golemcloud/golem/golem-annotate-agent-effect
- community
Checking that the SKILL.md file is still in the repository.
Adding prompt hints and descriptions to Effect-based Golem agents and methods. Use when an @golemcloud/effect-golem agent needs AI/LLM discovery metadata or human-readable method documentation.
Install
npx vskill@latest install golemcloud/golem/golem-annotate-agent-effectSKILL.md
Annotating Effect Agents and Methods
Effect Golem agents declare AI/LLM discovery metadata as fields in their defineAgent(...) and method(...) specs. Do not translate decorator syntax from another SDK: Effect agents do not use annotation decorators.
Metadata Fields
- Top-level
descriptiondescribes the agent type and its overall purpose. - Top-level
promptHint, when needed, tells an LLM when to construct or select an agent instance. - Method-level
promptHinttells an LLM when to invoke that method. - Method-level
descriptiondocuments the method's behavior, inputs, outputs, and edge cases.
The method name exposed by Golem is the key in the methods record, so use TypeScript camelCase there. A request for a method's “prompt” annotation maps to the Effect SDK's promptHint field.
Agent and Method Metadata
Set agent metadata directly on the defineAgent spec and method metadata directly inside method(...):
When editing an existing stateful agent, preserve its snapshot and implementation structure. Add the method spec under methods, then add a matching Effect-returning handler to the object returned by methods. Metadata belongs only on the specs; it does not change handler behavior.
Key Constraints
- Import
defineAgentandmethodfrom@golemcloud/effect-golem, andEffectandSchemafrom
effect.
- Use
descriptionandpromptHint, notprompt, decorator syntax, or helpers from
@golemcloud/golem-ts-sdk.
- Keep method
input,success, and optionalerrorschemas unchanged when adding metadata. - Both metadata fields are optional; omit them for methods that should not carry discovery hints.
- Keep the top-level
.implement({ ... })registration and the implementation module's side-effect
import from src/main.ts.
- Run
golem buildand redeploy after changing metadata so discovery reports the new values.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckinggolem-skills/skills/effect/golem-annotate-agent-effect/SKILL.md
Popularity
- Repository stars
- 1,521
- Repository forks
- 210
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/golemcloud/golem/golem-annotate-agent-effect)