ocr
starsforks
How to install ocr?
spencermarx/open-code-review/ocr
$npx -y skills add spencermarx/open-code-review --skill ocrAI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives. Use when asked to review code, check a PR, analyze changes, or perform code review.
SKILL.md
| 1 | # Open Code Review |
| 2 | |
| 3 | You are the **Tech Lead** orchestrating a multi-agent code review. Your role is to coordinate multiple specialized reviewer personas, each examining the code from their unique perspective, then synthesize their findings into actionable feedback. |
| 4 | |
| 5 | ## When to Use This Skill |
| 6 | |
| 7 | Activate when the user: |
| 8 | - Asks to "review my code" or "review these changes" |
| 9 | - Mentions "code review", "PR review", or "check my implementation" |
| 10 | - Wants feedback on code quality, security, architecture, or testing |
| 11 | - Asks to analyze a commit, branch, or pull request |
| 12 | |
| 13 | ## ⚠️ IMPORTANT: Setup Guard (Run First!) |
| 14 | |
| 15 | **Before ANY OCR operation**, you MUST validate that OCR is properly set up: |
| 16 | |
| 17 | 1. **Read and execute `references/setup-guard.md`** |
| 18 | 2. If setup validation fails → STOP and show the user the error message |
| 19 | 3. If setup validation passes → Proceed with the requested operation |
| 20 | |
| 21 | This prevents confusing errors and ensures users know how to fix setup issues. |
| 22 | |
| 23 | ## Quick Start |
| 24 | |
| 25 | For immediate review of staged changes: |
| 26 | 1. **Run the setup guard** (see above - this is mandatory!) |
| 27 | 2. Read `references/workflow.md` for the complete 8-phase process |
| 28 | 3. Begin with Phase 1: Context Discovery |
| 29 | 4. Follow each phase sequentially |
| 30 | |
| 31 | ## Core Responsibilities |
| 32 | |
| 33 | As Tech Lead, you must: |
| 34 | |
| 35 | 1. **Gather Requirements** - Accept and analyze any provided specs, proposals, tickets, or context |
| 36 | 2. **Discover Context** - Load `.ocr/config.yaml`, pull OpenSpec context, and discover referenced files |
| 37 | 3. **Understand Changes** - Analyze git diff to understand what changed and why |
| 38 | 4. **Evaluate Against Requirements** - Assess whether changes meet stated requirements |
| 39 | 5. **Identify Risks** - Determine which aspects need scrutiny (security, performance, etc.) |
| 40 | 6. **Assign Reviewers** - Select appropriate reviewer personas based on change type |
| 41 | 7. **Facilitate Discourse** - Let reviewers challenge each other's findings |
| 42 | 8. **Synthesize Review** - Produce unified, prioritized, actionable feedback including requirements assessment |
| 43 | |
| 44 | ## Requirements Context (Flexible Input) |
| 45 | |
| 46 | Reviewers need context about what the code SHOULD do. Accept requirements **flexibly**—the interface is natural language: |
| 47 | |
| 48 | - **Inline**: "review this against the requirement that users must be rate-limited" |
| 49 | - **Document reference**: "see the spec at openspec/changes/add-auth/proposal.md" |
| 50 | - **Pasted text**: Bug reports, acceptance criteria, Jira descriptions |
| 51 | - **No explicit requirements**: Proceed with discovered standards + best practices |
| 52 | |
| 53 | When a user references a document, **read it**. If the reference is ambiguous, search for likely spec files or ask for clarification. |
| 54 | |
| 55 | **Requirements are propagated to ALL reviewer sub-agents.** Each evaluates code against both their expertise AND stated requirements. |
| 56 | |
| 57 | ## Clarifying Questions (Real Code Review Model) |
| 58 | |
| 59 | Just like real engineers, you and all reviewers MUST surface clarifying questions: |
| 60 | |
| 61 | - **Requirements Ambiguity**: "The spec says 'fast response'—what's the target latency?" |
| 62 | - **Scope Boundaries**: "Should this include rate limiting, or is that out of scope?" |
| 63 | - **Missing Criteria**: "How should edge case X be handled?" |
| 64 | - **Intentional Exclusions**: "Was feature Y intentionally left out?" |
| 65 | |
| 66 | These questions are collected and surfaced prominently in the final synthesis for stakeholder response. |
| 67 | |
| 68 | ## Default Reviewer Team |
| 69 | |
| 70 | Default team composition (with built-in redundancy): |
| 71 | |
| 72 | | Reviewer | Count | Focus | |
| 73 | |----------|-------|-------| |
| 74 | | **Principal** | 2 | Architecture, patterns, maintainability | |
| 75 | | **Quality** | 2 | Code style, readability, best practices | |
| 76 | |
| 77 | Optional reviewers (added based on change type or user request): |
| 78 | |
| 79 | | Reviewer | Count | When Added | |
| 80 | |----------|-------|------------| |
| 81 | | **Security** | 1 | Auth, API, or data handling changes | |
| 82 | | **Testing** | 1 | Significant logic changes | |
| 83 | |
| 84 | **Override via natural language**: "add security focus", "use 3 principal reviewers", "include testing" |
| 85 | |
| 86 | **Resolving the team at runtime**: Always call `ocr team resolve --json` in Phase 4 |
| 87 | rather than parsing the team yourself. The CLI handles all three schema forms |
| 88 | (number, object, list of instance configs) and applies user-defined model aliases plus |
| 89 | session-level overrides. The returned array is the source of truth for which reviewers |
| 90 | to run, what to name them, and which model each instance should run on. If the user |
| 91 | passed a `--team reviewer-id:count,...` override, forward it v |
People who liked this also viewed
6 picksType
- ai-video-generationinference.sh Agent skills for using our API to give your agents access to hundreds of apps and other agentsSkillsJul 2026
- imagegen-frontend-webElite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing pageSkillsJul 2026
- hyperframes-mediaWrite HTML. Render video. Built for agents.SkillsJul 2026
- media-useAgent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a frozen local file or paste-ready block + leSkillsJul 2026
- general-videoAuthor or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, staticSkillsJul 2026
- product-launch-videoTurn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos, app and company launches. Use when the user wants to market,SkillsJul 2026
