padosoft-skill-creatorlisted

Use this skill when creating, editing or reviewing an Agent Skill of the padosoft/skills repository, when the user wants to turn a recurring workflow, a checklist or a set of guidelines into a reusable skill, or when they ask where a skill belongs (profile, scope, package) or why the repo CI is failing on catalog, profiles or manifests: it guides the whole creation with scaffolding, the Padosoft conventions and the automated checks. Do not use it to write the technical domain content (that is the job of the skill you are creating) nor to install existing skills (padosoft-skills-router handles that). It also keeps the provenance of the work — dates, customers, people, ids, credentials — out of anything that gets published.
padosoft/skills · ★ 1 · AI & Automation · score 80

Install: claude install-skill padosoft/skills

# Padosoft Skill Creator Creates skills that follow **the Agent Skills specification** and **the `padosoft/skills` conventions**, without having to remember them. The expected outcome: `make all` green on the first try, and a skill that triggers when it is needed, not at random. --- ## 0. What is in this skill | File | Use | |---|---| | `scripts/check_provenance.py` | **Mandatory gate**: fails if a skill carries a date, an address, a credential, an id, a local path, a customer term. `--json` for CI, `--topic-ok` for incident-response skills. | | `scripts/new_skill.py` | Scaffolding: creates `skills/<name>/` with a filled-in SKILL.md, folders and eval files. `--help` for the options. | | `templates/SKILL.template.md` | The skeleton used by the scaffolding, if you need to start by hand. | | `references/checklist.md` | Review checklist before the PR, and the recurring mistakes to avoid. | The validation scripts **live in the repo**, not here: **scripts/build_catalog.py**, **scripts/validate_plugins.py** and **skills/padosoft-email-html-builder/scripts/validate_skill.py** (repo paths, not paths of this skill). --- ## 1. Before writing: is the skill really needed? Answer these three, in order. If any answer is no, stop and say so to the user. 1. **Does the agent get it wrong without these instructions?** If the model already does fine on its own, the skill adds context and not quality. Test it: same prompt without the skill, look at the output. 2. **Is the know-how rea