codex-plugin skills

1,292 tagged codex-plugin, measured the same way as everything else here.

Browse within: codex-cli 191codex-skills 134github-copilot 99matlab 88codex-skill 83gemini-cli-extension 73prompt-engineering 66agent-workflow 65agentic-workflow 63coding-paradigm 59korean 59macos 59matlab-mcp-server 59outline-driven-development 59

mathworks/polyspace-agentic-toolkit

Skill Claude CodeCodex

REQUIRED before searching for any Polyspace option documentation page. Use when the user asks about a Polyspace option (-c, -target, -sources, -boolean-types, -misra3, etc.), wants to find an option's doc page, or asks 'what does this option do'. This skill contains the only reliable method to locate option reference…

23 +1 3mo ago A 87 tokens

justify-findings

74

mathworks/polyspace-agentic-toolkit

Skill Claude CodeCodex

Adds Polyspace justification annotations to C/C++ source code. Use when the user asks to "justify this finding", "add a Polyspace annotation", "mark as false positive", "suppress finding", or wants to add justification comments to Polyspace findings.

23 +1 3mo ago A 56 tokens

pixellab-pip

75

Shilo/pixellab-pip

Skill Claude CodeCodex

Use for PixelLab/Pip setup, auth, MCP/API routing, asset generation, editing, animation, talking portraits, lip sync, skeleton/template/preset animations, multi-shot/looping cinematics, docs/troubleshooting, bark completion sounds, and explicit PixelLab cost/budget/credit questions across MCP, REST v2/API…

21 6d ago A 248 tokens original MIT

amocrm-api-control

76

nebelov/yandex-direct-for-all

Skill Claude CodeCodex

A guide for securely connecting to amoCRM, a customer-relationship system, through its API. It covers OAuth sign-in, account structure, and checking leads by source, time, status, owner, and external link.

21 1mo ago A 45 tokens original MIT

nebelov/yandex-direct-for-all

Skill Claude CodeCodex

A workflow for researching commercial demand for a product or service through Wordstat, a Yandex tool that reports search activity. It records the collected queries and classifies them as relevant demand, noise, or uncertain.

21 1mo ago A 38 tokens original MIT

yandex-wordstat

78

nebelov/yandex-direct-for-all

Skill Claude CodeCodex

A reference guide to Yandex Wordstat API v2, the Yandex service used to study what people search for. It documents requests, authentication, quotas, regions, devices, and search-demand trends.

21 1mo ago A 53 tokens original MIT

m2ui

79

martysama0134/m2ui-skill

Skill Claude CodeCodex

Use when creating, modifying, auditing, or debugging Metin2 client UI code (uiscript dicts, root ui.py classes, locale entries) — user says "/m2ui", "create UI", "make a window", "add button to", provides a UI screenshot to replicate, asks to "check UI for bugs" / "diagnose", or reports a visibly broken window…

21 1mo ago A 97 tokens

flutter-ui

80

datit309/supergraph

Skill Claude CodeCodex

Build Flutter UI from Figma MCP or image input. Scans src for design tokens (colors, sizes, text styles), existing components, and naming conventions before writing a single line of code. Never hard-codes values.

21 5d ago A 48 tokens original MIT

review

81

datit309/supergraph

Skill Claude CodeCodex

Plan-aware graph-enhanced code review before merge. CRITICAL issues block merge. Use after fix/verify.

21 5d ago A 24 tokens original MIT

serena

82

datit309/supergraph

Skill Claude CodeCodex

Serena code intelligence — LSP-powered symbol navigation, diagnostics, and targeted code surgery. Activate before complex refactors, cross-file analysis, or when graph tools need symbol-level depth.

21 5d ago A 40 tokens original MIT

sdlc-nfr-spec

84

BlueSkyXN/Codex-is-all-you-need

Skill Claude CodeCodex

Use to define measurable NFRs for performance, reliability, security, privacy, accessibility, observability, and operations.

21 17d ago A 31 tokens GPL-3.0

session-harbor

86

WangPeterXF/session-harbor

Skill Claude CodeCodex

Operate a dedicated Codex session-management task: show backup progress and inventories, configure retention, safely back up or clean verified local Codex sessions, restore sessions, exchange cross-device evidence, or migrate legacy archives. Do not use for ordinary project-file backups or ChatGPT web conversations.

21 +10 6d ago A 61 tokens

hermes-codex-plugin

87

LYAKAKOY/Hermes-Codex-Plugin

Skill Claude CodeCodex

Use when a task may depend on prior user preferences, project conventions, architectural rules, workflow decisions, previous Codex work, full-text memory search, durable rule saving, or skill drafting/updating through Hermes Codex Plugin, especially to reduce Codex token spend by recalling minimal relevant context.

19 2mo ago A 65 tokens

claude

88

yanchuk/claude-plugin-codex

Skill Claude CodeCodex

Use when the user asks Codex to consult Claude Code, run a Claude advisor pass, get a Claude adversarial review, check a plan or diff with Claude, ask Claude to do a prepared coding, exploration, verifier, scout, or rescue task, inspect Claude advisor job status, fetch a Claude result, or cancel a Claude advisor job.…

18 3mo ago A 95 tokens original MIT

audit

89

aahil62/unslop

Skill Claude CodeCodex

Score an existing React + Tailwind site against the anti-slop checklist and produce DESIGN-AUDIT.md with evidence. Use when the user says their site "looks AI-generated", "looks generic", "feels off", asks "why is my site ugly", or wants a design audit/score before improving it. Read-only — never edits source.

17 2mo ago A 73 tokens original MIT

interview

90

aahil62/unslop

Skill Claude CodeCodex

Interview the user about taste, brand, and audience, then synthesize a custom design lane (LANE.md + tokens) for their React + Tailwind site. Use when the user wants a design direction, says "make it look premium/professional/not AI-generated", or after /unslop:audit before any re-theming. No code changes — output is…

17 2mo ago A 84 tokens original MIT

retheme

91

aahil62/unslop

Skill Claude CodeCodex

Systematically apply an approved design lane (LANE.md) to a React + Tailwind site — tokens first, then section-by-section, with build + screenshot verification after every pass. Use when the user says "retheme", "apply the lane", "make it match the design", or after /unslop:interview produced an approved LANE.md.

17 2mo ago A 76 tokens original MIT

askme

92

OutlineDriven/odin-codex-plugin

Skill Claude CodeCodex

Verbalized Sampling (VS) protocol for intent exploration before planning, mode-aware. Default exhaustive runs full VS; collaborative runs tip-sharing dialogue; adversarial walks the design tree one fork at a time. Auto-detects from phrasing ("help me refine" → collaborative, "poke holes" → adversarial); override via…

15 1mo ago A 106 tokens original Apache-2.0

design

93

OutlineDriven/odin-codex-plugin

Skill Claude CodeCodex

Set visual and interaction direction for any UI surface (web, React, TUI, CLI, desktop, Qt, design-system tokens) before any UI code. Direction-first: generates 3-4 distinct directions via verbalized sampling, picks one via per-axis single-select, then derives palette, typography, spacing, motion budget. Loads when…

15 1mo ago A 151 tokens original Apache-2.0

grill-ai-mastery

94

OutlineDriven/odin-codex-plugin

Skill Claude CodeCodex

Hybrid interview that probes AI-engineering mastery by tip-vocabulary depth — entity referencing, loop closure, observability, harness improvement — not by token usage or LOC. Start collaborative (two-way tip exchange), escalate to adversarial probing when depth is lacking. Trigger when the user says "interview me on…

15 1mo ago A 104 tokens original Apache-2.0

canopyops

95

Stunspot/CanopyOps

Skill Claude CodeCodex

Plan, diagnose, document, and review lawful cannabis cultivation operations. Use for crop plans, incident triage, calculations, harvest readiness, compliance records, CAPA, runbooks, and handoffs.

11 11d ago A 44 tokens

tokendiet

96

Fortytude/TokenDiet

Skill Claude CodeCodex

Audit this codebase for wasteful LLM API spend and hand back a concrete, honest fix plan — missing prompt caching, uncapped retries, prompt bloat, no batching, overpowered models. Describes technical waste and published provider rates only; never fabricates a dollar figure. Trigger on requests like "audit my LLM…

11 1mo ago A 100 tokens original MIT