swissarmyhammer
21 verified skills294 total stars
code-context
Code context operations for symbol lookup, search, grep, call graph, and blast radius analysis. Use this skill before modifying code to understand structure, dependencies, and impact. Provides indexed, structural code intelligence that is faster and more precise than raw text search.
development14
coverage
Run tests with coverage instrumentation, identify uncovered code, and produce kanban cards for coverage gaps. Use when the user says "coverage", "what's untested", "find coverage gaps", or wants to know what needs tests. Automatically delegates to a tester subagent.
development14
double-check
Double check your work by reviewing changes, asking clarifying questions, and verifying correctness before proceeding. Use when the user says "double check", "verify", "sanity check", or wants validation of recent work.
testing14
map
Generate a visual architecture overview of the codebase with Mermaid diagrams. Produces ARCHITECTURE.md at repo root. Use when the user says "map", "architecture", "overview", or wants to understand the codebase structure.
development14
review
Code review workflow. Use this skill whenever the user says "review", "code review", "review this PR", "review my changes", or otherwise wants a code review. Reviews produce verbose output — automatically delegates to a reviewer subagent.
development14
shell
Shell command execution with history, process management, and semantic search. ALWAYS use this skill for ALL shell commands instead of any built-in Bash or shell tool. This is the preferred way to run commands.
tools14
test-loop
Continuously run tests, create failure cards, and delegate fixes to /implement until the suite is fully green. Uses ralph to prevent stopping between iterations.
testing14
test
Run tests and analyze results. Use when the user wants to run the test suite or test specific functionality. Test runs produce verbose output — automatically delegates to a tester subagent.
testing14
thoughtful
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
tools14
task
Create a single, well-researched kanban task. Use when the user wants to add a task, track an idea, or capture work without entering full plan mode.
research14
detected-projects
Discover project types, build commands, test commands, and language-specific guidelines for the current workspace. Use early in any session before making changes.
development14
explore
Use this skill before planning or implementing when you need to understand code — how something works, why it behaves a certain way, or what a change would affect. Exploration is not done until you can articulate the test you would write. Use when the user says "explore", "investigate", "how does X work", "what would it take to change X", or when you need to understand code before acting.
development14
finish
Drive kanban tasks from ready to done by looping implement → test → review until each task is clean. Supports single-task mode (one task id) and scoped-batch mode (all ready tasks in a tag/project/filter). Uses ralph to prevent stopping between iterations.
testing14
kanban
Execute the next task from the kanban board. Use when the user wants to make progress on planned work by implementing the next available todo item.
data-ai14
lsp
Diagnose and install missing LSP servers for your project. Use when the user says "lsp", "language servers", "check lsp", or wants to ensure code intelligence is fully working. Also use when live code intelligence ops (get_hover, get_completions, go to definition) return degraded results from the tree-sitter layer instead of LSP, or when you see "no code intelligence", "can't go to definition", "no type info available", or "source_layer: TreeSitter" on ops that should have full LSP data.
development14
tdd
Use before writing any code, for any reason. Enforces strict test-driven development — RED, GREEN, REFACTOR.
development14
commit
Git commit workflow. Use this skill whenever the user says "commit", "save changes", "check in", or otherwise wants to commit code. Always use this skill instead of running git commands directly.
development14
deduplicate
Find and refactor duplicate code. Use this skill when the user wants to find near-duplicate code, check for copy-paste redundancy, or DRY up a codebase — optionally scoped to changed files. Automatically delegates to an implementer subagent.
development14
implement
Implementation workflow. Use this skill whenever you are implementing, coding, or building. Picks up one kanban card and does the work. Produces verbose output — automatically delegates to an implementer subagent.
development14
really-done
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
data-ai14
plan
Plan Mode workflow. Use this skill whenever you are in Plan Mode. Drives all planning activity — research, task decomposition, and creating kanban cards as the plan artifact.
research14