Automated summary
A compatibility entrypoint skill that guides creating, auditing, refactoring, or repairing Agent Skills against the v2 schema built around three aligned surfaces (routing, contract, runtime boundary).
Strengths
- Clear three-surface model (routing, contract, runtime boundary) with an explicit alignment requirement between them
- Quantified 100-point audit rubric split across eight weighted areas such as routing, contract, safety, and signal density
- Progressive resource loading keeps the body small and only pulls in detailed docs when needed
- Ships repair patterns and paper digests that justify the design decisions behind v2
Limitations
- This file is only the entrypoint: the full contract, audit rubric, and repair playbook live in the skill-schema-v2.skill/ subfolder, so the skill is unusable without those files
- Heavy meta jargon (contract surface, runtime boundary, signal density) assumes prior familiarity with Agent Skill design
- No complete SKILL.md template or filled-in scoring example is provided inline
Use it when designing, scoring, or fixing the SKILL.md of an Agent Skill meant to be reused and governed.
Skip it for ordinary application development or documentation work unrelated to packaging Agent Skills.
Security analysis
SafeThe skill is a documentation and auditing guide for skill schemas. It contains no executable commands, no network access, no file modification instructions, and no dangerous or obfuscated actions. The declared allowed-tools list is empty, consistent with its non-executable nature.
No concerns found
How this analysis is madeExamples
Audit my skill at ./skills/pdf-extractor/SKILL.md with the v2 schema: give me the score out of 100 per area and the top 3 fixes.Refactor this SKILL.md so its routing surface (name, description, frontmatter) matches its contract and runtime boundaries, and tell me what to move into separate docs.Design a new Agent Skill for database migrations using the v2 three-surface model, including goal, inputs, permissions, evidence, output, verification, and handoff.name: skill-schema-v2 description: "Load when creating, auditing, refactoring, or repairing an Agent Skill for reuse, governance, and runtime efficiency." version: "2.0.0" last_updated: "2026-06-02" depends: [] metadata: author: "yinyo" category: "skill-engineering" package: "skill-schema-v2.skill"
Skill Schema V2
This is the compatibility entrypoint for the v2 skill schema. The installable v2 package is in skill-schema-v2.skill/.
Use it when a user is designing, auditing, refactoring, or repairing an Agent Skill.
Core Rule
A skill has three surfaces:
Routing Surface: name + description + frontmatter
Contract Surface: goal + inputs + permissions + evidence + output + verification + handoff
Runtime Boundary Surface: docs + examples + scripts + operators + fallback paths
The three surfaces must be aligned. If the description routes one task, the contract must govern that task, and runtime resources must support that task without forcing irrelevant context into the model.
What Changed in v2
v2 adds three 2026 findings:
- Contractual Skills: skills should be readable task contracts with explicit boundaries and acceptance criteria.
- 138K SKILL.md reusability study: routing defects, body bloat, poor resources, safety issues, portability gaps, and persona/scope conflicts are measurable defects.
- SkillSmith: raw skill injection wastes context; skills should expose minimal runtime boundaries and load detail progressively.
Audit Output
When auditing, score out of 100:
| Area | Points | |---|---:| | Routing | 15 | | Contract | 20 | | Runtime Boundary | 15 | | Reusability | 15 | | Safety | 15 | | Signal Density | 10 | | Versioning | 5 | | Self-Consistency | 5 |
Runtime Resources
Load only as needed:
skill-schema-v2.skill/SKILL.mdfor the complete v2 contract.skill-schema-v2.skill/docs/v2-design-spec.mdfor design rationale.skill-schema-v2.skill/docs/audit-rubric.mdfor scoring details.skill-schema-v2.skill/docs/repair-playbook.mdfor repair patterns.docs/paper-digests.mdfor paper evidence.
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/skill-schema-v2-ms47vqxd' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/skill-schema-v2-ms47vqxd/download' --output '.skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md.part' && mv '.skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md.part' '.skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md' && test -s '.skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/skill-schema-v2' && cp -R '.skill-downloads/skill-schema-v2-ms47vqxd' '.claude/skills/skill-schema-v2'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/skill-schema-v2-ms47vqxd'openskills read 'skill-schema-v2-ms47vqxd'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/skill-schema-v2-ms47vqxd/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.