skill-review

skill-review is a cursor rule for Cursor from UiPath/skills. It costs 34 tokens per session (438 once invoked), scanned A, original, MIT.

A strict review framework for evaluating coding-agent skills. It scores structure, consistency, completeness, duplication, and how clearly the instructions guide an agent.

In plain words
What is it for?
Use it to audit, grade, compare, or review a skill or a change that substantially modifies one. It helps assess metadata, file organisation, command conventions, error handling, and agent usability.
Why use it?
It gives reviewers a common way to find missing instructions, conflicting conventions, copied content, and workflows that do not cover the full task. This makes skill reviews more repeatable.

Cursor rule for Cursor

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/uipath/skills/skill-review
Clone the repo
git clone --depth 1 https://github.com/UiPath/skills

Made for: Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-review

README.md
[![agentmods](https://agentmods.dev/badge/rules/uipath/skills/skill-review.svg)](https://agentmods.dev/rules/uipath/skills/skill-review)
Your own site
<a href="https://agentmods.dev/rules/uipath/skills/skill-review"><img src="https://agentmods.dev/badge/rules/uipath/skills/skill-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00438
Opus 5 $0.00017 $0.00219
Sonnet 5 $0.00007 $0.00088
Haiku 4.5 $0.00003 $0.00044

Measured 4d ago against content hash e990961cafc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/rules/skill-review.mdc · 15 lines

What it actually says

Score each skill on six dimensions (1–5 scale, 1 = failing, 3 = acceptable, 5 = excellent):

  1. Structure — SKILL.md frontmatter valid; name matches folder; description under 1024 chars, front-loads identity, includes redirects; [PREVIEW] tag for unstable skills; body follows Title → When to Use → Critical Rules → Workflow → Reference Navigation → Anti-patterns; references use kebab-case + -guide.md / -template.md suffix; no orphaned files.
  2. Consistency — CLI uses --output json uniformly; <UPPER_SNAKE_CASE> placeholders; heading hierarchy doesn't skip; code blocks have language identifiers; terminology matches other skills.
  3. Logic & Completeness — workflows cover full lifecycle; error handling specified; edge cases addressed; CLI commands correct; steps in order; validation loops present; anti-patterns section covers real mistakes.
  4. Duplication — no copy-paste between SKILL.md and references; no redundant reference files; SKILL.md links to references instead of inlining; no instructions repeated verbatim in Critical Rules and workflow.
  5. LLM Usability — prescriptive not descriptive; numbered Critical Rules; explicit decision trees; copy-paste-ready CLI commands; clear stop conditions; information front-loaded; SKILL.md not excessively long (extract to references/).
  6. Marketplace & Integrationdescription detailed enough to match correctly but not over-broad; redirects for sibling skills; passes hooks/validate-skill-descriptions.sh; no hardcoded personal paths; CODEOWNERS entry exists.

Read everything — SKILL.md, every references/ file, every assets/ file. Cite file paths and line numbers. Provide exact, actionable fixes. Full rubric: .claude/rules/skill-review.md.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 15 lines · 34 tokens per session scan A e990961cafc9

Subscribe to this mod's changes

skill-review is a cursor rule published in the GitHub repository UiPath/skills (154 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 438 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.