codex skills agents

AgriciDaniel/codex-seo

Agent

SEO image analyst. Audits existing OG/social preview images, identifies missing or low-quality images, and creates an image generation plan with prompts for key pages. Does NOT auto-generate images.

AgriciDaniel/codex-seo

Agent

DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.

raphaelchristi/harness-evolver

Agent

Use this agent when the evolution loop stagnates or regresses. Analyzes the agent architecture and recommends topology changes (single-call → RAG, chain → ReAct, etc.).

raphaelchristi/harness-evolver

Agent

Use this agent to evaluate experiment outputs using LLM-as-judge. Reads run inputs/outputs from LangSmith via langsmith-cli, judges correctness, and writes scores back as feedback. No external API keys needed.

raphaelchristi/harness-evolver

Agent

Self-organizing agent optimizer. Investigates a data-driven lens (question), decides its own approach, and modifies real code in an isolated git worktree. May self-abstain if it cannot add meaningful value.

datit309/supergraph

Agent

Independent senior code reviewer. Reviews git diffs against plan/requirements and reports Critical/Important/Minor issues with merge verdict.

datit309/supergraph

Agent

Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.

datit309/supergraph

Agent

Independent implementation plan reviewer. Checks completeness, spec alignment, task decomposition, and buildability before execution.

geekjourneyx/industry-research

Agent

A chief-arbitrator research agent that combines opposing investment arguments into a final strategic report. It compares claims with source records and confidence reports, which show how reliable each conclusion is.

geekjourneyx/industry-research

Agent

A research-planning agent that turns a business question into checkable claims and evidence plans. It can also prepare interview guidance when interviews are part of the research.

geekjourneyx/industry-research

Agent

A Chinese-language research agent that challenges business claims by looking for missing evidence, copied sources, conflicts, and unsupported promotional statements.

Victory-7291/project-scaffold-setup-skills

Agent Codex

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

Victory-7291/project-scaffold-setup-skills

Agent Codex

Compare two outputs WITHOUT knowing which skill produced them.

Victory-7291/project-scaffold-setup-skills

Agent Codex

Evaluate expectations against an execution transcript and outputs.

ramboz/jig

Agent Claude Code

../../agents/architect.md.

ramboz/jig

Agent Claude Code

../../agents/implementer.md.

ramboz/jig

Agent Claude Code

../../agents/reviewer.md.

Heapy/kortex

Agent

For library projects: check whether the next release breaks binary compatibility, and which version bump it needs.

Heapy/kortex

Agent

Review Kotlin project structure: module split, dependencies, SOLID, a framework-free core, and effects at the boundary.

Heapy/kortex

Agent

Judge whether Kotlin tests prove the code works: over-mocking, edge cases, slices, integration coverage, and the test mix.

vibhasdutta/loop-engineer

Agent

This is a reference for the researcher agent. Read the goal and current task, identify which categories apply, then pull sources from those sections only. Ignore irrelevant categories — don't load noise.

vibhasdutta/loop-engineer

Agent

Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.

vibhasdutta/loop-engineer

Agent

Maps what's known, what's needed, and what could go wrong before the executor acts. Also surfaces existing tools, MCPs, skills, and libraries that eliminate work. Writes structured findings for executor and verifier/auditor. Runs before every executor pass. Never executes the goal itself.

Crazy-MT/video-subtitle

Agent Claude Code

Translate SRT subtitle files between languages while preserving timestamps and SRT structure exactly. Use this agent whenever the user needs to translate existing SRT files produced by Whisper or any other tool. / 翻译 SRT 字幕文件，保留时间戳和序号结构。.