15
2
In review
Synced today
What it does
Load when creating, auditing, refactoring, or repairing an Agent Skill for reuse, governance, and runtime efficiency.
Skill profile
Keep exploring
More options in Dev Tools.
Claude Code · Codex · OpenClaw
Updated 6/10/2026
Agent compatibility
Compatibility has not been reviewed for this listing yet. Check the publisher documentation before installing.
Installation
npx skills add https://github.com/xiaoshiyilangzhao1996-droid/Skill-Schema-V2 --skill rootReview source code and installation permissions before adding third-party tools to an agent.
skill-schema-v2 is organized in the Dev Tools category. Compare its source, install method, and compatibility before adding it to your workflow.
Third-party agent tools may access source code, credentials, or browser sessions. Read the source documentation and use the minimum permissions needed.
npx skills add https://github.com/xiaoshiyilangzhao1996-droid/Skill-Schema-V2 --skill rootSKILL.md
--- 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: ```text 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.md` for the complete v2 contract. - `skill-schema-v2.skill/docs/v2-design-spec.md` for design rationale. - `skill-schema-v2.skill/docs/audit-rubric.md` for scoring details. - `skill-schema-v2.skill/docs/repair-playbook.md` for repair patterns. - `docs/paper-digests.md` for paper evidence.
skill
mattpocock
A tool that automates setting up Husky pre-commit hooks with lint-staged, Prettier formatting, type checking, and tests in a code repository.