Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xiaoshiyilangzhao1996-droid/Skill-Schema-V2 --skill skill-schema-v2.skillgit clone --depth 1 https://github.com/xiaoshiyilangzhao1996-droid/Skill-Schema-V2Wrote 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/xiaoshiyilangzhao1996-droid/skill-schema-v2/skill-schema-v2.skill)<a href="https://agentmods.dev/skills/xiaoshiyilangzhao1996-droid/skill-schema-v2/skill-schema-v2.skill"><img src="https://agentmods.dev/badge/skills/xiaoshiyilangzhao1996-droid/skill-schema-v2/skill-schema-v2.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/xiaoshiyilangzhao1996-droid/skill-schema-v2/skill-schema-v2.skill"><img src="https://agentmods.dev/badge/skills/xiaoshiyilangzhao1996-droid/skill-schema-v2/skill-schema-v2.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 | $0.00028 | $0.01353 |
| Opus 5.5 | $0.00011 | $0.00541 |
| Sonnet 5.5 | $0.00006 | $0.00271 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
skill-schema-v2 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 16d ago.
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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Schema v2
Use this skill to design, audit, or repair Agent Skills as reusable capability packages. v2 is based on three current findings:
- A skill is a readable task contract, not a prompt fragment.
- A skill must be routable and reusable, not just useful in its original chat or repo.
- A skill should expose a minimal runtime boundary, not inject every reference into context.
Core Model
Every serious skill has three surfaces:
Routing Surface
name + description + frontmatter
Decides whether the skill is loaded.
Contract Surface
goal + inputs + permissions + evidence + output + verification + handoff
Decides what correct behavior means.
Runtime Boundary Surface
docs + examples + scripts + operators + fallback paths
Decides what gets loaded or executed after selection.
These surfaces must not contradict each other. If the description routes one task, the contract must govern that task, and runtime resources must support that task.
Hard Rules
- Description is routing metadata. It must start with
Load when...or an equivalent trigger phrase, describe when to load the skill, and stay short enough for startup routing. - SKILL.md is not a knowledge warehouse. Keep it as the routing and contract surface. Put detailed references, examples, templates, long rules, and papers in
docs/,examples/,templates/, orscripts/. - Use contract fields only when they reduce ambiguity. Do not add enterprise fields as ceremony. Add goal, inputs, permissions, evidence, output, verification, or handoff only when they affect behavior.
- Runtime resources load progressively. A skill should reveal a compact handle first, then load detailed docs or run scripts only when needed.
- Safety belongs in both language and enforcement. The skill can state permissions, human gates, and evidence policy; tools, adapters, guardrails, tests, or humans must still enforce high-risk actions.
- No persona hijack unless persona is the product. Avoid “you are...” identity rewrites, instruction overrides, hidden authority claims, and scope drift.
- No hidden local coupling. Avoid hardcoded credentials, local-only paths, stale install instructions, repo-specific assumptions, or unportable scripts unless clearly marked.
- Every repair needs verification. A repaired skill must be re-audited against routing, contract, runtime boundary, safety, portability, and self-consistency.
What ships with it
4 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.
- 16d ago First seen · 177 lines · 28 tokens per session scan A 86f3d74b65d8
skill-schema-v2 is a skill published in the GitHub repository xiaoshiyilangzhao1996-droid/Skill-Schema-V2 (16 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,353 once invoked, about $0.0001 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 2026-10-02.
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…
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…