praxis-skills
Battle-tested coding, review, research, and release workflows
All Skills in This Repository (43)
Pure Emerald Level Indicatorsarchitecture-reviewer
Score system architectures across seven weighted dimensions with evidence-based findings.
debug-investigator
Guide hypothesis-driven debugging with ranked hypotheses and bisection strategies.
to-markdown
Convert files and URLs to Markdown using MarkItDown with OCR and transcription.
mcp-to-skill
Convert MCP server tool schemas into validated SKILL.md packages with token-savings estimates.
remotion-video
Create frame-accurate videos with React components and Remotion.
manuscript-review
Detect structural, logical, and citation defects in academic manuscripts.
concept-to-video
Create animated explainer videos from conceptual descriptions using Manim.
regex-builder
Convert positive and negative examples into tested regex patterns with Python and JavaScript code.
sql-optimizer
Analyze SQL queries and EXPLAIN output to recommend indexes and rewrites.
manuscript-provenance
Trace manuscript data values to their generating code and pipelines.
static-web-artifacts-builder
Build single-file HTML artifacts with inline CSS and SVG.
web-fetch
Retrieve web content and API responses as markdown or structured JSON.
Frequently Asked Questions
FAQPage SchemaHow to install praxis-skills?โผ
Run `npx skills add Mathews-Tom/praxis-skills --all -g -y` in your terminal to install the full package collection globally.
What does this collection actually do?โผ
It gives your coding agent 100+ tested workflows for planning, building, reviewing, and shipping software, plus research, content, and diagram skills. Each package defines exact steps, quality gates, and failure handling for a specific task.
How do the orchestrator agents work together?โผ
The team-lead agent decomposes complex requests and delegates to specialists like project-architect, full-stack-builder, and release-captain in sequence or parallel. Each agent hands structured output to the next, so multi-phase work runs end to end.
Does it work with Claude Code and other agents?โผ
Yes. All packages follow the standard SKILL.md and AGENT.md formats and run in Claude Code, OpenClaw, Cursor, and compatible agent runtimes.
Can I use it without prompt engineering experience?โผ
Yes. You describe the outcome in plain English, such as 'ship this' or 'audit the codebase', and the matching agent triggers automatically with its full workflow built in.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core