01
Confirm the job
Define the work before choosing the most popular Skill.
Platform compatibility
Codex Skills
Agent Skills for Codex workflows. Compare installation paths, permission actions, and source evidence before adding one to your stack.
- Compatibility
- Declared + inferred
- Evidence
- Source / computed
- Refresh
- Daily
Matching candidates
377
Current snapshot
Quality ready
375
Computed signal ≥ 75
Evidence layers
4
Source to editorial
Refresh cadence
24h
Repository signals
Qualified matches
Skills for Codex Skills
The list prioritizes source diversity, freshness, and documentation depth. Card scores are computed signals—not test certifications.
EvidenceSourceComputedTestedEditorial
Computed 9315,122
wanshuiyin/Auto-claude-code-research-in-sleep
ablation-planner
Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
Computed 9215,122
wanshuiyin/Auto-claude-code-research-in-sleep
ablation-planner
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
Computed 91203
PramodDutta/qaskills
Accessibility Auditor
Comprehensive WCAG 2.1 AA compliance testing combining automated axe-core scans with manual keyboard navigation, screen reader compatibility, and focus management verification
Computed 9520
upex-galaxy/agentic-qa-boilerplate
acli
Atlassian CLI (official `acli` binary, v1.3+ as of 2026) for Jira Cloud, Confluence Cloud, and org admin tasks from the terminal. Use whenever the user wants to create, view, edit, transition, assign, clone, archive, comment on, link, or bulk-operate on Jira work items; list or manage projects, boards, sprints, filters, dashboards, or custom-field definitions; create or update Confluence spaces, pages, or blog posts; activate/deactivate users at the org level; or authenticate to Atlassian from a
Computed 901,118
vellum-ai/vellum-assistant
acp
Set up, authenticate, and run external coding agents (Claude Code, Codex) via the Agent Client Protocol
Computed 9147
kennethkhoocy/applied-micro-skills
adversarial-empirical-review
N-round adversarial review pipeline for empirical research output — the chain from data to LaTeX tables to a manuscript that cites them. A Claude drafter proposes minimal diffs, a deterministic mechanical battery gates every diff from a clean state with a regression gate, a Codex reviewer files check-backed critiques, and a blind judge panel decides residual disputes. Manual-invoke ONLY: trigger when the user explicitly runs /adversarial-empirical-review or names 'adversarial-empirical-review' /
Computed 9416
reddb-io/red-skills
afk
Autonomous loop that drains the `ready-for-agent` queue on the issue tracker. Registers the project with the `redskilled` daemon at a runner and a target width, arms the drain, and observes; the daemon admits each Worker, which claims an issue, works it in its own workspace, validates, lands, and closes. Use when the user wants to run AFK execution, drain a Spec, hammer specific issues, or otherwise let agents grind through the backlog.
Computed 9152
hyperb1iss/sibyl
agent-activity-audit
Audit recent agent transcripts (Claude Code and Codex) to learn how a tool, system, or skill is actually being used in the wild. Surfaces failure modes, friction, success patterns, and concrete improvement candidates from real session data. Use this when you want to improve a developer-facing system that agents interact with regularly.
Computed 91286
Undertone0809/rudder
agent-work-reviewer-maintainer
Use when reviewing Rudder agent work, Codex sessions, PRs, commits, UI, releases, regressions, proposals, or agent outcomes for product correctness, evidence quality, scope, architecture, and handoff trust.
Computed 94203
PramodDutta/qaskills
Agentic Testing Patterns
AI-first testing methodology where autonomous agents plan, generate, execute, and maintain test suites with minimal human intervention, covering agent orchestration, feedback loops, and intelligent test prioritization.
Computed 9980
vasilyu1983/AI-Agents-public
agents-hooks
Configures Claude Code hooks and Codex hooks.json/notify callbacks. Use when adding guardrails, preflight, audit trails, worktree automation, or budget enforcement.
Computed 9180
vasilyu1983/AI-Agents-public
agents-skills
Creates and audits agent skills with SKILL.md, references, scripts, and platform-scoped metadata. Use when creating, updating, or validating shared skills.
Decision path
Move from discovery to installation in four checks
02
Compare evidence
Separate source claims, computed signals, tests, and editorial judgment.
03
Review permissions
Review network, script, file, and outbound-data actions.
04
Test narrowly
Pin the source and run a reversible test in isolation.