oct 31, 2026
First version recorded
Sep 23, 2026
Size
13,488 bytes
Repository stars
49
License
MIT

Turn a problem into testable requirements with acceptance criteria, through a first-principles gate, a memory-first prior-art gate, and a PRD schema. Use when you say `spec this out`, `what should we build`, or `define the requirements`, and run it before plan. Do NOT use to sequence work into milestones (use plan), do NOT use to write the code (use build), and do NOT use to emit the REQ, DESIGN and TASK files directly (use spec-generator, which this invokes).

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

# Spec

<!-- vendor-portability: contributor-scoped citation. The retrospective at
     .project-toolkit/retrospective/2026-05-05-pr-1887-iteration-paradox.md is the evidence for
     why the Step 0 gate exists and lives upstream in the rjmurillo/ai-agents
     repo; it is cited, not resolved at runtime (ADR-083). -->

Define what to build: a problem turned into requirements each of which can be
judged pass or fail, gated twice before any of it is written.

Migrated from the spec command under ADR-064, which makes skills the single
user-invocable surface. The command file is gone, so its path is named here in
plain text rather than as a citation to something a reader could open.

## Triggers

`spec this out`, `what should we build`, `define the requirements`,
`turn this into acceptance criteria`

## Arguments

Spec: $ARGUMENTS

If `$ARGUMENTS` is empty, ask the user what problem to solve. Do not proceed
without a problem statement.

## Process

### Step 0: First Principles Gate (blocking, runs before Step 1)
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rjmurillo/ai-agents/spec@sha256:ec5bd7382148d865

The line at the top of this page pins the label v1.0.0, 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_evqitt5i3b24xuxb.svg)](https://markdownregistry.com/a/art_evqitt5i3b24xuxb)

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

Versions

The registry has recorded 5 versions of this file, between Sep 23, 2026 and Oct 31, 2026, about one every 10 days.

versioncommittedcommitsizeaudit
v1.0.0 latest2026-10-31 78e8145 13,488 BA view · diff
v1.0.02026-10-31 42e4093 13,514 BA view · diff
v1.0.02026-10-19 2b6b398 13,408 BA view · diff
v1.0.02026-09-25 3fda96c 12,115 BA view · diff
v1.0.02026-09-23 efd148e 11,967 BA view

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 (13488 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

rjmurillo/ai-agents · 49 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_evqitt5i3b24xuxb
GET https://markdownregistry.com/api/v1/resolve?ref=rjmurillo/ai-agents/spec
GET https://markdownregistry.com/api/v1/blob/ec5bd7382148d8657385b77fe029a24fa1e0bda986e579cf69fc59806ad00fd3

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 rjmurillo/ai-agents

AGENTS.md@.agents AGENTS.md file
rjmurillo/ai-agents · .agents/AGENTS.md
git:20260929.83dc994 · audit A · 49 stars
CLAUDE.md@.agents CLAUDE.md file
rjmurillo/ai-agents · .agents/CLAUDE.md
git:20260911.1c2f8a7 · audit B · 49 stars
CLAUDE.md@.agents/archive/planning/v0.3.1 CLAUDE.md file
rjmurillo/ai-agents · .agents/archive/planning/v0.3.1/CLAUDE.md
git:20260727.ee75598 · audit B · 49 stars
AGENTS.md@.claude-mem/memories AGENTS.md file
rjmurillo/ai-agents · .claude-mem/memories/AGENTS.md
git:20260916.4e0e8ee · audit A · 49 stars
CLAUDE.md@.claude-mem/scripts CLAUDE.md file
rjmurillo/ai-agents · .claude-mem/scripts/CLAUDE.md
git:20260217.979709c · audit B · 49 stars
CLAUDE.md@.claude-plugin CLAUDE.md file
rjmurillo/ai-agents · .claude-plugin/CLAUDE.md
git:20260217.979709c · audit B · 49 stars
AGENTS.md@.claude AGENTS.md file
rjmurillo/ai-agents · .claude/AGENTS.md
git:20261001.3f27efd · audit A · 49 stars
CLAUDE.md@.claude CLAUDE.md file
rjmurillo/ai-agents · .claude/CLAUDE.md
git:20260916.4e0e8ee · audit A · 49 stars
AGENTS.md@.claude/hooks AGENTS.md file
rjmurillo/ai-agents · .claude/hooks/AGENTS.md
git:20261001.3f27efd · audit A · 49 stars
CLAUDE.md@.claude/hooks CLAUDE.md file
rjmurillo/ai-agents · .claude/hooks/CLAUDE.md
git:20260911.1c2f8a7 · audit B · 49 stars
CLAUDE.md@.claude/hooks/PostToolUse CLAUDE.md file
rjmurillo/ai-agents · .claude/hooks/PostToolUse/CLAUDE.md
git:20260217.979709c · audit B · 49 stars
CLAUDE.md@.claude/hooks/PreCompact CLAUDE.md file
rjmurillo/ai-agents · .claude/hooks/PreCompact/CLAUDE.md
git:20260529.50f1eef · audit A · 49 stars

Every file in rjmurillo/ai-agents

Other files named spec

spec SKILL.md skill
garrytan/gstack · spec/SKILL.md · Turn vague intent into a precise, executable spec in five phases. (gstack)
v0.1.0 · audit A · 140,694 stars
spec SKILL.md skill
snowflake-labs/cocoplus · .cortex/skills/cocobrew/spec/SKILL.md · Enter the Spec phase of CocoBrew. Guides the developer through structured requirements capture: goal, success criteria…
v1.0.4 · audit A · 728 stars
spec SKILL.md skill
atelier-fashion/adlc-toolkit · spec/SKILL.md · Write requirement specs from feature requests
git:20261030.c4e119a · audit A · 173 stars
spec SKILL.md skill
moonlight-lupin/agent-skills · plugins/dev-pipeline/skills/spec/SKILL.md · Use when pinning intent before code — capture a spec (user stories, acceptance criteria, [NEEDS CLARIFICATION]…
v2.1.0 · audit A · 119 stars
spec SKILL.md skill
kerberosclaw/kc_ai_skills · spec/SKILL.md · Use when the user wants a spec-driven development workflow for implementing a feature in the current codebase, from…
v1.10.0 · audit A · 79 stars
spec SKILL.md skill
renzrollon/interlock · skills/spec/SKILL.md · Take a rough intent to a reviewed, implementation-ready OpenSpec change — explore first, generate proposal, design…
git:20261030.e664622 · audit A · 60 stars
spec SKILL.md skill
surething-io/cockpit · skills/spec/SKILL.md · Turn agreed requirements or a QA brief into an implementation-ready specification: behavior, contracts, boundaries…
git:20261103.24ec40a · audit A · 44 stars
spec SKILL.md skill
kriscard/skills · skills/dev/spec/SKILL.md · Builds reviewed requirements, technical design, and an executable implementation plan from an issue URL or requirements…
git:20261028.c86455e · audit A · 15 stars

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