Skip to main content
Agent skills give AI coding agents structured knowledge about how to use fallow: when to run each command, what flags to use, how to interpret output, and how to avoid common pitfalls. Instead of relying on the agent’s general knowledge, skills provide precise, up-to-date instructions.
Skills work alongside the CLI and MCP integrations. They tell agents how to use fallow effectively, while the CLI and MCP provide the tools to do it.

​
What’s included

The fallow-skills package includes:
ComponentDescription
Analysis skillStep-by-step workflows for dead code analysis, duplication detection, auto-fix, and CI setup
CLI referenceComplete command specs, flags, output formats, and configuration
GotchasCommon pitfalls with correct vs incorrect examples (e.g., fix --yes requirement in non-TTY)
Workflow patternsRecipes for CI pipelines, monorepo analysis, migration from knip/jscpd, incremental adoption

​
Installation

/install fallow-rs/fallow-skills
Skills follow the open Agent Skills specification and work with any compatible agent.

​
What agents can do after installation

Once installed, agents understand how to use fallow for natural language requests:

Find dead code

“Find all unused exports in this project”. Agent runs fallow check --format json --quiet --unused-exports and summarizes findings.

Clean up dependencies

“Are there any unused dependencies?” Agent runs targeted analysis and suggests removals.

Detect duplication

“Find code duplication in the codebase”. Agent runs fallow dupes with the right mode and interprets clone families.

Auto-fix

“Remove unused exports”. Agent runs dry-run first, shows proposed changes, then applies with --yes.

CI setup

“Set up a dead code check in CI”. Agent generates the correct GitHub Actions workflow with baselines.

Debug false positives

“Why is this export flagged?” Agent uses --trace to investigate and suggests suppression if needed.

​
Skills vs MCP vs CLI

SkillsMCPCLI
What it providesKnowledge about how to use fallowStructured tool interfaceDirect command execution
SetupOne-time install per agentMCP server configurationfallow binary in PATH
Agent supportAny agent with skill supportAgents with MCP supportAny agent that runs shell commands
Best forTeaching agents fallow best practicesTyped tool calling in agent frameworksUniversal compatibility
For the best experience, combine all three: install the skill for knowledge, configure MCP for structured tool calling, and ensure fallow is in PATH for CLI fallback.

​
See also

Agent integration

CLI and MCP integration for AI agents.

CI integration

Catch dead code in your CI pipeline.

VS Code extension

Real-time feedback for human developers.