Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

spec-converge

6169

JKHeadley/instar

Skill Claude CodeCodex

Iteratively review an instar-development spec with multi-angle internal reviewers (security, scalability, adversarial, integration, decision-completeness, lessons-aware) and real cross-model external reviewers routed through the agent's own installed CLIs (codex → GPT-tier, gemini → Gemini-tier; one pass per available…

not rated 86 +1 changed 2d ago A SkillSpector: warn 135 tokens original MIT

mentor

6170

smixs/mentor

Skill Claude CodeCodex

Generate an /insights-style HTML report across MANY of your agent coding sessions (Claude Code and OpenAI Codex): what you work on, how you use the agent, your wins, your friction points, and concrete fixes to become more effective — precise goal-setting, not trusting output blindly, scoping, context hygiene…

not rated 86 3mo ago A SkillSpector: warn 167 tokens original MIT

osint

6171

0dayInc/pwn

Skill Claude Code

Drive extroosint with the right kind, feeds, pivots, and keys.

not rated 86 2d ago A SkillSpector: pass 21 tokens original MIT

mikromcp

6172

AliKarami/MikroMCP

Skill Claude CodeCodex

Use when managing, configuring, or troubleshooting MikroTik RouterOS devices through the MikroMCP server — picking the right tool, running safe (dry-run, confirmed, rollback-able) changes, fleet operations, and diagnosing network issues.

not rated 86 +2 changed 15d ago A SkillSpector: pass 50 tokens original MIT

unslop

6173

asavvin-pixel/unslop

Skill Claude CodeCodex

Removes signs of AI generation from English text and prevents them from appearing in new writing. Works on three levels: typography and mechanics, vocabulary and rhetoric, structure and epistemics. Use whenever the user asks to "humanize", "unslop", "de-AI", "make this sound human", "remove the AI style", "make it not…

5 · 1 86 +4 3mo ago A 131 tokens original MIT

resume-optimizer

6174

Liliane0310/Resume-Optimizer

Skill Claude CodeCodex

A Chinese-language resume editor and HTML generator for matching a CV to a job description.

not rated 86 +1 5mo ago A 132 tokens

kent-workflows

6175

respawn-llc/kent

Skill Claude CodeCodex

How to use the Kent CLI to author and edit Kent workflow graphs — nodes, edges, transitions, parameters, context modes, and project links. Use when the user asks to define, build, inspect, or modify Kent workflows.

not rated 86 +1 changed 1mo ago A 50 tokens AGPL-3.0

ambient-project

6176

Bene-2020/plane-codex-mcp

Skill Codex

Quietly maintain a useful project view from meaningful work in the current Codex session. Use when work creates a task, bug, decision, idea, risk, milestone, plan, progress update, or explicit completion.

not rated 86 5d ago A SkillSpector: pass 46 tokens original MIT

Samin12/instagram-thread-carousel

Skill Claude CodeCodex

Use when the user wants to turn a text thread into an Instagram carousel that looks like tweet/X post screenshots. Generates slide images with profile pic, name, verified badge, handle, and tweet text. Supports embedded images and combining short tweets on one slide.

not rated 86 +4 8mo ago B 55 tokens

academic-paper

6178

timpara/opencode-academic-research

Skill Claude Code

12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns…

not rated 86 +2 2mo ago A 147 tokens

prd-planner

6179

zhaono1/agent-playbook

Skill Claude Code

A file-based workflow for writing a PRD, or product requirements document—a description of what a product should do and why.

not rated 86 +1 1mo ago A Socket: passSnyk: warnSkillSpector: pass 48 tokens original MIT

xjli360/sealeap-amazon-ad-skills

Skill Codex

A playbook for planning advertising on Amazon US for clothing products, using an ASIN lifecycle. An ASIN is Amazon's product identifier; the lifecycle describes whether a product is new, growing, mature, declining, or seasonal.

not rated 86 changed 2mo ago A SkillSpector: pass 167 tokens original MIT

session-harbor

6181

WangPeterXF/session-harbor

Skill Codex

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.

not rated 86 2mo ago A 61 tokens

code-review

6182

tianemon/EasyMint

Skill Claude CodeCodex

A code-review procedure for checking whether changes meet their requirements, behave correctly, stay within safe boundaries, and have effective tests.

not rated 86 +3 changed 4d ago A 103 tokens original MIT

ripdpi-design

6183

po4yka/RIPDPI

Skill Claude Code

Use this skill to generate well-branded interfaces and assets for RIPDPI (an Android-native, Compose-first VPN and DPI-bypass app), either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, brand-ship icons, and an interactive UI kit of every public composable…

not rated 86 +1 today A 77 tokens original BSD-3-Clause

user-defined-command

6184

googlicius/obsidian-steward

Skill Claude CodeCodex

Create and edit Steward user-defined commands (UDCs). Use when the user wants to create, modify, or troubleshoot custom command workflows defined as YAML in the Steward/Commands folder.

not rated 85 3mo ago A SkillSpector: warn 40 tokens original MIT

auto-optimize

6185

gilbertwuu/Auto-Optimize

Skill Claude CodeCodex

Host-agnostic Agent Skill: double-layer workflow for AI-assisted delivery—requirement specification, multi-prompt outer loop, on-disk inner iterations, phase gates, optional byte-level verify. For any IDE, CLI, or Skill-capable tool (e.g. OpenClaw). Read program.md and docs/verifiability.md before editing delivery…

not rated 85 +1 7mo ago A 78 tokens original MIT

ab-test-generator

6186

Humblytics/humblytics-marketing-skills

Skill Claude CodeCodex

Reads page analytics and click data from Humblytics, generates A/B test hypotheses with element selectors, and launches no-code split tests via the Humblytics MCP. Use when creating A/B tests, split tests, multivariate tests, or when you need to test headlines, CTAs, layouts, or pricing. Triggers: A/B test, split…

not rated 85 2d ago A SkillSpector: pass 87 tokens original MIT

windows-shell

6187

RikyZ90/ShibaClaw

Skill Claude CodeCodex

Manage long-running background jobs and interactive workflows on Windows using PowerShell Jobs (Start-Job, Receive-Job) — the Windows equivalent of tmux sessions.

not rated 85 +1 6d ago A SkillSpector: pass 35 tokens original Apache-2.0

patsnap/patent-literature-search-mcp

Skill Claude CodeCodex

Search Patsnap's global patent and scientific literature databases together using natural-language, semantic, keyword, and BM25-based queries with multidimensional filters, then fetch patent or literature records as Markdown.

not rated 85 +1 3mo ago A 48 tokens original Apache-2.0

viraloop

6189

Upload-Post/viraloop

Skill Claude CodeCodex

OpenClaw AI agent skill for automated TikTok and Instagram carousel growth. Analyzes any website URL to extract brand, competitors, value proposition, then generates viral slides with auto-publishing and trending music via upload-post API. Built-in analytics feedback loop.

not rated 85 +2 7mo ago A 56 tokens

telbot-mcp

6190

0xtbug/telbot

Skill Claude CodeCodex

Manage Telkomsel quota, packages, and profile via natural language over MCP. Use for: Logging in to Telkomsel, checking quotas, buying packages (pulsa/qris), and scheduling auto-buys.

not rated 85 6mo ago A 49 tokens

build-to-learn

6191

Tasihi89/build-to-learn

Skill Claude CodeCodex

Learn by building — learning is the goal, building is the test. When the user wants to make something, first turn the product into scenario scripts, translate those into capability blocks, then cut a ladder of stages: stage 1 is a runnable MVP, every later stage adds one block and still runs. Each stage carries a…

not rated 85 3mo ago A 283 tokens original MIT

awesome-skills/mobile-app-design

Skill Claude CodeCodex

This skill should be used when the user asks to "design mobile UI", "review app design", "check UI guidelines", "improve app UX", "design React Native interface", "create app screens", "follow design standards", or mentions iOS/Android design patterns, accessibility, or mobile user experience. Provides comprehensive…

not rated 85 +2 9mo ago A 78 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: