test-corpus

The test_documents submodule is a bucket-fetched fixture corpus that is not committed. This skill covers read_test_fixture, missing fixtures, valid A/B controls, and submodule push order. Load before running Rust tests on a fresh clone, setting up an A/B control, adding a fixture-backed test, or diagnosing missing-fixture failures.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable body that leads with concrete commands and embeds real validation and ordering guidance for risky corpus operations. It lands a solid 4 across all dimensions rather than 5 due to minor trims available, placeholder/fragment examples, and prose-form rather than explicit retry-loop workflows.

Suggestions

Convert the corpus-push sequence into an explicit numbered validate->fix->retry checklist (dry-run, publish, verify, re-verify on failure) to lift workflow_clarity to 5.

Replace the <ref>/<main-tree> placeholders in the worktree block with a concrete example ref and path so the snippet is copy-paste ready, improving actionability.

Tighten the "Two more worktree traps" and clippy-breakage asides to the essential rule plus a one-line rationale to reclaim token budget.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what a submodule or GCS bucket is — but narrative passages like the "Two more worktree traps" paragraph and the clippy-breakage aside could be trimmed slightly.	4 / 5
Actionability	Concrete, executable commands are given throughout (fetch_corpus.py, the worktree+symlink setup, publish_corpus.py with --dry-run, verify_corpus.py) plus the Rust helper, but placeholders like <ref> and <main-tree> and a fragment-style Rust snippet leave minor gaps.	4 / 5
Workflow Clarity	The corpus-push flow is clearly sequenced with explicit validation checkpoints (dry-run preview, verify_corpus.py, git branch -r --contains) and ordering rules, but it is prose-driven rather than an explicit validate->fix->retry loop.	4 / 5
Progressive Disclosure	A single self-contained file organized into clear, well-signaled sections with no nested or buried references; at ~85 lines (above the 50-line simple-skill threshold) it stays just short of the top anchor that expects well-split one-level references.	4 / 5
	Total	16 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill covers and when to load it, with natural trigger phrases and minimal conflict risk. It is held below a perfect specificity score only because a couple of listed items read as topic areas rather than crisp actions.

Dimension	Reasoning	Score
Specificity	Names the domain ("bucket-fetched fixture corpus") and lists several concrete actions — "read_test_fixture, missing fixtures, valid A/B controls, and submodule push order" — but a couple read as topic areas rather than crisp verbs, leaving minor coverage gaps.	4 / 5
Completeness	Explicitly answers both what ("This skill covers read_test_fixture, missing fixtures, valid A/B controls, and submodule push order") and when ("Load before running Rust tests on a fresh clone, setting up an A/B control, adding a fixture-backed test, or diagnosing missing-fixture failures") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ("running Rust tests on a fresh clone", "A/B control", "fixture-backed test", "missing-fixture failures"), with only a few common synonyms missing.	4 / 5
Distinctiveness Conflict Risk	A clearly distinct niche (bucket-fetched, non-committed submodule fixture corpus for Rust tests) with specific triggers that would not collide with general test or fixture skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: xberg-io/xberg
Path: .ai-rulez/skills/test-corpus/SKILL.md
Commit: 04336bd

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.