Design, review, and package reusable Agent Skills and SKILL.md files.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "skill-authoring-coach" skill from askskill: 1. Download https://raw.githubusercontent.com/microsoft/cat-agent-skills/main/submissions/skill-authoring-coach/SKILL.md 2. Save it as ~/.claude/skills/skill-authoring-coach/SKILL.md 3. Reload skills and tell me it's ready
Please turn this draft into a submission-ready Agent Skill: complete the SKILL.md structure, clarify triggers, inputs, workflow, output format, and quality checks, and point out what should be moved to references/ or assets/.
A clearer SKILL.md draft plus a suggested folder structure and content split.
Please review this skill package using the Skill Authoring Coach rubric. Score trigger clarity, task focus, instruction quality, portability, safety, and packaging quality, then list required changes.
A scored review table, an overall recommendation, and a list of required changes.
I have a long internal prompt. Help me genericise it into a reusable skill: keep the repeatable workflow, remove organization-specific assumptions, and separate what belongs in SKILL.md, references, assets, or scripts.
A genericised skill plan explaining what should not remain directly in SKILL.md.
Developers, product managers, or writers can use it when they repeatedly run the same AI workflow. It helps define triggers, steps, outputs, and a reusable file structure.
Use it when you already have a draft skill or package but are unsure whether it is clear, focused, and portable enough. It provides a structured review with required changes and an overall recommendation.
When users try to put examples, lookup material, and static templates all into SKILL.md, this skill helps split them appropriately. It suggests moving reference material to references/, static structures to assets/, and adding scripts/ when needed.
The document explains how to design and package reusable Agent Skills. It emphasizes that a good skill should have clear triggers, concise operational steps, guardrails, and quality checks instead of being a long prompt dump. It also distinguishes skills, references, templates, and scripts, recommends a folder structure, outlines what SKILL.md should contain, and provides a six-part review rubric for evaluating skill quality.
Use this skill to help users design, review, genericise, and package reusable Agent Skills.
A good skill is not a long prompt dump. It is a focused, reusable capability with:
Use these distinctions:
If the user tries to put everything into SKILL.md, recommend moving detailed lookup material into references/ and static output structures into assets/.
<skill-folder>/
├── SKILL.md
├── references/ optional
├── assets/ optional
└── scripts/ optional
The SKILL.md should contain:
name and description.SKILL.md where appropriate.Score candidate skills from 0 to 5 on:
## Skill review
Overall recommendation: [Submit / Revise / Keep private]
| Dimension | Score /5 | Notes |
|---|---:|---|
## Required changes
1. [Change]
2. [Change]
3. [Change]
## Suggested folder structure
```text
[folder tree]
## References
This skill includes supporting reference material. Read the relevant reference file when the task needs additional structure, rubric detail, examples, or checklist support.
- `references/skill-design-checklist.md` - use this when additional structure, examples, or checks are useful for the task.
## Quality checklist
Before responding, check:
- The proposed skill has a clear reusable job.
- The trigger description is precise.
- Organisation-specific material is removed or parameterised.
- Long reference content is not overloaded into the main skill file.
- The result is practical for a maker to copy into a skills repository.
It is for designing, reviewing, genericising, and packaging reusable Agent Skills. The focus is turning long prompts into clear, triggerable, reusable skill structures rather than dumping instructions into prose.
The excerpt recommends including frontmatter with name and description, when to use the skill, inputs to look for, workflow steps, output formats, and guardrails with quality checks. Long reference material should move to references/, and static output structures can go into assets/.
According to the document, a skill teaches a repeatable workflow, a reference provides detailed information, a template supplies a reusable output shape, and a script handles deterministic work. If more structure or examples are needed, the document mentions reference files; see the source repository for details.
Prepare and improve negotiations with calm, structured, ethical decision support.
Validate a SharePoint list, analyze it, and return an interactive HTML report link.
Turn whiteboard sketches into polished, editable PowerPoint infographics.
Humanizes and polishes prose so it reads naturally, not AI-generated.
Run a task with a debug command and export a JSON tool trace.
Analyze Teams chats and emails to build a reusable personal writing style profile.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Turn a repeated workflow into a reusable skill file from the current session.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Create, refine, and evaluate AI skills for better performance and triggering accuracy.
Design, evaluate, refine, and package AI skills with an architecture-first workflow.