By chriswch
Spec-driven workflows: /craft for full TDD with checkpoints, /forge for fast delivery, plus reusable stage skills.
Closes the loop after TDD by verifying the implementation holistically against the behavioral spec, reconciling spec-vs-reality divergences, capturing emerged design knowledge, and routing to the next slice or done. Use after driving-tdd completes. Triggers on "verify this", "are we done?", "check against the spec", "close out this story", "what's next?", "wrap up", or when all TDD acceptance criteria are green and the developer needs to confirm completion and decide the next step.
Splits a Feature Brief into an ordered slice map of thin, vertical story slices — each capturing scope and build order, while deferring detailed acceptance criteria to downstream `clarifying-intent`. Use after clarifying-intent produces a Feature Brief, when a feature is too large for one story. Triggers on "split this into stories", "slice this feature", "what should we build first", "create a slice map", or when a Feature Brief needs to be broken into deliverable increments.
Produces a lightweight design sketch from a Story-Level Behavioral Spec by locating affected files in the codebase, matching existing patterns, and proposing a single implementation direction — just enough to write the first failing test. Use before TDD when the implementation path is non-obvious, after clarifying-intent or slicing-stories. Triggers on "where do I start?", "which files do I change?", "how should I implement this?", mapping a spec to code, or pre-implementation codebase exploration.
Clarifies ambiguous ideas, features, tasks, user stories, or problems by eliciting intent, constraints, unknowns, risks, and success criteria; asks focused questions; then produces a structured Feature Brief or Story-Level Behavioral Spec with testable acceptance criteria. Use when a request is vague or underspecified, when scoping work, when a user says "I have a rough idea", "help me scope this", "what should we build", "spec this out", or before planning and coding.
Write and revise all prose with clarity, precision, and concision. Use this skill whenever producing written content longer than a few sentences: documentation, specifications, design sketches, explanations, briefs, READMEs, PR descriptions, commit messages, technical writing, or any content a reader will consume. Also trigger when the user asks to improve, tighten, edit, rewrite, or revise existing prose — even if they don't say 'clear writing' explicitly.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Spec-driven software engineering workflows for Claude Code and Codex, shipped as agent skills.
Praxis is a collection of skills that take a request through clarification, slicing, design, implementation, review, and verification — and two orchestrator entry points (craft and forge) that chain them.
Add the Praxis plugin from your marketplace, or install the plugin/ directory as a local plugin. The plugin manifest is at plugin/.claude-plugin/plugin.json.
Add the Praxis plugin from your marketplace, or install the plugin/ directory as a local plugin. The plugin manifest is at plugin/.codex-plugin/plugin.json.
/craft and /forge slash commands (plugin/commands/craft.md, plugin/commands/forge.md).craft and forge skills (plugin/skills/craft/SKILL.md, plugin/skills/forge/SKILL.md).Both entry points orchestrate the same underlying skills.
Full TDD pipeline with user checkpoints between stages.
clarifying-intent → [slicing-stories] → sketching-design → driving-tdd
→ code-reviewing → code-improving → verifying-and-adapting
Fast pipeline with one user checkpoint at the spec, then auto-advance.
clarifying-intent → [slicing-stories] → sketching-design → rapid-implementing
→ code-reviewing → code-improving
| Skill | Purpose |
|---|---|
clarifying-intent | Turn an underspecified request into a Feature Brief or Story-Level Behavioral Spec. |
slicing-stories | Split a Feature Brief into an ordered slice map of thin, vertical stories. |
sketching-design | Produce a lightweight design sketch — change map, pattern match, first test. |
driving-tdd | Drive Red → Green → Refactor cycles, one acceptance criterion at a time. |
rapid-implementing | Implement each acceptance criterion without writing new tests. |
code-reviewing | Independent five-layer review (data, special cases, complexity, breaking changes, practicality). |
code-improving | Apply fixes for critical/high/medium review findings. |
verifying-and-adapting | Reconcile spec vs. reality, update the spec, recommend the next action. |
clear-writing | Revise prose for clarity, precision, and concision. Reusable across skills. |
Every skill follows the same prompt-in / prose-out contract:
There is no enforced artifact layout. Skills focus on what they resolve; the calling agent or user owns input and output handling.
MIT
npx claudepluginhub chriswch/praxis --plugin praxisHarness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Superpowers Plus core skills library for Claude Code: planning, execution routing, TDD, debugging, and collaboration workflows
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development