ulw-loop
121Skill Claude CodeCodex
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
Skill Claude CodeCodex
Goal-like loop that uses ultrawork mode to decompose work into systematic, evidence-bound steps.
Skill Claude CodeCodex
Removes AI-generated code smells from a SINGLE file while preserving functionality. For multiple files, call in PARALLEL per file.
Skill Claude CodeCodex
MUST USE for any real runtime debugging across ANY language or binary — crashes, silent failures, wrong responses, stuck processes, memory leaks, async misbehavior, unexplained timing, reverse engineering. Runs a hypothesis-driven loop: form ≥3 hypotheses, investigate in parallel, after 2 failed rounds spawn Oracles…
Skill Claude CodeCodex
Designer-turned-developer who crafts stunning UI/UX even without design mockups.
Skill Claude CodeCodex
(builtin) Initialize hierarchical AGENTS.md knowledge base.
Skill Claude CodeCodex
Strategic planning consultant that produces decision-complete work plans through Socratic interview, codebase exploration, Metis gap analysis, and optional Momus high-accuracy review. MUST USE when the task has 5+ steps, scope is ambiguous, multiple modules are involved, or the user asks for a plan. Triggers: plan…
Skill Claude CodeCodex
MUST USE for ANY work on .py .pyi .rs .ts .tsx .mts .cts .go files. One philosophy: strict types, modern stacks (Pydantic v2 / serde+thiserror / Zod / gin+sqlc+pgx+slog), modern toolchains (uv+basedpyright+ruff / cargo+clippy+miri / Bun+Biome+tsc / gofumpt+golangci-lint v2+nilaway+go-race), parse-don't-validate…
Skill Claude CodeCodex
Intelligent refactor command. Triggers: refactor, refactoring, cleanup, restructure, extract, simplify, modernize.
Skill Claude CodeCodex
Remove AI-generated code smells (slop) from branch changes or an explicit file list. Locks behavior with regression tests FIRST, then runs categorized cleanup via parallel deep agents in batches of 5, then verifies with quality gates. Covers 10 slop categories including performance equivalences, excessive complexity…
Skill Claude CodeCodex
Post-implementation review orchestrator. Launches 5 parallel background sub-agents: Oracle (goal/constraint verification), Oracle (code quality), Oracle (security), unspecified-high (hands-on QA execution), unspecified-high (context mining from GitHub/git/Slack/Notion). All must pass for review to pass. MUST USE after…
Skill Claude CodeCodex
Execute a Prometheus work plan in Codex with Boulder state, evidence ledger updates, worktree discipline, parallel subagents, and Stop-hook continuation. Use after planning when the user says start work, execute plan, continue plan, resume plan, or asks to run a .omo/plans plan.
Instructions file CodexOpenCode
Instructions for code-yeongyu/codex-rules, covering repository conventions, style, commands, constraints and don'ts.
Hook
Runs when a session starts, executing cli.js via node. From code-yeongyu/codex-rules.
Hook
Runs when you submit a prompt, before the agent sees it, executing cli.js via node. From code-yeongyu/codex-rules.
Hook
Runs after a tool call finishes for ^apply_patch$ tool calls, executing cli.js via node. From code-yeongyu/codex-rules.
Hook
Runs after the context is compacted for manual and auto tool calls, executing cli.js via node. From code-yeongyu/codex-rules.
Skill Claude CodeCodex
Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.
Instructions file CodexOpenCode
Instructions for code-yeongyu/pi-rules, covering agents.md, code style, test conventions, architecture and when adding a new rule source.
Cursor rule Cursor
React components must be functional and prop-typed.
Instructions file GitHub Copilot
Instructions for code-yeongyu/pi-rules: Always include error messages with context.
Instructions file GitHub Copilot
Instructions for code-yeongyu/pi-rules: Reviewers MUST check tests pass before approving.
code-yeongyu/ultimate-web-search-skill
Skill Claude CodeCodex
MUST USE when the user needs current, online, or web-derived information — news, latest releases, vendor docs, real-world examples, recent changes, or anything not in the model's training set. LLM-neutral skill that exposes a unified web search CLI behind a single command. Runs single or multi-provider in parallel…
code-yeongyu/opinionated-basic-cc-setup
Plugin Claude Code
Plugin marketplace listing 1 plugin: opinionated-basic-cc-setup.
code-yeongyu/opinionated-basic-cc-setup
Plugin Claude Code
Opinionated basic Claude Code setup with intelligent context injection, language-specific guides, project knowledge, and encoding validation.