Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/write-better-skill/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thunderkds/easy-ui-mcp/write-better-skill)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/write-better-skill"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/write-better-skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/write-better-skill"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/write-better-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00068 | $0.03265 |
| Opus 5.5 | $0.00027 | $0.01306 |
| Sonnet 5.5 | $0.00014 | $0.00653 |
| Haiku 4.5 | $0.00007 | $0.00327 |
Grade A, and why
write-better-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Skill Craft Reference
The authoritative vocabulary and principles for writing predictable Claude Code skills in this framework. Consumed by the teach skill during draft generation and invoked directly when auditing or refactoring an existing SKILL.md. All reference — no sequential steps.
Predictability — the agent taking the same process every run, not producing the same output — is the root virtue every rule below serves.
Invocation
Two choices, trading different loads:
- Model-invoked: keep a
descriptionwith rich trigger phrasing. Other skills can reach it. Contributes context load every turn. Use when the agent must fire it autonomously or another skill must call it. - User-invoked: set
disable-model-invocation: true. Only the user (typing the name) can invoke it — no other skill can reach it. Zero context load; costs cognitive load (you must remember it exists). Description becomes human-facing; strip trigger phrasing.
Pick model-invocation only when autonomous reach is required. When user-invoked skills multiply past memory, a router skill (one user-invoked skill that names the rest) cures the cognitive load.
Writing the description
A model-invoked description does two jobs: state what the skill is, and list the branches that trigger it. Every word is context load — prune harder than the body.
- Front-load the leading word — the description is where it does its invocation work.
- One trigger per branch. Synonyms that rename a single branch are duplication — collapse them.
- Cut identity already in the body. Keep triggers plus any "when another skill needs…" reach clause.
Read references/descriptions.md when writing or revising a model-invoked description — it carries the rules that decide whether the skill fires at all (imperative phrasing, user intent, pushiness) and the trigger-eval method for testing one.
Agent Skills Spec Conformance
This framework's skills implement the open Agent Skills specification. The rules below are normative — a skill that breaks one is malformed, not merely unpolished. Checked automatically by .claude/hooks/tests/test_skill_spec_conformance.py over every directory in .claude/skills/.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 193 lines · 68 tokens per session scan A 1737534698fb
write-better-skill is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 3,265 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.