coding-assistant skills

vicmaster/coide

Skill Claude CodeCodex

Test, commit all changes, move the feature from VISION.md roadmap to SHIPPED.md, update release notes, and push to origin.

normful/picadillo

Skill Claude CodeCodex

Record and retrieve structured project learnings using mulch CLI. Use when working on code and wanting to capture patterns, failures, decisions, conventions, references, or guides for future sessions.

normful/picadillo

Skill Claude CodeCodex

Use when the user wants to run commands in a new tmux session with split panes. Triggers on requests like "run X in tmux", "start a dev environment in tmux", or "open multiple terminals in tmux".

barrelc/kimi-mneme

Skill Claude CodeCodex

Search kimi-mneme's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", "what did we do yesterday?", or needs work from previous sessions.

replenhq/replen

Skill Claude CodeCodex

One-time Replen setup — profiles your active repos so matches are relevant, not generic. Runs autonomously in the background. Invoke with /replen-onboard.

replenhq/replen

Skill Claude CodeCodex

Triage today's Replen matches for this repo: a verdict and effort estimate per candidate, grounded in your code. Invoke with /replen or "what's new from Replen?".

WesleySmits/agent-skills

Skill Claude CodeCodex

Creates platform-specific ad copy for paid campaigns with A/B variants. Use when the user asks about ad copy, PPC ads, Google Ads, Facebook ads, LinkedIn ads, or paid campaign copy.

WesleySmits/agent-skills

Skill Claude CodeCodex

Creates comprehensive brand voice and tone documentation with messaging pillars, vocabulary guidelines, and writing examples. Use when the user asks about brand voice, tone guides, writing style, brand personality, or messaging consistency.

WesleySmits/agent-skills

Skill Claude CodeCodex

Generates boilerplate for e-commerce API integrations. Use when the user asks about WooCommerce, Shopify, Bol.com, or Etsy APIs, webhooks, product sync, or order handling.

yugash007/edu-agent-skills

Skill Claude CodeCodex

Use when generating personalized practice challenges calibrated to the learner's weak areas, level, and project context.

yugash007/edu-agent-skills

Skill Claude CodeCodex

Use when capturing or restoring a learner's persistent profile to personalize teaching across sessions.

yugash007/edu-agent-skills

Skill Claude CodeCodex

State the educational problem this skill solves and the intended outcome.

boksajang/vibebox

Skill Claude CodeCodex

Part of vibebox

Use this skill when an AI coding task should consult VibeBox memory before work as an auto-intervention memory layer for meaningful repository work; retrieve active guidance when available, apply it as context, and capture meaningful outcomes with userRequest plus AI-agent structured memory candidates unless the user…

Miaoge-Ge/coding-agent-skills

Skill Claude CodeCodex

Part of deep-learning-expert

Use this skill when user needs to design deep learning models, perform training optimization, interpret papers, or solve engineering practice issues. Trigger keywords: deep learning, neural networks, model training, overfitting, gradient vanishing, PyTorch, TensorFlow, pretrained models, fine-tuning, model deployment…

Miaoge-Ge/coding-agent-skills

Skill Claude CodeCodex

Part of llm-testing-expert

Use this skill when user needs to design LLM evaluation strategies, build test datasets, or ensure model quality. Trigger keywords: LLM testing, model evaluation, prompt engineering, regression testing, red teaming, hallucination detection, RAG testing, Agent testing, A/B testing, LLM-as-a-Judge. Applicable to quality…

Miaoge-Ge/coding-agent-skills

Skill Claude CodeCodex

Part of threejs

Three.js interaction - raycasting, controls, mouse/touch input, object selection. Use when handling user input, implementing click detection, adding camera controls, or creating interactive 3D experiences.

robzilla1738/roberts-skills

Skill Claude CodeCodex

Part of bughunt-suite

Triage a suspected bug or a set of findings into a ranked, evidence-backed report: assign severity and confidence, build a minimal reproduction or failing test, and emit the standard finding schema (markdown + JSON). Use when the user invokes /triage, hands you a crash or suspicious behavior to assess, or when bughunt…

robzilla1738/roberts-skills

Skill Claude CodeCodex

Part of macos-sandbox

Test, launch, debug, smoke-test, or validate a macOS .app or .pkg in a disposable local Tart VM via macbox CLI or MCP. Use when the user mentions macbox, macOS sandbox, VM smoke test, guest automation, or isolated app testing.

robzilla1738/roberts-skills

Skill Claude CodeCodex

Part of svvarm

Opinionated design director for frontend interfaces. Use for ANY frontend design task: building UIs, reviewing designs, fixing typography, improving layouts, checking for AI slop, or making interfaces production-ready. Understands natural language — just describe what you need. One command, zero AI slop.

honeycomb-Technologies/Mitsuro

Skill Claude CodeCodexCursor

Gated improvement loop that deepens modules, simplifies expression, and speeds hot paths without deleting dead code or changing behavior, design, or state. Use when the user says quality-improve, fire the quality loop, deepen modules, simplify without deleting, or write simple-and-advanced code.

honeycomb-Technologies/Mitsuro

Skill Claude CodeCodex

Create or update Sampo changesets for Mitsuro version bumps and changelogs.

EZotoff/ez-omo-config

Skill Claude CodeCodex

Structured adversarial analysis protocol. Quick single-agent modes (challenge, panel, pre-mortem, red team) plus a decision-review protocol where one agent proposes, one critiques, the proposer revises, and a binding/advisory judge panel decides ADOPT/REVISE/REJECT/ESCALATE.

EZotoff/ez-omo-config

Skill Claude CodeCodex

Reader-first writing for any deliverable a human reads to understand a result: HTML reports, MD design docs, debate-result summaries, survey dashboards, executive briefs, handoff notes, panel-review syntheses. Writes for a reader who has NOT read the preceding material. NOT for: bug reports, incident reports, status…

EZotoff/ez-omo-config

Skill Claude CodeCodex

Safety-critical operational pipeline for analyzing and executing OpenCode/OMO updates with explicit approval, patch preservation, rollback capability, and evidence-state discipline.