stevesolun/ctx / .agents/skills/writing-great-skills
writing-great-skills
VerifiedDesign or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.
| File | Kind | Size |
|---|---|---|
| GLOSSARY.md | markdown | 1.9 KB |
| SKILL.md | skill md | 1.6 KB |
| agents/openai.yaml | config | 149 B |
GLOSSARY.md
View on GitHub# Skill-design glossary
Use these terms as optional shared vocabulary, not as a required ontology.
## Invocation
- **Explicit invocation:** the user deliberately selects a skill. Prefer it
when the workflow is rare, consequential, or highly opinionated.
- **Implicit invocation:** the host selects a skill from its description.
Descriptions should distinguish positive triggers from nearby non-triggers.
- **Context load:** metadata or instructions occupying attention before they
are relevant.
- **Router:** a small skill that recommends another skill or short sequence.
## Information hierarchy
- **Entrypoint:** `SKILL.md`; contains essential selection and execution
guidance.
- **Reference:** detail loaded only for a relevant branch.
- **Asset:** material used in output without needing to become prompt context.
- **Script:** deterministic code for repeated or reliability-sensitive work.
- **Progressive disclosure:** exposing detail only when the current branch
needs it.
- **Single source of truth:** one authoritative home for each instruction or
contract.
## Steering
- **Degree of freedom:** how much implementation judgment the workflow leaves
to the model.
- **Guardrail:** a constraint justified by concrete safety, correctness, or
recovery cost.
- **Rubric:** criteria for evaluating output without prescribing one exact
implementation.
- **Completion evidence:** observable proof that the requested outcome was
reached.
## Maintenance failures
- **Duplication:** the same instruction in more than one place.
- **Sediment:** obsolete guidance retained because deletion feels risky.
- **Sprawl:** entrypoint detail that belongs behind a branch-specific reference.
- **No-op:** an instruction that does not change behavior from the model's
default.
- **Overconstraint:** a fixed procedure applied where context admits safer or
better alternatives.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |
| 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: 198k | Updated | Claude CodeCodex | Verified | Install |