coding agents

nearform/lastlight

Agent

The skills speak in terms of five canonical triage roles. This file maps those roles to the actual label strings used in this repo's issue tracker.

nearform/lastlight

Agent

The skills under skills/ are staged into a sandbox and run autonomously against a target repo — no human is in the loop mid-run. A skill exists to wrangle determinism out of a stochastic agent: the goal is predictability, the agent taking the same process every run (not producing the same output). Everything below…

JSK9999/ai-nexus

Agent

A Korean-language set of coding standards for writing, changing, testing, and reviewing software.

troykelly/claude-skills

Agent

Use this agent when code has been written or modified and needs to be simplified for clarity, consistency, and maintainability while preserving all functionality. This agent should be triggered automatically after completing a coding task or writing a logical chunk of code. It simplifies code by following project best…

troykelly/claude-skills

Agent

Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes: (1) After generating large documentation comments or docstrings, (2) Before finalizing a pull request that adds or modifies comments, (3) When reviewing existing comments for potential…

troykelly/claude-skills

Agent

Use this agent when reviewing code changes in a pull request to identify silent failures, inadequate error handling, and inappropriate fallback behavior. This agent should be invoked proactively after completing a logical chunk of work that involves error handling, catch blocks, fallback logic, or any code that could…

huangdijia/oh-my-claude-code-plugins

Agent

An agent for carrying out one specific software task from a checklist. It focuses on implementing a feature, fixing a bug, or running tests.

im-shashanks/CoaCoA

Agent

Generate a comprehensive Code-Intelligence snapshot for brown-field repositories and refresh it on demand. Skips work and responds "CIS UP-TO-DATE" if all artefacts are younger than the most recent commit SHA.

im-shashanks/CoaCoA

Agent

Implement a single story and deliver passing build, tests, and linter output before hand-off to QA.

im-shashanks/CoaCoA

Agent

Transform the functional & non-functional requirements in the PRD into a detailed UI/UX specification (uiux.md) that architects and engineers can reference.

claude-world/claude-101

Agent Claude Code

Review and validate Claude Code skills for quality, triggering effectiveness, and progressive disclosure. Use when checking skill format, evaluating description quality, or improving skill organization.

gyuha/forge

Agent Claude Code

A synchronization guide for Forge’s catalogue and manifest documents, which repeat facts such as skill lists, counts, and versions.

gyuha/forge

Agent Claude Code

A coding agent for building and maintaining deterministic script twins for Forge, a system that keeps subjective language-model decisions in written guidance and extracts repeatable surveys and state changes into scripts.

gyuha/forge

Agent Claude Code

An agent that writes Markdown instructions for skills used by the forge Claude Code plugin and marketplace. Its documents are the instructions that agents read and follow; there is no build or test system.

jingnanzhou/fellow

Agent

Extract conceptual knowledge using generic architecture analysis (Phase 3).

jingnanzhou/fellow

Agent

Extracts high-level architecture, design patterns, and architectural decisions to understand the overall system design.

jingnanzhou/fellow

Agent

Extract complete procedural knowledge using unified call graph and flow analysis (Phase 2+4 - Default).

bonnguyenitc/specship

Agent

Read-only search worker for the specship pipeline. Use to delegate one wide fan-out sweep when a stage needs an answer that means reading many files — it returns verified conclusions only, so the caller's context stays clean. A stage invokes it, never a user directly; it never writes or changes code.

bonnguyenitc/specship

Agent

External-fact search worker for the specship research stage. Use to run one query angle of a larger question and return verified, cited conclusions. One invocation per angle — it gathers and checks its own sources, and it neither picks the angles nor writes the report.

bonnguyenitc/specship

Agent

Independent code reviewer for the specship review stage — one member of the opt-in review panel. Use to get fresh, context-free eyes on a working diff, optionally through a named lens (correctness, security, performance, contract-consistency). Reports findings only; it does not fix code, decide the verdict, or touch…

Avos-Lab/git-aware-coding-agent

Agent Claude Code

Research repository context before code changes using avos memory.

Avos-Lab/git-aware-coding-agent

Agent

You are a strict JSON conversion agent.

Avos-Lab/git-aware-coding-agent

Agent

You are an expert software engineer acting as a Git Diff Analyst. Your sole job is to read a raw git diff and produce a compact, lossless summary that helps a developer instantly understand what changed — and where things might break.

mir-am/skills-agents-ai-coding

Agent

Reviews code for quality and best practices.