Agent skill

Oai Solution Reviewer

by shepherdjerred in shepherdjerred/monorepo

This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my…

GPL-3.0Auto-check passedBusiness, Finance & HR

Install Oai Solution Reviewer

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .claude/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .claude/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .agents/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .agents/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .agents/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .cursor/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .cursor/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/shepherdjerred/monorepo.git --path packages/dotfiles/dot_agents/skills/oai-solution-reviewer

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .gemini/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .gemini/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .github/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .github/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .github/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install shepherdjerred/monorepo oai-solution-reviewer --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/shepherdjerred/monorepo.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/packages/dotfiles/dot_agents/skills/oai-solution-reviewer .opencode/skills/oai-solution-reviewer && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "oai-solution-reviewer" agent skill from https://github.com/shepherdjerred/monorepo/tree/main/packages/dotfiles/dot_agents/skills/oai-solution-reviewer into .opencode/skills/oai-solution-reviewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "oai-solution-reviewer", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: oai-solution-reviewer
GitHub stars: 112
Token cost: ~1.9k tokens
SKILL.md length: 711 words
Files: 3 (incl. references)
Skills in repo: 63
Repo updated: Oct 10, 2026
First seen: Oct 7, 2026
Licence: GPL-3.0

At a glance

This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my…

Works in 4 steps: Read the Solution → Evaluate Four Dimensions → Assess Follow-up Readiness → …
Asks to grade my solution
SKILL.md covers When to Use, Evaluation Workflow and Additional Resources
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Oai Solution Reviewer is an agent skill from shepherdjerred/monorepo. This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my interview prep", "evaluate my solution", "how would this score", or wants feedback on a coding interview practice solution. Evaluates Java implementations against OpenAI interviewer grading criteria and produces a comprehensive grade sheet with letter grades, numeric scores, pass/fail, and prose feedback.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/grading-rubric.md` and `references/java-quality-checklist.md`).

It sits in Business, Finance & HR, covering Interview preparation. It works with Java and OpenAI. The repository describes itself as: Monorepo for all of my projects. The licence is GPL-3.0.

When your agent uses it

Asks to grade my solution
Review my OAI prep
Grade my practice problem
Review my interview prep

Example prompts

“grade my solution”
“review my code”
“score this”
“/oai-solution-reviewer”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

Read the Solution
Evaluate Four Dimensions
Assess Follow-up Readiness
Generate Grade Sheet

What it can do on your machine

Read from SKILL.md and the folder at commit d66c497. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Oai Solution Reviewer loads about 1.9k tokens when it runs, and up to ~6.2k if it reads all its reference files. Until then it costs about 131 tokens; SKILL.md has 711 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~131
When it runs · the whole SKILL.md, loaded when a task matches: ~1.9k
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~6.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shepherdjerred/monorepo at commit d66c497, republished under its GPL-3.0 licence (© shepherdjerred). 711 words, ~1,913 tokens.

Download SKILL.mdSave it as .claude/skills/oai-solution-reviewer/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: oai-solution-reviewer
description: This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my interview prep", "evaluate my solution", "how would this score", or wants feedback on a coding interview practice solution. Evaluates Java implementations against OpenAI interviewer grading criteria and produces a comprehensive grade sheet with letter grades, numeric scores, pass/fail, and prose feedback.

OAI Solution Reviewer

Grade coding interview practice solutions against OpenAI's interviewer evaluation criteria. Produces a structured grade sheet combining letter grades (A-F), numeric scores (1-4), pass/fail verdicts, and detailed prose feedback per dimension.

When to Use

User solutions are typically in sandbox/practice/leetcode/src/main/java/sjer/red/openai/ with progressive parts (P1, P2, P3+). Works for any coding problem, not just OAI-specific ones. The user writes Java.

Evaluation Workflow

Step 1: Read the Solution

Read the implementation file(s) the user wants graded. If the problem has multiple parts (P1, P2, P3), read all completed parts to assess follow-up readiness. Do not read or grade test files -- focus on the implementation only.

Identify from the code:

The problem being solved (from Javadoc header or class name)
Which part number this is (P1, P2, P3, etc.)
Whether earlier parts exist (to evaluate progression)

Step 2: Evaluate Four Dimensions

Score each dimension using the detailed rubric in references/grading-rubric.md. Consult references/java-quality-checklist.md for Java-specific quality signals.

Dimension 1 -- Problem Solving

Is the approach correct and efficient?
Are the right data structures chosen for the job?
Is time/space complexity optimal or near-optimal?
Are tradeoffs considered (visible in comments or design choices)?
Does the solution handle the problem's core constraints?

Dimension 2 -- Code Quality

Are variable/method names meaningful and descriptive?
Is logic decomposed into helper methods with single responsibility?
Are edge cases handled proactively (null, empty, boundaries)?
Is the code readable without requiring mental gymnastics?
Are Java idioms used correctly? (Consult references/java-quality-checklist.md)
Is this production-quality code, not just "passes the tests" code?

Dimension 3 -- Communication

Does the code self-document through naming and structure?
Do comments explain why, not what?
Is the API design clear (method signatures, return types, Javadoc)?
Is reasoning visible in the code (approach comments, tradeoff notes)?
Template exclusion: The class-level Javadoc problem header is template-provided, not user-written. Do not credit it. Only evaluate user-authored communication: naming choices, structural clarity, inline comments, method-level Javadoc they added, and tradeoff notes.
Limitation: Verbal fluency and live interviewer interaction cannot be assessed from written code. Note this in the grade sheet.

Dimension 4 -- Testing

Does the implementation defensively handle edge cases in its logic?
Are boundary conditions addressed (empty collections, zero, negative, overflow)?
Are error conditions handled gracefully (exceptions, invalid input)?
Is there evidence of thinking about what could go wrong?
Contract vs boundary distinction: Only penalize missing null handling for boundary inputs (user-facing data, external API responses). When null represents a broken caller contract (e.g., a Function<> parameter returning null), an NPE is the correct failure mode -- do not penalize its absence.

Show full SKILL.md (292 more words)Show less

Step 3: Assess Follow-up Readiness

If the solution is part of a progressive series (P1 -> P2 -> P3):

Is the code modular enough that the next part would NOT require a rewrite?
Are abstractions at the right level to accommodate added complexity?
Would adding concurrency, persistence, or new features require gutting the existing design?

If earlier parts exist, compare: did the code evolve gracefully, or did each part require starting over?

Step 4: Generate Grade Sheet

Produce the grade sheet in exactly this format:

# Grade Sheet: [Problem Name] -- Part [N]

## Overall Verdict: [Strong Hire / Hire / Lean No Hire / Strong No Hire]

## Dimension Scores

| Dimension | Letter | Score (1-4) | Pass/Fail |
|-----------|--------|-------------|-----------|
| Problem Solving | [A-F] | [1.0-4.0] | [PASS/FAIL] |
| Code Quality | [A-F] | [1.0-4.0] | [PASS/FAIL] |
| Communication | [A-F] | [1.0-4.0] | [PASS/FAIL] |
| Testing | [A-F] | [1.0-4.0] | [PASS/FAIL] |

## Detailed Feedback

### Problem Solving [Letter | Score/4 | PASS/FAIL]
**Strengths:** [what was done well]
**Improvements:** [specific, actionable changes]

### Code Quality [Letter | Score/4 | PASS/FAIL]
**Strengths:** [what was done well]
**Improvements:** [specific, actionable changes]
**Java-specific:** [idiom usage, anti-patterns found]

### Communication [Letter | Score/4 | PASS/FAIL]
**Strengths:** [what was done well]
**Improvements:** [specific, actionable changes]
*Note: Verbal communication cannot be assessed from written code.*

### Testing [Letter | Score/4 | PASS/FAIL]
**Strengths:** [defensive coding observed]
**Improvements:** [edge cases missed, error handling gaps]

## Follow-up Readiness
- Could this code extend to Part [N+1] without a rewrite? [Yes/No/Partial]
- What would need to change? [specific refactoring needed]

## If This Were a Real Interview...
[1-2 paragraph honest, direct assessment. No sugarcoating. Would this pass at OAI?
What would the interviewer's internal notes say? What would tip the decision?]

## Top 3 Action Items
1. [highest-impact improvement]
2. [second priority]
3. [third priority]

Scoring Guide (Quick Reference)

Score	Letter	Verdict	Pass/Fail Threshold
3.7-4.0	A/A+	Strong Hire	PASS
3.3-3.6	A-/B+	Hire	PASS
3.0-3.2	B/B+	Hire (borderline)	PASS
2.5-2.9	B-/C+	Lean No Hire	FAIL
2.0-2.4	C/C-	Lean No Hire	FAIL
1.0-1.9	D/F	Strong No Hire	FAIL

Pass threshold is 3.0 (maps to "Hire"). Overall verdict is the lowest dimension verdict -- one FAIL dimension means the overall cannot be higher than Lean No Hire.

Grading Principles

Be honest, not encouraging. The goal is to prepare for a real interview, not to feel good. A 2.5 is a 2.5.
Be specific, not vague. "Naming could be better" is useless. "Rename m to cellDependencies on line 47" is actionable.
Grade against OAI's bar, not a general bar. OAI expects production-quality code. A solution that "works" but is messy is a Lean No Hire.
Acknowledge what's done well. Strong Hire signals should be called out so the user knows what to keep doing.
Java-specific feedback matters. Using Stack instead of ArrayDeque or raw types is a concrete signal to interviewers.

Additional Resources

Reference Files

For detailed scoring criteria and checklists, consult:

references/grading-rubric.md -- Per-dimension scoring criteria at each level (Strong Hire through Strong No Hire) with concrete examples
references/java-quality-checklist.md -- Java-specific idiom checks, anti-pattern detection, and data structure selection guidance

Files

SKILL.md and 2 other files (references) in packages/dotfiles/dot_agents/skills/oai-solution-reviewer of shepherdjerred/monorepo.

SKILL.md
references/grading-rubric.md
references/java-quality-checklist.md

Open the folder on GitHubat commit d66c497

Compare with similar skills

Oai Solution Reviewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Oai Solution Reviewer compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Oai Solution Reviewer this skillshepherdjerred/monorepo	112	—	~1.9k	Automated safety check: Pass	GPL-3.0	today
Backend Interview SimulatorHazehacker/backend-interview-simulator	208	—	~2.3k	Automated safety check: Pass	MIT	2 mo ago
Classify Interview Questionsranxi2001/zero2Agent	715	—	~2.6k	Automated safety check: Pass	MIT	today
Java Backend InterviewerSnailclimb/interview-guide	3.3k	—	~132	Automated safety check: Pass	AGPL-3.0	yesterday
Tencent Java Backend InterviewSnailclimb/interview-guide	3.3k	—	~143	Automated safety check: Pass	AGPL-3.0	yesterday
Claude APIKocoro-lab/Kocoro	414	7 repos	~4.5k	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

Backend Interview Simulator
Hazehacker/backend-interview-simulator
A skill your agent uses when users want to practice or simulate Java, C++, Go, Golang, mixed-stack, or general backend technical interviews, including resume-based and job-description-based…
208 GitHub stars~2.3k tokensUpdated 2 mo ago
Business, Finance & HRAuto-check passed
Classify Interview Questions
ranxi2001/zero2Agent
将批量面经或零散面试题逐题去重并分发：Agent/LLM/AI工程题写入 zero2Agent 的 learn-agent-interview，传统后端八股写入相邻 zero2Leetcode 的夏季八股。大批量输入使用 gpt-5.6-luna API 逐篇并发抽题和语义召回，再审查、去重和写答案；不新建面经实录文章。
715 GitHub stars~2.6k tokensUpdated today
Business, Finance & HRAuto-check passed
Java Backend Interviewer
Snailclimb/interview-guide
Acts as a Java backend interviewer who asks about Java core, MySQL, Redis, Spring and project work, then probes design trade-offs, failure handling and performance.
3.3k GitHub stars~132 tokensUpdated yesterday
Business, Finance & HRAuto-check passed
Tencent Java Backend Interview
Snailclimb/interview-guide
Sets the agent up as a Tencent-style backend interviewer who probes networking and operating-system fundamentals, then ties technology choices to business scenarios.
3.3k GitHub stars~143 tokensUpdated yesterday
Business, Finance & HRAuto-check passed
Claude API
Kocoro-lab/Kocoro
Build apps with the Claude API or Anthropic SDK. An agent skill from Kocoro-lab/Kocoro.
414 GitHub starsUsed in 7 repos~4.5k tokens
AI & LLM EngineeringAuto-check passed
Workflow AI Coding
w8123/EnterpriseAgentFramework
Edit, validate, debug, publish, and inspect ReachAI Workflow drafts through the Workflow AI Coding REST API.
865 GitHub stars~3.7k tokensUpdated 3 days ago
AI & LLM EngineeringAuto-check passed

Questions about Oai Solution Reviewer

What does Oai Solution Reviewer do?

This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my…. Oai Solution Reviewer is an agent skill from shepherdjerred/monorepo. This skill should be used when the user asks to "grade my solution", "review my code", "score this", "how did I do", "grade sheet", "review my OAI prep", "grade my practice problem", "review my interview prep", "evaluate my solution", "how would this score", or wants feedback on a coding interview practice solution.

When should I use Oai Solution Reviewer?

Oai Solution Reviewer fits situations like: asks to grade my solution; review my OAI prep; grade my practice problem; review my interview prep.

How do I install Oai Solution Reviewer in Claude Code?

Run `npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a claude-code`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/oai-solution-reviewer in shepherdjerred/monorepo) into .claude/skills/oai-solution-reviewer in your project. Claude Code loads it when a task matches its description.

How do I install Oai Solution Reviewer in Codex?

Run `npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a codex`. Or copy the skill folder (packages/dotfiles/dot_agents/skills/oai-solution-reviewer in shepherdjerred/monorepo) into .agents/skills/oai-solution-reviewer in your project. Codex loads it when a task matches its description.

Can I use Oai Solution Reviewer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add shepherdjerred/monorepo --skill oai-solution-reviewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/oai-solution-reviewer, .gemini/skills/oai-solution-reviewer, .github/skills/oai-solution-reviewer and .opencode/skills/oai-solution-reviewer in your project.

What does Oai Solution Reviewer need to run?

SKILL.md names no scripts, command-line tools or credentials: Oai Solution Reviewer is instructions for the agent only.

Does Oai Solution Reviewer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Oai Solution Reviewer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Oai Solution Reviewer use?

Oai Solution Reviewer is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Oai Solution Reviewer use?

About 1.9k tokens (SKILL.md is roughly 7.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 4.3k tokens, read only when the agent opens those files.

What are the alternatives to Oai Solution Reviewer?

Skills that share tags, products or a category with Oai Solution Reviewer: Backend Interview Simulator (Hazehacker/backend-interview-simulator, 208 stars), Classify Interview Questions (ranxi2001/zero2Agent, 715 stars), Java Backend Interviewer (Snailclimb/interview-guide, 3.3k stars) and Tencent Java Backend Interview (Snailclimb/interview-guide, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Oai Solution Reviewer?

shepherdjerred (a GitHub user) maintains it in shepherdjerred/monorepo, which has 112 GitHub stars. The repository holds 63 skills in this directory. The repository was last updated on October 10, 2026.

Source: shepherdjerred/monorepo on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Oai Solution Reviewer

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

OAI Solution Reviewer

When to Use

Evaluation Workflow

Step 1: Read the Solution

Step 2: Evaluate Four Dimensions

Step 3: Assess Follow-up Readiness

Step 4: Generate Grade Sheet

Scoring Guide (Quick Reference)

Grading Principles

Additional Resources

Reference Files

Files

Compare with similar skills

Similar skills

More from shepherdjerred/monorepo

Related

Questions about Oai Solution Reviewer