ast-grep
Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.
fly-sprites
Operate Fly.io Sprites with the `sprite` CLI. Use for Sprite lifecycle; remote commands, files, and package installation; exec sessions or wake-safe services; HTTP URLs and port forwarding; checkpoints and restores; or troubleshooting target selection, authentication, lifecycle, networking, and storage.
gob
Process manager for long-running background processes. Use when starting development servers, watching files, or running commands that need to continue in the background while agent continues working.
emacsclient
Use emacsclient to open files, inspect or debug a running Emacs, evaluate or reload Elisp, or manage windows.
herdr-subagents
Herdr subagent orchestration. Use when the user asks to delegate through Herdr for a read-only investigation or review, an implementation-and-review loop, or a sequential task queue.
martin-fowler-refactoring
Apply Martin Fowler's catalog to identify code smells and select systematic refactorings.
pair-programming
Human-navigated, agent-driven pair programming through small design increments and natural handoffs.
pi-sessions-duckdb
Inspect Pi session conversations and analyze session logs with DuckDB. Use when asked what happened in a session, to summarize or extract conversation fragments, to read user/assistant messages without tool traffic or thinking, to find debugging evidence, or to calculate session, message, and tool-use statistics from ~/.pi/agent/sessions/**.
safe-refactoring
Refactor code when the user wants behavior-preserving cleanup or raises a structural concern such as a large method, duplication, mixed responsibilities, awkward control flow, misplaced logic, or difficult naming—even when they are still exploring what to change. Use for extracting, moving, simplifying, reorganizing, renaming internals, and replacing implementations without changing behavior. Route behavior changes and bug fixes to test-driven-development; styling and declarative configuration use targeted verification instead.
story-splitting
Turn broad requirements, large stories, epics, features, initiatives, or backlog items into small end-to-end child stories without turning them into technical component tasks. Use when refining a backlog, decomposing epics, planning an MVP or walking skeleton, looking for vertical slices, reducing story size, applying SPIDR/Hamburger/capability slicing, avoiding scatter-gather/component stories, or deciding the first valuable story before implementation planning.
test-driven-development
Test-drive meaningful application-owned behavior when adding or changing domain rules, interactions, state transitions, authorization, calculations, persistence, API contracts, or fixing bugs—even when the user does not request TDD. Route behavior-preserving structural work to safe-refactoring. Styling, declarative metadata or configuration, generated code, dependency upgrades, mechanical wiring, and test-only maintenance fall outside this TDD process.
tidy-first-analysis
Command-only workflow for analyzing an intended code behavior change using Kent Beck's Tidy First principles and recommending small behavior-preserving tidyings before implementation. Use via /skill:tidy-first-analysis when comparing skill versus prompt-template approaches, or when explicitly asked to run a Tidy First analysis.