Menu

Individual skill

promoter-draft

0upvotes

Turn one recurring pattern from a promoter scan into a complete, reusable skill in this library's format: a SKILL.md with a strong trigger description, required inputs, a framework, an output template, quality checks, anti-patterns, and three worked examples derived from the user's real prompts, plus the bundle manifest. Use when asked to draft a skill from this pattern, promote this pattern into a skill, write the SKILL.md for what I keep asking, or as the second step of the promote loop. Produces a ready-to-test skill folder that anyone, not just the original user, can use.

plugins/pm-skill-promoter/skills/promoter-draft/SKILL.md

Read pinned source

Source commit f7c90bc09ee05dc25cf257bdb1826f2c2552c2cb

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
No
Observed behavior
Network or broad shell
Last checked
Nov 9, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
1,539
Repository last updated
Nov 9, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Promoter Draft

A recurring prompt tells you what someone wants; a skill tells the assistant how to do it well every time. This skill takes one pattern from the scan report and writes the skill properly: the trigger description a model can match on, the inputs to ask for, the method, the output shape, and the checks that keep it honest. The worked examples come from the user's real prompts, generalised so the skill is useful to strangers.

Second step of the promote loop. Follows `promoter-scan`; feeds `promoter-test`.

## What This Skill Produces

- **`skills/<name>/SKILL.md`** in the library's format, with a description that has all three parts: what it does, "Use when ..." in the user's own vocabulary, "Produces ..." the concrete artefact
- **Three worked examples** inside the skill (input, abridged output), derived from the pattern's example prompts with anything specific to one person, employer or dataset removed
- **A `plugin.json` stanza** for the bundle it joins, and any supporting reference file the framework needs
- **A collision note**: the nearest existing skills by name and by job, and why this one is different

## Required Inputs
Back to top