ai-coding skills

7,594 tagged ai-coding, measured the same way as everything else here.

Browse within: agentic-coding 200best-practices 151ai-assistant 144vibe-coding 122awesome-list 118antigravity 95ai-pair-programming 93bun 85agent-swarm 82agent-orchestration 81agentic-workflow 79code-quality 76codex-cli 70api-integrations 67

skill-creator

73

chaohong-ai/ai-auto-work

Skill Claude CodeCodex

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

not rated 132 +1 1mo ago A 63 tokens

architect-implement

74

tikalk/adlc-team-skills

Skill Claude CodeCodex

Generate a full Architecture Description (AD.md) from accepted ADRs using multi-agent DAG orchestration. Use when accepted ADRs exist and you need to produce or update unified architecture documentation.

not rated 132 +1 yesterday A 41 tokens original MIT

speckit-checklist

75

dceoy/speckit-agent-skills

Skill Claude CodeCodexCursor

Generate a custom checklist for the current feature based on user requirements.

not rated 129 9d ago A 19 tokens AGPL-3.0

ppt-generation

76

peintune/runjam

Skill Claude CodeCodex

Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Has TWO workflows: (1) Primary — AI-generated full-slide images composed via scripts/generate.py; (2) Fallback — python-pptx programmatic slides (all text editable, better for reports/project management). The fallback…

not rated 184 today A 0 tokens original MIT

source-reading

77

itshen/source-reading-methodology

Skill Claude CodeCodex

A source-code reading method for understanding a large open-source repository and turning it into documentation, a course, or a book. Every technical claim is tied to exact lines in the repository.

not rated 133 11d ago A 229 tokens original MIT

anti-slop-design

78

madebyaris/advance-minimax-m3-cursor-rules

Skill Claude CodeCodexCursor

Category-aware design skill that builds distinctive, production-grade UIs. Brand-vs-product register, color strategy commitment, scene-based theme choice, palettes, font pairings, UX patterns, shadcn/token integration, empty-error-loading copy, secondary slop signals, multimodal design parity from mocks, and a…

not rated 125 2mo ago A 78 tokens original MIT

memory

79

lokikill123/codex-token-skills

Skill Claude CodeCodex

Persistent global memory across conversations. Read memory file at start of every conversation, write important context during conversation so it survives context compression. Use ALWAYS. Triggered automatically.

not rated 110 +1 2mo ago A 35 tokens original MIT

singula-ai/alego

Skill Claude CodeCodex

Use before pushing, force-pushing, marking ready for review, or claiming checks pass on an alego branch, and immediately after gh stack sync publishes rewritten branches, to select the smallest tests and checks that cover the outgoing or just-published diff without reflexively running the full repository suite.

not rated 109 8d ago A 66 tokens copy · 88% MIT

roadmap

81

Ovid/paad

Skill Claude CodeCodex

Read the feature roadmap, find the next unplanned phase, brainstorm it, and update the roadmap with the resulting document name.

not rated 110 +4 today A 27 tokens original MIT

email-service

82

cohen-liel/hivemind

Skill Claude CodeCodex

Email sending patterns for transactional and marketing emails. Use when implementing email sending, templates, SMTP configuration, or email services like SendGrid, Resend, or Mailgun.

not rated 108 4mo ago A 37 tokens original Apache-2.0

prompt-sensei

83

chengzhongwei/Prompt-sensei

Skill Claude CodeCodex

Stage-aware prompt coaching, prompt improvement, lookback analysis, prompting habit feedback, and local reports about prompt quality for AI coding agents such as Claude Code or Codex.

not rated 107 1mo ago A 39 tokens original Apache-2.0

repo-context-ledger

84

gviiisen/repo-context-ledger

Skill Claude CodeCodex

Maintain durable, evidence-based repository context whenever an agent initializes a repository, changes behavior, checkpoints or resumes work, switches AI tools or windows, collaborates through Git, prepares a pull request, or completes a coding task. Use the deterministic runtime to route bounded context, isolate…

not rated 105 8d ago A 103 tokens original MIT

flow

85

Facets-cloud/flow

Skill Claude CodeCodex

Personal task and agent-session manager. CLI binary is flow (assumed on PATH) and stores metadata in /.flow/flow.db (SQLite). Use this skill when the user asks about their work, tasks, or projects in any natural phrasing — including but not limited to: "what's left", "what's remaining", "what's pending", "what do I…

not rated 100 changed yesterday B 316 tokens original MIT

TwiTech-LAB/devchain

Skill Claude CodeCodex

Plan architecture improvements and refactoring for a codebase: scan for deepening opportunities (shallow modules, leaky seams, low-leverage interfaces), present candidates as a markdown report with before/after diagrams, interview the user through the chosen design, and decompose the outcome into devchain epics. Use…

not rated 99 +1 11d ago A 108 tokens

lerim

87

nablo-io/lerim

Skill Claude CodeCodex

Query Lerim's persistent project context before agent work. Use it to check prior decisions, constraints, preferences, and historical context through exact queries or synthesized answers.

not rated 97 1mo ago A 35 tokens

anhvt52/jetpack-compose-skills

Skill Claude CodeCodex

Guides writing, reviewing, and reasoning about modern Android UI code using Jetpack Compose. Covers best practices for state management, side effects, recomposition, navigation, Material 3 design, accessibility, and performance. Use when reading, writing, or reviewing any Jetpack Compose project.

not rated 96 5mo ago A 63 tokens original MIT

stream-coding

89

frmoretto/stream-coding

Skill Claude CodeCodex

Documentation-first development methodology. The goal is AI-ready documentation - when docs are clear enough, code generation becomes automatic. Triggers on "Build", "Create", "Implement", "Document", or "Spec out". Version 3.5 adds Phase 2.5 Adversarial Review and renames internal verification to Spec Gate…

not rated 96 6mo ago A 89 tokens

Tubo2333/obsidian-knowledge-brain

Skill Claude CodeCodex

A project knowledge system that saves technical decisions, debugging fixes, searchable notes, and evolving project rules as Markdown files. Obsidian is an optional note-taking application that can display these files as a linked knowledge graph.

not rated 96 +1 2mo ago A 0 tokens original MIT

ai-ml-development

91

travisjneuman/.claude

Skill Claude CodeCodex

AI and machine learning development with PyTorch, TensorFlow, and LLM integration. Use when building ML models, training pipelines, fine-tuning LLMs, or implementing AI features.

not rated 95 today A 43 tokens original MIT

armada-gate

92

rafmacalaba/armada

Skill Claude CodeCodex

Run an evidence-gate checklist for each success criterion in the current phase. Use when checking if a phase is complete before marking it passed.

not rated 93 +2 7d ago A 33 tokens original MIT

private-house-code

94

See-Sol-Lab/private-house-code-v2.5

Skill Claude CodeCodex

Use for every task that plans, writes, edits, debugs, tests, refactors, reviews, or maintains code. Apply to professional repositories, scripts, apps, services, prototypes, beginner work, vibe coding, and bounded code changes inside large systems. Choose the fewest clear lines, files, paths, states, and abstractions…

not rated 89 +6 14d ago A 158 tokens

delight

95

rwliebs/Dossier

Skill Claude CodeCodex

Add moments of joy, personality, and unexpected touches that make interfaces memorable and enjoyable to use. Elevates functional to delightful.

not rated 88 1mo ago A 28 tokens

truthmark-document

96

merlinhu1/truthmark

Skill Claude CodeCodex

Use when the user asks to document existing implemented behavior, or Sync, Check, or Structure finds implemented behavior missing canonical truth. Not for functional-code changes, doc-first implementation, or topology repair that needs Structure.

not rated 88 +1 2d ago A 46 tokens original MIT

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: