rolandbrecht/agent-skills

A collection of shareable, high-quality AI coding agent skills and workflows. These skills provide structured guidance, recipes, and helper scripts to make LLM agents significantly more effective at complex codebase tasks.

4Stars on the repository
7Mods indexed here, across every type
23d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

ast-code-graph

01

rolandbrecht/agent-skills

Skill Claude CodeCodex

Use this skill ANY time you need to search for code structure, refactor symbols, analyze impact, find dead code, or trace dependencies. ALWAYS invoke BEFORE using grep for structural code analysis. Trigger categories: structural pattern search (e.g. useEffect without deps, async without try-catch, fetch calls outside…

not rated 4 23d ago A 196 tokens original MIT

ast-grep

02

rolandbrecht/agent-skills

Skill Claude CodeCodex

Use this skill ANY time you must search, lint, or rewrite code by its syntax structure. ast-grep is an AST-based CLI tool. It matches code by syntax tree, not by text. ALWAYS prefer it over grep/ripgrep when the query is about code structure. Trigger categories: structural code search (find all calls to X, functions…

not rated 4 23d ago A 193 tokens original MIT

self-reflection

03

rolandbrecht/agent-skills

Skill Claude CodeCodex

Execute this meta-skill ALWAYS at the end of complex tasks, debugging sessions, or when learning a new project codebase quirk. You MUST trigger this skill to codify hard-won lessons into reusable project rules (saving them to project-specific AI instruction files or a new SKILL.md). Do NOT close a complex task without…

not rated 4 23d ago A 85 tokens original MIT

structural-refactor

04

rolandbrecht/agent-skills

Skill Claude CodeCodex

Use this skill for any structural code search or replacement task — it is the right choice whenever grep/sed would feel clunky or risky. Trigger on ANY of these patterns: Structural find-and-replace across a codebase: "replace all fetch(url, options) calls with the new fetchWithRetry signature", "rename the first…

not rated 4 23d ago B 375 tokens original MIT

rolandbrecht/agent-skills

Skill Claude CodeCodex

Trigger this AUTOMATICALLY anytime you encounter a stack trace, test failure, production bug, or unexpected behavior. Do NOT guess the fix or propose code changes before explicitly triggering this skill. This skill mandates a strict data-gathering and hypothesis phase before you are permitted to edit ANY source code.

not rated 4 23d ago A 64 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: