Pythoughts-labs
OrganizationNext-generation AI coding agent for your terminal — reads code, edits files, runs tools, and integrates with editors via ACP.
Categories
Indexed Skills (31)
release
Execute the release workflow for Pythinker CLI packages.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
subagent-driven-delegation
Execute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by a verified Claude Architect Producer — isolated worktree, frozen Candidate Artifact, independent verification, fresh-context review, runtime-gated acceptance. Use when executing a multi-task plan through delegation rather than editing directly.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
gen-rust
Sync Rust implementation with Python changes (exclude UI/login) by reviewing recent changes, mapping modules, porting logic, and updating tests.
worktree-status
Audit all git worktrees in the current project. Use when the user asks about worktree status, which branches are merged, which have uncommitted changes, or which worktrees can be safely cleaned up.
agent-creator
Author a new project-specific Pythinker subagent (a specialist like "migration-reviewer" or "api-contract-checker") with a correct spec, a persona-rich system prompt, and a structured output contract. Use when the user wants to create, scaffold, or design a custom agent / subagent, or asks how Pythinker agent YAML / markdown agent files, tool scoping, or the extend-inheritance schema work.
cleanup-audit
Whole-repo audit for over-engineering and accidental complexity. Scans the entire codebase (not just a diff) and returns a ranked, read-only list of what to delete, simplify, or replace with standard-library or platform equivalents. Use when the user asks to "audit the codebase", "find bloat", "what can I delete", or wants a repo-wide simplification pass. For a diff-scoped pass use `pythinker review diff --mode deslopify` instead. One-shot report; applies no fixes.
customize-pythinker
Edit Pythinker's own configuration — agent YAML specs and extend-inheritance, the permission profiles that gate tools, plugin.json, and hook lifecycle events. Use ONLY when the user wants to configure, customize, or extend Pythinker itself (its agents, permissions, plugins, or hooks). For authoring a new agent use agent-creator; for authoring a skill use skill-creator; for general usage Q&A use pythinker-code-help.
judge-minimum-diff
Reduction-ladder and minimum-diff checks the Pythinker judge subagent applies to every non-trivial diff.
judge-overengineering-review
Over-engineering review checklist the parent runs before declaring non-trivial code changes done.
skill-creator
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Pythinker's capabilities with specialized knowledge, workflows, or tool integrations.
check-impl-against-spec
Compare an implementation against a product or technical spec and report gaps with evidence.
create-pr
Prepare a pull request by summarizing changes, verification, risks, and reviewer guidance without adding AI footers.
designer-skill
Prescriptive frontend design guidance via the designer-skill MCP server. Use when the user asks to use designer-skill, improve UI/UX, run the anti-slop ship gate, apply a design system, or enhance pages/components with MCP-backed design references — especially for Pythinker docs and marketing surfaces with DESIGN.md/PRODUCT.md.
diagnose-ci-failures
Diagnose failing CI, lint, typecheck, build, or test logs and propose or implement the smallest verified fix.
fix-errors
Fix concrete errors from logs, failing commands, exceptions, or diagnostics with root-cause-first discipline.
implement-specs
Implement one or more checked-in specs using scout-plan-implement-verify workflow.
pr-walkthrough
Produce a concise reviewer-friendly walkthrough of a PR or diff, including changed areas, behavior, tests, and risks.
pythinker-code-help
Answer Pythinker CLI usage, configuration, and troubleshooting questions. Use when user asks about Pythinker CLI installation, setup, configuration, slash commands, keyboard shortcuts, MCP integration, providers, environment variables, how something works internally, or any questions about Pythinker CLI itself.
reproduce-bug-report
Reproduce a bug report with evidence-first investigation, bounded variants, and a clear repro/non-repro verdict.
resolve-merge-conflicts
Resolve git merge/rebase conflicts safely by preserving both sides' intent and validating the result.
review-pr
Review a pull request or working-tree diff with severity-scored, evidence-backed findings.
spec-driven-implementation
Implement a feature or fix from product/technical specs while checking the final code against the stated requirements.
write-product-spec
Draft a product spec from a user request, issue, or bug report with goals, non-goals, requirements, and acceptance criteria.
write-tech-spec
Draft a technical implementation spec from product requirements and codebase evidence.
sample-plugin
Sample plugin demonstrating the Skills + Tools model. Includes a Python tool (greeting) and a TypeScript tool (calculator).
plan-authoring
How to write an implementation plan the Codex implementer can execute without guessing — the six sections, evidence discipline, scope fencing, and verification design. Read before dispatching any plan.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.