Fresh Review
Review an artifact with an independent agent that has no access to the author's reasoning, then classify its findings.
Install
npx skills add roman-s8o/workflow-pack-free --skill fresh-reviewgit clone --depth 1 https://github.com/roman-s8o/workflow-pack-free.git /tmp/workflow-pack-free
mkdir -p ~/.claude/skills
cp -r /tmp/workflow-pack-free/.claude/skills/fresh-review ~/.claude/skills/fresh-reviewPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Skill: Fresh-Context Review Get an independent review of an artifact from an agent that has not seen the conversation that produced it. The goal is to catch defects the author cannot see. Use it on: a diff before merge, a plan before approval, a test fixture before it becomes a baseline, a document before it is relied on. --- ## 1. Define the review 1. Identify the target (path, diff range, or document). 2. Write the acceptance criteria the artifact must meet. Take them from `docs/ROADMAP.md` if the project has one; otherwise ask the user. 3. Decide what the reviewer should check and what it should ignore. --- ## 2. Build the brief The reviewer receives ONLY: - the target artifact; - the acceptance criteria; - the project rules from `CLAUDE.md` that apply; - the output format below. The reviewer does NOT receive the author's reasoning, the conversation, or a summary of what the author thinks is right. This avoids anchoring. --- ## 3. Run it in a fresh context Run the review in a separate agent with no shared context: a subagent, or a new session. The reviewer must not modify any file. Ask the reviewer to return findings in this format, or "No findings": - **Finding:** what is wrong - **Location:** file and line, or section - **Evidence:** what in the artifact shows it - **Severity:** high, medium or low - **Suggested fix:** one sentence --- ## 4. Classify the findings For each finding, check it against the artifact yourself and label it:
Details
- Skill name
fresh-review- Repository
- roman-s8o/workflow-pack-free
- Path
.claude/skills/fresh-review/SKILL.md- License
- MIT
- Repo updated
- 21 October 2026
- Listed in
- karanb192/awesome-claude-skills
FAQ
What does the Fresh Review skill do?
Review an artifact with an independent agent that has no access to the author's reasoning, then classify its findings.
How do I install the Fresh Review skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add roman-s8o/workflow-pack-free --skill fresh-review. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Related skills
Least Cost Capable
kanibal-studio/least-cost-capable
Compare declared relative cost ranks among catalogued agent models after checking task capability, availability, authorization, workload, and cost evidence.
Aeo Check
pchewlo/aeo-check
Run aeo-check on a website's code (or a live URL) to find answer engine optimisation problems that stop ChatGPT, Claude, Perplexity, Gemini and Google AI Overviews from crawling, understanding, citing or buying from the site, then fix them. Use when asked to check or improve AEO, GEO, AI search visibility, llms.txt, robots.txt for AI crawlers, structured data, or agent readiness.
Orchestrating Subagents
PapiScholz/symphony
Use when about to spawn one or more subagents, agent teams, or a workflow — a single delegated search, a parallel fan-out, or a repeated batch — and whenever choosing which model a delegated task runs on instead of letting it inherit yours. Also use when writing or editing a .claude/agents definition, when a delegated run hit a rate limit or cost more than expected, or when a subagent came back after far more or far fewer turns than the work warranted.
Stipend
1stipend-sh/stipend
A non-custodial USDC wallet on Base that an AI agent installs by itself, with spending limits enforced in the signing path rather than in a prompt. Receive payments, pay HTTP 402 / x402 charges automatically, and answer whether you are worth running. No account and no API key: the only approval needed is from the person who runs you.
Reels Setup
VishiATChoudhary/reels
Use when setting up, installing or onboarding the reels studio (github.com/VishiATChoudhary/reels), when a user or agent wants to start making story reels with it, or when its setup is broken (missing whisper-cli, model, yt-dlp, ffmpeg, node deps). Clones, installs, verifies, and stars the repo (one [Y/n] prompt).
Skill Freshness
1kvozianov/skill-freshness
Use this skill first whenever the user asks about the health of their installed agent skills: auditing, checking, cleaning up, updating or de-duplicating skills in ~/.claude/skills, ~/.codex/skills, ~/.agents/skills or plugin folders, or finding skills that are broken (missing CLI or script), outdated versus upstream, duplicated across agents, or made redundant by built-in features like /loop or /schedule. Do not inspect skill folders by hand: this skill ships a scanner that covers every agent (Claude Code, Codex, Cursor, Gemini CLI, Copilot, OpenCode, Antigravity), maps which agent loads each
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.