Is the Assess skill free?

Yes. The skill itself is free from yonatangross/orchestkit. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Assess SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.

How do I install Assess?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Assess with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Assess

Weighted 7-dimension code/design quality scorer with a pass/fail gate — needs the full ork plugin plus memory MCP.

by yonatangross · yonatangross/orchestkit

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.4/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 149a826

Manually applied its rubric.json weights to a deliberately vulnerable SQL-concatenation snippet: the skill's weighted composite (4.61, driven down by a 1/10 security score against a 4.0 min_blocker) correctly failed the code and named the exact injection line as a blocker, versus a baseline review that just said '3/10, use parameterized queries' with no structure. Caught a real doc bug: the frontmatter's dimension list names 'simplicity' as one of the 6 core dimensions, but the live rubric.json and quality-model.md show 7 default-mode dimensions (scalability and compliance instead) — simplicity only appears in comparison mode.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 3/5

What Assess does

Runs a structured, evidence-backed 0-10 quality assessment across 7 weighted dimensions (correctness, maintainability, performance, security, scalability, testability, compliance) with adversarial refutation at high effort and a composite pass/fail verdict gated at 5.5. Triggers on 'rate/evaluate/compare/pros and cons' phrasing for code, designs, or architecture trade-offs, and correctly stays out of the way of fix/implement/build requests. Heavily orchestrated: it loads sibling skills (quality-gates, chain-patterns, shared rules), a PreToolUse hook script, and an optional memory MCP server, so copying just the assess folder alone will not run standalone.

How to install Assess

git clone https://github.com/yonatangross/orchestkit
cd orchestkit
mkdir -p ~/.claude/skills
cp -r plugins/ork/skills/assess ~/.claude/skills/assess

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Assess

/assess Weighted 7-dimension code/design quality scorer with a pass/fail gate — needs the full ork plugin plus memory MCP.

It also activates on plain-language prompts like these:

Rate this architecture proposal across correctness, security, and scalability
Compare these two design approaches and give me pros and cons
Evaluate this code change and tell me if it's good enough to merge

Frequently asked questions

Is the Assess skill free?: Yes. The skill itself is free from yonatangross/orchestkit. SkillProof publishes the install command and an independent test verdict at no cost.
Does Assess work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. Manually applied its rubric.json weights to a deliberately vulnerable SQL-concatenation snippet: the skill's weighted composite (4.61, driven down by a 1/10 security score against a 4.0 min_blocker) correctly failed the code and named the exact injection line as a blocker, versus a baseline review that just said '3/10, use parameterized queries' with no structure. Caught a real doc bug: the frontmatter's dimension list names 'simplicity' as one of the 6 core dimensions, but the live rubric.json and quality-model.md show 7 default-mode dimensions (scalability and compliance instead) — simplicity only appears in comparison mode.
What is the Assess SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 3/5.
How do I install Assess?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Assess with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.