plugin-settings
Per-project plugin configuration via .local.md files — covers the .claude/plugin-name.local.md pattern for storing user-configurable settings with YAML frontmatter and markdown body. Use when implementing plugin settings, reading YAML frontmatter from hooks, creating configuration-driven behavior, managing agent state files, or adding per-project plugin configuration. Covers file structure, parsing techniques, common patterns (temporarily active hooks, agent state management, configuration-driven behavior), security considerations, and best practices.
prompt-optimization
Optimize CLAUDE.md files and Skills for Claude Code CLI. Use when reviewing, creating, or improving system prompts, CLAUDE.md configurations, or Skill files. Transforms negative instructions into positive patterns following Anthropic's official best practices.
python3-add-feature
Executes a four-phase feature addition workflow (Discovery, Planning, TDD Implementation, Verification) for Python projects. Use when adding a new feature end-to-end — discovering project structure and integration points, drafting a feature spec with MoSCoW-prioritized requirements and BDD acceptance criteria, implementing via test-first TDD cycles, then verifying with ruff lint, ty type checks, and 100% coverage on new code.
python3-bug
Debug functional issues in Python code using specs, logs, and observed behavior. Use when a feature isn't working as specified, when investigating runtime errors, or when scoping a problem before implementing a fix.
python3-cli
Use when building CLI applications with Typer and Rich — creating commands with Annotated parameter syntax, defining arguments and options, composing subcommands, async concurrent CLI tasks with semaphores, testing with CliRunner, PEP 723 shebang scripts, progress bars, Rich terminal output, or non-TTY display width handling.
python3-core
Activates on any Python task involving *.py files, uv, ruff, ty, pytest, or pyproject.toml — establishes Python 3.11+ coding standards, SOLID design guidance, strict typing policy, testing defaults (pytest + pytest-mock), tooling expectations (uv, ruff, ty, hatchling), and code smell detection as design signals. Routes to specialist skills for TDD, CLI, web, data, async, or constrained environments.
python3-data
Specialist skill for Python data engineering — pandas, polars, DuckDB, numpy, ETL pipelines, tabular data ingestion, and notebook-to-module extraction. Use when working with dataframes, data validation at ingress boundaries, merge/join operations, typed column contracts, or choosing between pandas vs polars vs DuckDB for a data task.
python3-development-meta-docs
Python 3 development plugin documentation index. Load when needing to read about Python implementation patterns, task file conventions, or stdlib scripting.
python3-packaging
Configures pyproject.toml and Python packaging using PEP 517/518/621/660/723 standards. Use when creating or updating pyproject.toml, selecting a build backend (hatchling/setuptools/flit), configuring ruff, ty, mypy, pytest, or coverage tool sections, setting up dependency constraints or optional extras, defining CLI entry points, configuring pre-commit hooks, establishing src-layout directory structure, or preparing a package for PyPI publishing.
python3-publish-release-pipeline
Configures CI/CD pipelines for automated Python package publishing to PyPI or GitLab Package Registry. Use when creating GitHub Actions or GitLab CI release workflows, setting up trusted publishing or API token-based PyPI authentication, configuring version management with git tags and hatch-vcs, writing pyproject.toml publishing metadata, testing packages against TestPyPI, or documenting the release process for a Python project.
python3-review
Comprehensive Python code review checking patterns, types, security, and performance. Use when reviewing Python code for quality issues, when auditing code before merge, or when assessing technical debt in a Python codebase.
python3-stdlib-only
Use when building dependency-free Python 3.11+ scripts for airgapped, stdlib-only, or restricted environments where third-party package installation is prohibited — triggers on "stdlib-only", "airgapped", "no dependencies", "no internet", "restricted environment", or confirmed environments where external packages cannot be installed.
python3-tdd
Guides test-driven development for Python using a five-phase red-green-refactor cycle. Use when asked to write tests first, apply TDD, do test-first implementation, or follow red-green-refactor — designs typed interfaces and Protocol classes, writes failing pytest tests (RED), implements minimal passing code (GREEN), verifies with prek or ruff plus pytest-cov, and enforces a quality gate requiring all tests pass with no lint or type errors and coverage at or above 80 percent.
python3-test-design
Guides pytest test suite architecture and coverage strategy for Python 3.11+ projects. Activates when designing test architecture, planning test pyramid distribution, choosing between unit/integration/property-based/BDD strategies, structuring fixture hierarchies, configuring branch coverage thresholds, or applying mutation testing to critical code paths.
python3-testing
Pytest testing patterns for Python — fixtures (session/module/function/factory), AAA structure, behavioral naming, coverage targets by code type, property-based testing with Hypothesis, and mutation testing with mutmut. Use when writing tests, designing fixtures, configuring coverage, or applying parametrize, async testing, or property-based strategies.
python3-tools
Use when working with Python tooling — uv package management, Hatchling build backend, ty or mypy type checker configuration, ruff linting, pre-commit hook setup, TOML read-write with tomlkit or tomllib, or PyPI packaging and release workflows. Routes to standalone specialist skills for deep dives on any single tool.
python3-typing
Auto-selects and enforces the strongest valid Python typing lane for the detected Python version and dependencies — no user input required. Use when adding or tightening type annotations, eliminating Any usage in internal code, designing boundary validators or parsers, choosing between stdlib typing (TypedDict, Protocol, dataclasses), Pydantic models, or Hypothesis property tests, addressing ty or mypy failures, or applying version-specific features (TypeIs, ReadOnly, PEP 695 generics, PEP 649 deferred evaluation). Enforces boundary isolation — raw payloads validated immediately at ingress and returned as typed internal objects.
python3-web
Python web and API development enforcing strict route/domain/data layer separation, Pydantic v2 strict request-response models, edge-resolved auth, and async-safe HTTP clients. Use when working with FastAPI, Starlette, Django, Flask, HTTP endpoints, request models, authentication flows, async handlers, or any Python web framework task.
python-cli-architect
Use when the python-cli-architect agent needs project structure reference and task completion quality gates for Python CLI projects. Loaded automatically by the python-cli-architect agent — covers package layout, Hatchling configuration, and implementation quality criteria.
python-cross-platform-smoothing
Use when writing Python scripts that must run on Windows, Linux, and macOS — especially when Rich or Typer output breaks on Windows, when dealing with Unicode/encoding errors, ANSI escape handling, terminal detection, path separators, or console color support. Provides verified cross-platform patterns covering stdout/stderr encoding guards, Windows console quirks, terminal capability detection, and portable I/O for CLI, TUI (Rich/Textual), and GUI environments.
refactor-plugin
Start a complete plugin refactoring workflow that analyzes plugin structure, creates a refactoring plan with tasks, and guides through execution. Use when you need to refactor an entire plugin — triggers assessment, design, planning, and parallel agent execution phases.
refactor-skill
Assess and refactor oversized or multi-domain skills. First determines whether splitting or references/ extraction is appropriate — then executes the correct action. Use when a skill exceeds token thresholds (SK006/SK007) or covers multiple independent domains. Performs candidate assessment before any structural changes; cohesive single-intent skills are redirected to references/ extraction instead of splitting. When splitting is warranted — domain analysis gate, split plan, new SKILL.md generation, validation, and backwards-compatible facade conversion.
research-note
Synthesis step in the multi-angle technical research pipeline. Receives structured outputs from all four research angles (api-state, ecosystem-research, impact-measurement, codebase-auditor), applies cross-angle signal weighting and conflict resolution, and produces a single synthesized Research section. Invoked by the technical-researcher orchestrator after all angle skills complete. Returns content to the orchestrator — does not write to the backlog.
review
Reviews Python code across 9 dimensions — type safety, error handling, security, performance, modern patterns, design clarity, typed-boundary compliance, test quality, and documentation. Use when performing code review, PR review, pre-merge quality checks, or assessing Python for security vulnerabilities, bare except clauses, Any usage outside boundaries, or missing input validation at system boundaries.
review-permissions
Configure Claude Code permissions — tool approval rules, permission modes, managed policies, and sandboxing. Use when setting up permission rules, configuring allow/deny/ask policies, debugging permission prompts, deploying managed settings for organizations, or controlling Bash/Read/Edit/WebFetch/MCP/Agent tool access.
rich
Use when writing Python code with the Rich library — console output with markup, tables, progress bars, syntax highlighting, pretty printing, logging, or tracebacks. Covers Console, markup syntax, renderables (Panel/Table/Tree), Progress, Live, RichHandler, and the __rich_console__ protocol.
rtfp
Read The Fucking Prompt — finds the strongest user reaction to an AI instruction-following failure in a chosen session, reconstructs what the assistant did wrong, and renders a shareable terminal-style PNG. Use when asked to find rage moments, generate a rage receipt, or capture a frustration incident from a session.
rt-ica
Use before creating plans, delegating to agents, or defining acceptance criteria — performs Reverse Thinking Information Completeness Assessment (RT-ICA) to surface missing prerequisites and block planning until all required inputs are verified. Activates on specs, PRDs, tickets, RFCs, architecture designs, and multi-step engineering tasks. Integrates with CoVe-style planning pipelines.
scientific-thinking
Use when facing unknowns, debugging without a clear cause, or making architecture decisions — enforces hypothesis-driven scientific reasoning through observation, hypothesis formulation, prediction, experiment design, and evidence-based conclusion. Use when previous attempts have failed or the problem space involves uncertainty.
semantic-code-search
Use when searching a codebase by behavior, intent, or natural language description rather than exact identifiers. Activates the CocoIndex Code MCP server for semantic code search — finding implementations without knowing exact names, exploring unfamiliar codebases, or locating code by concept.
setup
Use when installing, updating, or troubleshooting the dasel v3 binary — runs the install script, verifies installation, and diagnoses PATH and download issues
setup-skill-discovery
Use when creating or updating the project skill discovery config — generates or regenerates .dh/skill_discovery.yaml by scanning the repo to infer tech stack, inventorying installed skills via npx skills list, loading candidate skill content before suggesting, and writing a config-driven skill injection file. Triggers on /dh:setup-skill-discovery invocations and programmatic --auto calls from add-new-feature Phase 3.
shebangpython
Validates and corrects Python shebangs and PEP 723 inline script metadata by applying four shebang-selection rules. Use when auditing or fixing shebangs in Python files — choosing between plain python3 and the uv shebang for standalone scripts with external dependencies, enforcing correct uv flag ordering (--quiet before run subcommand), adding or removing PEP 723 metadata blocks to match actual import requirements, checking execute bit presence, or avoiding redundant transitive dependencies when typer is declared (typer bundles rich and shellingham automatically).
skill-creator
Use when creating a new skill or updating an existing skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Activates on "create a new skill", "add a skill to plugin", or "update existing skill".
skill-sync
Sync a skill's content against the upstream library it covers — check whether the API descriptions, version references, and SOURCE: citations inside SKILL.md and its reference files still reflect what the library actually does today. Use when a library has released updates that may have changed the APIs the skill covers, when a skill references an old library version, when asked to sync, refresh, update, or check a skill against upstream docs, when the skill's content may have drifted from current library behavior, or when SOURCE: citations are stale. Accepts a SKILL.md path, skill directory, or plugin directory.
snakepolish
Executes the implementation phase of the python-engineering stinkysnake modernization workflow. Use when stinkysnake phases 1-8 are complete — modernization plan reviewed, interfaces designed, and failing tests written. Implements functions in dependency order (types, data structures, utilities, core logic, integration, entry points) applying modern Python patterns (Protocol, dataclass, Pydantic, modern type annotations, httpx, orjson). Runs iterative pytest loops until all tests pass, then verifies with static analysis via prek or ruff. Success criteria — all tests pass, no type errors, no lint errors, coverage meets project threshold.
specialist-skill-routing
Routes Python engineering tasks to specialist skills by matching trigger patterns before any architecture, plan, or code is written. Use when working with Typer CLI frameworks, Rich or Textual terminal UIs, CLI UI/UX design, questionary prompts, FastMCP/MCP servers, ty type checker, uv package manager, Hatchling build backend, TOML editing, pre-commit/prek hooks, async Python, PyPI packaging, complex linting, technical debt modernization, testing workflows, feature development, or stdlib-only scripting.
standards-for-python-development
Shared Python 3.11+ development standards covering type safety (ty, native generics, Protocol, TypeIs), layered architecture, error handling, performance, identifier naming, UI/CLI patterns (Rich/Typer), testing requirements (pytest, 80% coverage, TDD), and quality gates. Activates when any Python skill or agent needs to apply shared standards for implementation, code review, refactoring, or test authoring.
start-refactor-task
Start or complete a specific refactoring task from a task file. Use when a sub-agent needs to pick up a refactoring task, update its status, implement acceptance criteria, and run verification steps.
start-task
Use when executing a SAM task — claims the task via MCP to set it IN PROGRESS, writes active-task context for hooks, loads task-level skills, implements against acceptance criteria, and marks complete via --complete flag. Triggers on task execution within the implement-feature loop or when an agent picks up a specific task from a plan file.
stdlib-scripting
LAST RESORT for stdlib-only Python 3.11+ scripts in CONFIRMED restricted environments (airgapped systems, no uv, no internet access). Creates portable dependency-free scripts using argparse, logging, config management (JSON/TOML/INI), and cross-platform patterns. Use ONLY when environment restrictions prevent Typer+Rich with PEP 723. Triggers on "stdlib-only script", "no dependencies", "airgapped", "restricted environment", "portable script no network". For standard CLI development, use python-cli-architect with Typer+Rich instead.
stinkysnake
Nine-phase Python quality improvement system for file paths passed as arguments. Runs prek/ruff/ty static analysis with auto-fixes, inventories Any types and typing gaps, plans Protocol/Generic/TypeGuard/TypedDict/dataclass modernization, forks a code-reviewer agent to critique the plan, refines the plan, discovers documentation changes, designs interfaces first, forks python-pytest-architect for failing tests, then hands off to snakepolish for implementation. Use when eliminating Any types, addressing technical debt, applying modern Python 3.11+ patterns, modernizing library usage (httpx, orjson), or refactoring for stronger type safety.
subagent-contract
Global contract for all specialist subagents — enforces role boundaries, scope discipline, and DONE/BLOCKED status signaling. Use when loading any agent that should operate as a bounded specialist following supervisor delegation patterns.
subagent-refactoring-methodology
Analysis criteria, transformation patterns, output format, and validation checklist for refactoring Claude Code agent prompt files. Load this skill when preparing to run the subagent-refactorer agent or when reviewing agent prompt files for structural, model optimization, or instruction quality improvements.
summarizer
Route summarization requests to the correct methodology and enforce fidelity rules. Activates on summarize, tl;dr, give me the highlights, what's important in this, break down this, what does this code do, explain this file, describe this image, read and summarize. Routes files, URLs, images, and multi-source content to type-specific strategies. Enforces anti-hallucination rules — read before summarizing, extract before abstracting, preserve counts, distinguish absence from nonexistence, prevent lossy re-summarization chains.
task-decomposition
Decomposes a contextualized plan into atomic, independently executable task files with complete embedded context. Use after SAM Stage 3 Context Integration produces the contextualized plan artifact — when the plan is ready for TASK file generation with CLEAR ordering, CoVe checks, and dependency graphs for parallel execution.
test-failure-mindset
Use when encountering failing tests, diagnosing test errors, or establishing a systematic approach to test failure investigation. Activates on "test failure analysis", "debugging tests", or "why tests fail" requests. Establishes the mindset that treats test failures as valuable diagnostic signals requiring root-cause investigation — not automatic code fixes or test dismissal.
textual
Use when building terminal UI apps with the Textual framework — creating widgets, screens, layouts, handling events, managing reactive attributes, testing with Pilot, snapshot testing with pytest-textual-snapshot, or running background workers. Covers App lifecycle, CSS styling, screen stack, custom messages, actions, bindings, and the Worker API.
ty
Use when working with ty — the Astral Python type checker. Activates for running type checks, interpreting diagnostic error codes, suppressing ty errors with inline comments, configuring ty.toml or pyproject.toml, resolving unresolved imports, targeting Python versions, and integrating ty into editors or CI. Covers CLI flags, configuration schema, rule severity, environment discovery, module resolution, and all installation methods including uvx and uv add --dev.
typer
Use when building CLI applications with Typer — creating commands, defining arguments and options with enum restrictions, path validation, date and UUID types, composing subcommands, testing with CliRunner, or using advanced features like colored output, progress bars, shell autocompletion, and version callbacks.
Page 685 of 1685 · 84231 results
