Bump tantivy to the latest commit on main branch, fix compilation issues, and open a PR
83
75%
Does it follow best practices?
Impact
99%
4.71xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/bump-tantivy/SKILL.mdQuality
Discovery
50%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is highly specific to a single task involving the tantivy library, which makes it distinctive but also very narrow. It clearly states what actions are performed but completely lacks any 'Use when...' guidance, which is a significant gap for skill selection. The description reads more like a task instruction than a reusable skill description.
Suggestions
Add a 'Use when...' clause such as 'Use when the user asks to update or bump the tantivy dependency, or when tantivy needs to be upgraded to the latest version.'
Include natural trigger term variations like 'update tantivy', 'upgrade tantivy dependency', 'sync tantivy with upstream' to improve matching.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: bump tantivy to latest commit on main, fix compilation issues, and open a PR. These are clear, actionable steps. | 3 / 3 |
Completeness | Describes what it does (bump tantivy, fix compilation, open PR) but has no 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'when' is entirely absent, making this a 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'tantivy', 'bump', 'compilation', and 'PR', but these are quite narrow. A user might say 'update tantivy' or 'upgrade dependency' which aren't covered. Missing common variations like 'update', 'upgrade', 'dependency'. | 2 / 3 |
Distinctiveness Conflict Risk | Extremely specific to a single library (tantivy) and a particular workflow (bumping to latest main commit). Very unlikely to conflict with other skills due to the narrow, named-dependency scope. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent procedural skill that provides a clear, complete workflow for bumping a dependency. It is concise, fully actionable with specific commands, includes appropriate validation loops (cargo check retry) and guard rails (branch check, user consultation for complex fixes). The structure is clean and easy to follow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. Every step provides only the necessary command or instruction without explaining what git, cargo, or PRs are. No unnecessary padding or concept explanations. | 3 / 3 |
Actionability | Each step provides specific, executable commands (gh api, cargo check, make fmt, gh pr create) with concrete examples like the Cargo.toml line format and branch naming convention. Copy-paste ready throughout. | 3 / 3 |
Workflow Clarity | The 10-step sequence is clearly ordered with logical dependencies. Step 5 includes an explicit feedback loop (repeat cargo check until it passes) with decision criteria for when to fix autonomously vs. ask the user. Step 1 includes an abort condition. The workflow covers validation at multiple points. | 3 / 3 |
Progressive Disclosure | For a single-purpose procedural skill under 100 lines, the content is well-organized with clear numbered steps and descriptive headers. No external references are needed, and the structure is easy to scan and follow. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
cfb53e9
Table of Contents
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.