Skill
ork-assess
Assess a code change, design, architecture, workflow, or competing options against explicit criteria and evidence. Use when a request asks to assess, rate,…
@yonatangrossView SkillDevelopment
Skill
/ork-review-pr
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or
Install
$ npx -y skills add yonatangross/orchestkit --skill ork-review-pr --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/ork-review-pr
Context preview
The summary Claude sees to decide when to auto-load this skill.
Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or
SKILL.md
ork-review-pr.SKILL.mdname: ork-review-pr
description: Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.
Ork Review PR
Stay read-only and review the actual diff in its repository context. Read the applicable instructions, trace changed behavior to its callers and tests, and prioritize correctness, security, data loss, race conditions, backwards compatibility, and evidence gaps over style.
Verify third-party API and configuration claims against the context7 MCP server (`resolve-library-id`, then `query-docs`) before reporting or dismissing a finding that turns on library behavior. A wrong recalled signature is how a review invents a bug and how it misses one.
Use one reviewer for a focused diff. For a broad or high-risk PR, fan out independent read-only passes for code-path mapping, risk review, and documentation/API verification; each must return file and line evidence. Prefer `ork_reviewer` when installed, otherwise use a fresh built-in explorer/reviewer role.
Lead with findings ordered by severity. Every finding needs a concrete location, impact, and a reproduction or reasoning path. If there are no findings, say what was checked and what was not. Do not modify files or approve/merge the PR.
Read more
name: ork-review-pr description: Review a pull request or branch for correctness, regressions, security, operational risk, and missing evidence. Use when a request asks to review a PR, review a diff, find real bugs, assess merge risk, or provide evidence-backed review findings. Do not use for implementation or style-only cleanup.
Ork Review PR
Stay read-only and review the actual diff in its repository context. Read the applicable instructions, trace changed behavior to its callers and tests, and prioritize correctness, security, data loss, race conditions, backwards compatibility, and evidence gaps over style.
Verify third-party API and configuration claims against the context7 MCP server (`resolve-library-id`, then `query-docs`) before reporting or dismissing a finding that turns on library behavior. A wrong recalled signature is how a review invents a bug and how it misses one.
Use one reviewer for a focused diff. For a broad or high-risk PR, fan out independent read-only passes for code-path mapping, risk review, and documentation/API verification; each must return file and line evidence. Prefer `ork_reviewer` when installed, otherwise use a fresh built-in explorer/reviewer role.
Lead with findings ordered by severity. Every finding needs a concrete location, impact, and a reproduction or reasoning path. If there are no findings, say what was checked and what was not. Do not modify files or approve/merge the PR.
Ships withorchestkit
The Complete AI Development Toolkit for Claude Code. 106 skills, 36 agents, 171 hooks. Install `ork` for stable (v9.x), or `ork-alpha` for the v10 line, which ships daily.
Get the whole plugin
Stats
277
Stars
31
Forks
Active
Maintenance
TypeScript
Language
MIT
License
7h ago
Last commit
8mo ago
Created
Repo: yonatangross/orchestkit
Other skills on orchestkit.
@yonatangrossView SkillSkill
ork-brainstorm
Compare plausible implementation, architecture, product, or operational approaches before committing to one. Use when a request asks to brainstorm, think…
@yonatangrossView SkillSkill
ork-explore
Map an unfamiliar codebase, feature, architecture, data flow, or operational path with file-backed evidence. Use when a request asks how a system works, where…
@yonatangrossView SkillSkill
ork-implement
Make an approved, scoped change and prove the affected behavior. Use when a request asks to implement, build, add, or land a feature that already has an agreed…
@yonatangrossView SkillSkill
ork-verify
Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove,…
@yonatangrossView SkillSkill
accessibility
Accessibility patterns for WCAG 2.2 compliance, keyboard focus management, React Aria component patterns, cognitive inclusion, native HTML-first philosophy,…
@yonatangrossView Skill