Skip to content

stark-ai-de/agent-skills / incubator/skills/skill-maintenance/skill-authoring-review

skill-authoring-review

Verified

Create or review Agent Skills with correct SKILL.md frontmatter, trigger descriptions, concise workflow design, progressive disclosure, references, scripts, assets, safety rules, and installability. Use when writing a new skill, improving an existing skill, or validating a public skills repo.

FileKindSize
SKILL.mdskill md3.5 KB
references/frontmatter-examples.mdmarkdown864 B
references/skill-quality-rubric.mdmarkdown1.6 KB

references/skill-quality-rubric.md

View on GitHub
# Skill Quality Rubric

Use this rubric for review reports. Score each area from 0 to 3.

| Area                   | 0                              | 1                           | 2                              | 3                                                |
| ---------------------- | ------------------------------ | --------------------------- | ------------------------------ | ------------------------------------------------ |
| Routing                | Missing or vague description   | Has trigger words but broad | Clear triggers and scope       | Clear triggers, exclusions, and object           |
| Focus                  | Multiple unrelated workflows   | Mostly focused but bloated  | One workflow with minor extras | One tight workflow                               |
| Progressive disclosure | Everything in `SKILL.md`       | Some references but unclear | References are linked by need  | Core body is lean and references are precise     |
| Safety                 | Unsafe or undocumented scripts | Safety mentioned vaguely    | Safe defaults and script notes | Safe defaults, approval gates, and risk handling |
| Output                 | No artifact                    | Generic summary             | Concrete report or decision    | Concrete artifact with acceptance criteria       |
| Installability         | Invalid structure              | Valid but untested          | Valid and locally checked      | Valid, cataloged, and smoke-tested               |

Blocking issues include invalid frontmatter, name mismatch, missing description, destructive scripts without approval gates, secret exposure, and copied proprietary text.
brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).Stars: 323kUpdated Claude CodeCodexVerifiedInstall
brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).Stars: 198kUpdated Claude CodeCodexVerifiedInstall