Pierre Schurmann
Community@escotilha · Brazil
Agent Skills by Pierre Schurmann
Showing 54 vetted skills indexed across 3 GitHub repositories.
research
Convert URLs and images into relevance-scored improvement recommendations for Claude Code projects.
demo
Generate reproducible markdown demo documents with executed code output.
local-inference
Route LLM requests to local MLX or Ollama models with cloud fallback.
officecli
Edit and validate .docx, .xlsx, and .pptx files via a dependency-free CLI.
agent-browser
Automate browser navigation and interaction for QA evidence collection.
gbrain
Builds a PostgreSQL-native hybrid RAG knowledge brain from Markdown notes and conversations.
llm-eval
Build an end-to-end LLM evaluation pipeline with synthetic data and CI regression checks.
test-and-fix
Run failing test suites and apply targeted source-code fixes across JavaScript, Python, Go, and Rust.
qmd
Search markdown collections using BM25, vector retrieval, and LLM reranking.
freeze
Restrict Edit and Write operations to a single directory boundary.
careful
Warns before executing destructive Bash and database commands in Claude Code.
pinchtab
Automate local browser interactions via accessibility trees and stable element references.
verify
Run type-check, tests, and build checks for detected tech stacks.
run-local
Set up local dev environments with dependency installation and health checks.
handoff
Append structured progress logs to plan docs and push git commits before context clearing.
firecrawl
Extract and structure public website content into LLM-ready markdown.
investigate
Debugges software failures by collecting symptoms, testing hypotheses, and verifying fixes with regression proof.
platform-sweep
Audit web platform health across UX, code, security, dependencies, and performance.
revert-track
Revert related git commits as a single history-safe operation.
claude-api
Integrate Claude into backends with Messages API and Managed Agents.
codebase-cleanup
Scan codebases recursively to identify unused, redundant, and dead files.
deep-research
Produce investment-memo-grade research reports with evidence hierarchies and citations.
deep-plan
Create research.md and plan.md artifacts before gated code implementation.
get-api-docs
Fetch versioned API documentation for libraries via the chub CLI.