Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Open Code Review · spencermarx | DecimalAI

code reviewby spencermarx

Open Code Review

spencermarx/ocr

Source spencermarx/open-code-review ↗License Apache-2.0

AI-powered multi-agent code review. Simulates a team of Principal Engineers reviewing code from different perspectives.

SkillScore68Maintained

Automatic

Coding pack

Last verified 8/21/2026

What it changes

Passed 12 of 18 test cases with the skill, and 5 of 18 without it.

Without skill27%

With skill68%

Checks it passed that the model alone missed

Uses the hyphenated slash command /ocr-doctor.
Assigns exactly 2 Quality reviewers to the team.
Assigns exactly 2 Principal reviewers to the team.

and 9 more in the full report

11 fixed4 passed either way5 still failing2 broke

Pass-rate lift: +41 pp
Tokens: +93%
Agent turns: 0%
Response time: -55%

Model gemini-3.6-flashMeasured 8/21/2026v115 of 22 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/spencermarx-ocr/SKILL.md https://app.decimal.ai/s/spencermarx-ocr/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add spencermarx-ocr, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/spencermarx-ocr/ and pins it in .decimal/skills.lock

decimalai skills add spencermarx-ocr

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/spencermarx-ocr/SKILL.md https://app.decimal.ai/s/spencermarx-ocr/SKILL.md

Raw file: /s/spencermarx-ocr/SKILL.md ↗ · machine-readable summary at /s/spencermarx-ocr.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

In a Claude Code terminal session, what is the exact slash command to inspect past review session history?

What was checked, without and with the skill
Checked	Without skill	With skill
Uses the colon-separated slash command /ocr:history.	Missed	Passed

case-10 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md204 lines14 files

Open Code Review

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.

When to Use This Skill

Activate when the user:

Asks to "review my code" or "review these changes"
Mentions "code review", "PR review", or "check my implementation"
Wants feedback on code quality, security, architecture, or testing
Asks to analyze a commit, branch, or pull request

⚠️ IMPORTANT: Setup Guard (Run First!)

Before ANY OCR operation, you MUST validate that OCR is properly set up:

Read and execute references/setup-guard.md
If setup validation fails → STOP and show the user the error message
If setup validation passes → Proceed with the requested operation

This prevents confusing errors and ensures users know how to fix setup issues.

Quick Start

For immediate review of staged changes:

Run the setup guard (see above - this is mandatory!)
Read references/workflow.md for the complete 8-phase process
Begin with Phase 1: Context Discovery
Follow each phase sequentially

Core Responsibilities

As Tech Lead, you must:

Gather Requirements - Accept and analyze any provided specs, proposals, tickets, or context
Discover Context - Load .ocr/config.yaml, pull OpenSpec context, and discover referenced files
Understand Changes - Analyze git diff to understand what changed and why
Evaluate Against Requirements - Assess whether changes meet stated requirements
Identify Risks - Determine which aspects need scrutiny (security, performance, etc.)
Assign Reviewers - Select appropriate reviewer personas based on change type

Track record

Benchmark

12 / 18

test cases passed, vs 5 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

spencermarx / open-code-review

.ocr/skills/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1Bundled 13 files

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Open Code Review

When to Use This Skill

⚠️ IMPORTANT: Setup Guard (Run First!)

Quick Start

Core Responsibilities

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills