Use when performing significant refactoring — guides a disciplined process that leverages duplication detection, characterization tests, staged execution, and continuous simplicity review
From clavainnpx claudepluginhub mistakeknot/interagency-marketplace --plugin clavainThis skill uses the workspace's default tool permissions.
SKILL-compact.mdSearches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Understand → Protect → Change → Verify → Simplify.
Announce: "I'm using the refactor-safely skill to guide this refactoring."
tldr-swinton:finding-duplicate-functions to detect semantic duplication in the affected areafd-architecture to understand existing patterns and house styletest-driven-development skill to ensure tests exist for the target behaviorIf tests are missing: write them first. Don't refactor untested code.
Use writing-plans to create a staged plan:
For each batch:
fd-quality — is the result actually simpler?After each batch verify: tests pass, code is objectively simpler (fewer lines, clearer intent, less coupling), no unintended behavior changes.
fd-quality on the complete changelanding-a-change to ship| Agent | When |
|---|---|
tldr-swinton:finding-duplicate-functions | Step 1 — duplication targets |
fd-architecture | Step 1 — house patterns, module boundaries |
fd-quality | Steps 4 & 5 — simplicity and idiom compliance |
Never:
Always: