Guidance
Skill ActiveControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
To provide developers with a powerful tool for precisely controlling LLM output, guaranteeing valid structured formats like JSON and XML, and building complex multi-step generation workflows.
Features
- Control LLM output syntax with regex and grammars
- Guarantee valid JSON/XML/code generation
- Enforce structured formats (dates, emails, IDs)
- Build multi-step workflows with Pythonic control flow
- Reduce latency vs traditional prompting
Use Cases
- When you need to guarantee valid JSON output for an API response.
- When enforcing a specific date or email format for user input.
- When building agent workflows that require structured intermediate thoughts or observations.
- When reducing token waste and latency by directly generating valid outputs.
Non-Goals
- Performing LLM inference directly; it relies on configured backends.
- Handling arbitrary file system operations or system commands.
- Replacing the core functionality of LLM providers like OpenAI or Anthropic.
Trust
- warning:Issues AttentionIn the last 90 days, 17 issues were opened and 4 were closed, indicating a low closure rate of 23.5%, suggesting slow response times for open issues.
Execution
- info:Pinned dependenciesDependencies are listed in SKILL.md but not explicitly pinned with lockfiles, which could lead to versioning conflicts.
Installation
npx skills add davila7/claude-code-templatesRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
Trust Signals
Similar Extensions
Guidance
99Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework
Arize Prompt Optimization
100Optimizes, improves, and debugs LLM prompts using production trace data, evaluations, and annotations. Extracts prompts from spans, gathers performance signal, and runs a data-driven optimization loop using the ax CLI. Use when the user mentions optimize prompt, improve prompt, make AI respond better, improve output quality, prompt engineering, prompt tuning, or system prompt improvement.
Prompt Optimization
100Applies prompt repetition to improve accuracy for non-reasoning LLMs
Teach Guidance
100Guide a person in becoming a better teacher and explainer. AI coaches content structuring, audience calibration, explanation clarity, Socratic questioning technique, feedback interpretation, and reflective practice for technical presentations, documentation, and mentoring. Use when a person needs to present technical content and wants preparation coaching, wants to write better documentation or tutorials, struggles to explain concepts across expertise levels, is mentoring a colleague, or is preparing for a talk or knowledge-sharing session.
Chat Format
100Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval
Oh My Claudecode
100Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly