test-coverage

A test-coverage review command that compares what a skill explains with what its tests check. It produces a written gap analysis.

In plain words
What is it for?
It helps review one skill or all skills, save Markdown reports, and prepare gap descriptions for generating follow-up tasks.
Why use it?
It reveals parts of a skill that are described but not tested, so missing checks are easier to find and prioritize.

Command for Claude Code

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 commands/uipath/skills/test-coverage
Clone the repo
git clone --depth 1 https://github.com/UiPath/skills

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 16,078 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 $0.00000 $0.16078
Opus 5 $0.00000 $0.08039
Sonnet 5 $0.00000 $0.03216
Haiku 4.5 $0.00000 $0.01608

Measured 2d ago against content hash 173bc6a70ac5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

test-coverage 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 2d 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.

.claude/commands/test-coverage.md · 797 lines

How it starts

The opening of the file, as written. The whole thing — 797 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UiPath Skills Test Coverage Report

Analyze what a skill teaches vs what its tests verify. Produce a gap analysis with prioritized recommendations.

Input: $ARGUMENTS

  • Skill name or path (e.g., uipath-maestro-flow) — single skill.
  • Empty or all — every skill under skills/.

Output: Markdown report(s) in tests/reports/<skill-name>.md (e.g., tests/reports/uipath-maestro-flow.md), unless the user specifies a different path. Overwrite existing reports at the same path.

Feed-forward contract. This report is the primary input to /generate-task <description>. /generate-task takes a free-form description and infers the target skill from it — write gap titles as self-contained descriptions that name the skill or its CLI surface, so the reader can paste a gap straight into /generate-task (e.g. "Brown-field editing of existing uipath-maestro-flow projects" → /generate-task Brown-field editing of existing uipath-maestro-flow projects).


Phase 1 — Discovery

  1. Resolve target skill(s):
    • Single name → skills/<name>/. If skills/<name>/ does NOT exist but <name> is in the Planned Skills Registry below, treat it as a planned skill (use the planned-skill template in Phase 5). If <name> is in the Cross-Cutting Capability Registry below, treat it as a cross-cutting capability (see that section).
    • Empty/all → union of (a) glob skills/uipath-*/, (b) every entry in the Planned Skills Registry whose folder does not yet exist, and (c) every entry in the Cross-Cutting Capability Registry. Planned-but-missing skills MUST appear in the per-skill report set and roll-up at 0% until they ship; cross-cutting capabilities MUST appear as their own report + roll-up row (flagged cross-cutting, see §4f and §5).
  2. For a normal skill, check for tests/tasks/<skill-name>/. For a cross-cutting capability, there is no dedicated dir — discover its tests by tag (step 3).
  3. Find *.yaml test files. Normal skill: recursively under tests/tasks/<skill-name>/, exclude _shared/. Cross-cutting capability: grep -rl '<tag>' tests/tasks --include='*.yaml' | grep -v _shared across the whole tests/tasks/ tree (its tasks live inside other skills' dirs).
  4. Find check_*.py scripts recursively. Exclude _shared/test_*.py (unit tests for shared helpers).

Read the full file on GitHub · 797 lines

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. 2d ago First seen · 797 lines · 0 tokens per session scan A 173bc6a70ac5

Subscribe to this mod's changes

test-coverage is a command published in the GitHub repository UiPath/skills (150 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 16,078 tokens. 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.