NeVibeCode · repository · 21 items
skills: a set by srinitude
The srinitude/skills repository on GitHub: 21 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.
About the repository
- GitHub
- srinitude/skills
- Stars
- ★ 2
- Installs across cards
- 10,389
- License
- MIT
- Source updated
- 2026-10-21
- In the catalog since
- 2026-10-26
starting-point skill starting-point directs coding agents to verify the observable outcome instead of blindly executing a method that fails to solve or prove the problem.
CX Codex +1
714installs
reify skill reify turns vague ideas, fragments, and loose concepts into concrete artifacts, decision records, or verified handoffs.
CX Codex +1
691installs
visual-design-system-extractor skill visual-design-system-extractor is a Claude Code skill that turns screenshots, moodboards, and web pages into a strict YAML design system, matching visual details with rare Google Fonts.
CX Codex +1
689installs
skill-factory skill skill-factory is a Claude Code skill that builds, updates, and standardizes agent skills with checks, tests, evals, and a Mise task graph. It handles workflows that need a reusable skill package.
CX Codex +1
682installs
always-current-datetime skill The always-current-datetime skill refreshes local date and time before each direct reply. It helps agents handle relative dates, deadlines, and time zones without guessing.
CX Codex +1
558installs
outcome-bounded-work skill The outcome-bounded-work skill separates required outcomes and proof from replaceable implementation recipes. Use it when a task, plan, or policy mixes goals with one suggested method.
CX Codex +1
555installs
timebox skill timebox — a skill that takes on a task only when the full job and its validation can finish before the deadline you name.
CX Codex +1
545installs
logic-audit skill Logic audit locates contradictions and reasoning gaps in specifications, plans, and prose. It verifies claims against sources and drafts minimal fixes.
CX Codex +1
545installs
meaning-preserving-rewrite skill meaning-preserving-rewrite rewrites policies, plans, and technical standards in plain language without dropping clauses or altering rule strictness. Keeps every constraint intact.
CX Codex +1
545installs
would-humans-actually skill would-humans-actually evaluates whether people will perform a real action using primary empirical evidence. Separates declared intentions from observable behavior.
CX Codex +1
543installs
dedupe skill dedupe builds a duplicate report with evidence for a bounded collection. It separates discovery, grouping, canonical choice, mutation, and verification, so data present in only one item cannot vanish during cleanup.
CX Codex +1
542installs
simplify-skill skill simplify-skill simplifies complex agent skills without losing existing behavior or contracts. Cuts accidental instruction clutter while preserving all tests and outputs.
CX Codex +1
540installs
would-agents-actually skill would-agents-actually evaluates whether an agent system will execute or avoid specific actions based on execution traces and real environment state. Useful before granting autonomous permissions.
CX Codex +1
536installs
goal-prompt skill Packages prompts, text files, and plans into standing goal specifications without altering their meaning. Useful for creating deterministic execution contracts.
CX Codex +1
535installs
prompt-enhancer skill prompt-enhancer takes your prompt and hands back a clearer, more specific version of it. It never runs the prompt for you.
CX Codex +1
328installs
mobile-first-website-design skill mobile-first-website-design — a skill that walks the agent through landing and marketing pages: style-free structure first, identity second, implementation from the narrowest width up.
CX Codex +1
321installs
design-like-im-5 skill design-like-im-5 — a skill for designing and reviewing interfaces: keeps the user-facing core simple and checks states, inputs and screen sizes.
CX Codex +1
306installs
tool-call-configuration-for skill tool-call-configuration-for turns one verified tool contract plus your behavior notes into a tool-specific skill, or folds that behavior into an existing skill.
CX Codex +1
306installs
only-one-interpretation skill only-one-interpretation turns ambiguous prompts into a single bounded interpretation or asks clarifying questions. It keeps agents from guessing missing requirements.
CX Codex +1
303installs
dtcg-tokens skill dtcg-tokens is a skill for Claude Code that converts multimodal sources into DTCG 2025.10 JSON with a vision-reviewed HTML proof artifact. It exposes generate, validate, and prove commands through Mise tasks.
CX Codex +1
303installs
by-design skill by-design turns design critique into a record of choices, trade-offs, and decisions no one made. Use it to assess an existing screen or shape work that has not been built yet.
CX Codex +1
302installs