Automated summary
This skill end-to-end mints a new PMOVES skill: it scaffolds the SKILL.md, lints it, registers it through Archon, and publishes the NATS mint event.
Strengths
- Chains scaffolding, linting, Archon registration and NATS publishing into a single flow
- The lint gate blocks on FAILs such as missing frontmatter or absent 'When to invoke', 'Inputs', 'Outputs' and 'Implementation' sections
- Binds each skill to an authenticated creator identity via Google OAuth / Supabase, with the same RLS rules as agents
- Appends a row to skills/README.md so the constellation catalog stays in sync
Limitations
- The archon:create-skill MCP tool isn't shipped yet, so registration falls back to a curl call or a /tmp manifest stash and may not actually complete
- Halts entirely if the Google OAuth / Supabase wiring isn't live
- Linting is heuristic grep checks and only warns when the description doesn't start with an action verb
Use it when an operator wants to create and register a new composable skill in the PMOVES constellation.
Avoid it for editing existing skills or in non-PMOVES projects that lack Archon and NATS.
Security analysis
CautionThe skill performs legitimate file creation, shell-based linting, a localhost HTTP POST, and NATS event publication. There is no evidence of destructive commands, exfiltration, obfuscation, or disabling of safety controls. However, it uses bash and network operations, so it warrants a caution rating rather than safe.
- •Executes shell commands for scaffolding, validation, and uniqueness checks.
- •Posts manifest to a localhost HTTP API via curl (optional).
- •Publishes events via NATS, which is a network messaging operation.
- •Writes files under .claude/skills and /tmp.
Examples
Mint a new skill called pmoves-room-rotator that rotates room assignments across PMOVES agents; make it user-invocable and set the owning persona to ops@pmoves.ai.Scaffold a SKILL.md for a skill named pmoves-digest that summarizes the daily NATS event stream; it should not be user-invocable (Claude-only).Register a composable skill pmoves-nats-replay, run the skill linter on it, then publish the archon.mint.skill.v1 event.description: Mint a new PMOVES skill through Archon — scaffold SKILL.md, lint, register, publish archon.mint.skill.v1.
Mint a new composable skill into the PMOVES skills constellation. Mirrors /archon:mint-agent for skills.
Usage
Invoke when the operator says "mint a skill", "scaffold a SKILL.md", or "register a composable skill". Produces a SKILL.md under .claude/skills/<name>/, runs the skill linter, registers via Archon (when ready), and publishes the NATS mint event.
Implementation
Step 0 — Authenticate the creator (Google OAuth via Supabase)
Mandatory. Skills are tied to a creator identity (same RLS rules as agents). Follow the Step 0 procedure in /archon:mint-agent to obtain a valid Supabase session JWT with provider: 'google' and email_verified: true. Capture creator_id (Supabase auth.users.id) and creator_email for the skill manifest.
If OAuth wiring is not live, halt — see .claude/context/self-hosted-defaults.md § "Authentication".
Step 1 — Collect the manifest
Ask the operator for:
skill-name— kebab-case (e.g.pmoves-room-rotator).description— single sentence beginning with an action verb; this becomes the frontmatterdescription.user-invocable?— boolean. If false, set frontmatteruser-invocable: false(Claude-only).owning-persona— accountable agent or human; defaults to authenticated creator email from Step 0.- Optional:
tools,dependencies(other skills it composes with).
Validate uniqueness:
test ! -d ".claude/skills/<skill-name>" || { echo "skill exists"; exit 1; }
Step 2 — Scaffold the skill
Create .claude/skills/<skill-name>/SKILL.md:
---
name: <skill-name>
description: <description>
user-invocable: <true|false>
owning_persona: <owning-persona>
minted_at: <YYYY-MM-DD>
---
# <Skill-Name>
## When to invoke
<one paragraph trigger conditions>
## Inputs
<bullet list>
## Outputs
<bullet list>
## Implementation
<script reference or inline steps>
If the skill ships a script, also scaffold .claude/skills/<skill-name>/scripts/<entry>.sh (or .py) with a shebang and set -euo pipefail.
Step 3 — Lint
Run frontmatter + structure checks:
# Frontmatter present
head -1 .claude/skills/<skill-name>/SKILL.md | grep -q '^---$' || echo "FAIL: missing frontmatter"
# Description starts with verb (heuristic)
grep -E '^description: [A-Z][a-z]+ ' .claude/skills/<skill-name>/SKILL.md || echo "WARN: description should start with an action verb"
# Required sections
for s in "When to invoke" "Inputs" "Outputs" "Implementation"; do
grep -q "^## $s$" .claude/skills/<skill-name>/SKILL.md || echo "FAIL: missing section '$s'"
done
Block on any FAIL.
Step 4 — Register through Archon
Contract for the future archon:create-skill MCP tool:
{
"name": "create-skill",
"input": {
"skill_name": "<skill-name>",
"description": "<description>",
"user_invocable": <bool>,
"path": ".claude/skills/<skill-name>/SKILL.md"
},
"output": { "skill_id": "<uuid>", "registry_url": "<url>" }
}
Until the MCP tool ships, optionally curl -sf -X POST http://localhost:8091/api/skills with the manifest. If the endpoint is unavailable, stash the manifest under /tmp/skill-manifest.json and continue.
Step 5 — Publish NATS mint event
{
"subject": "archon.mint.skill.v1",
"payload": {
"skill_id": "<uuid|null>",
"skill_name": "<skill-name>",
"path": ".claude/skills/<skill-name>/SKILL.md",
"user_invocable": <bool>,
"owning_persona": "<owning-persona>",
"ts": "<RFC3339>"
}
}
Publish via pmoves-nats-mcp nats_publish tool if configured, otherwise print the payload + the nats pub archon.mint.skill.v1 ... fallback.
Step 6 — Cross-link
Append a row to skills/README.md (Status: provisional) so the constellation surface reflects the new skill.
Notes
- Wave-0 Task 9 in the gap-fill roadmap.
- Wave-1 dependency: Supabase
archon_minted_artifactstable (W1.10). - Wave-2 dependency:
archon.mint.skill.v1publishers on the bus (W2.1). - Companion:
/archon:mint-agentfor agents,/archon:creator-onboardfor human creators.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/mint-a-composable-skill-mrzxurlk/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/mint-a-composable-skill-mrzxurlk' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/mint-a-composable-skill-mrzxurlk/download' --output '.skill-downloads/mint-a-composable-skill-mrzxurlk/SKILL.md.part' && mv '.skill-downloads/mint-a-composable-skill-mrzxurlk/SKILL.md.part' '.skill-downloads/mint-a-composable-skill-mrzxurlk/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/mint-a-composable-skill-mrzxurlk/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.