bump-tantivy
Bump tantivy to the latest commit on main branch, fix compilation issues, and open a PR
72
Quality
58%
Does it follow best practices?
Impact
99%
4.71xAverage score across 3 eval scenarios
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/bump-tantivy/SKILL.mdDiscovery
17%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 reads like a one-time task instruction rather than a reusable skill description. It lacks trigger guidance for when Claude should use it, contains no natural user keywords, and describes a very narrow workflow specific to the tantivy library rather than generalizable capabilities.
Suggestions
Add a 'Use when...' clause specifying triggers like 'when updating tantivy dependency', 'when user mentions tantivy version upgrade', or 'when dealing with tantivy compilation errors'
Generalize the description to cover the skill's broader purpose - is this for dependency updates, Rust library maintenance, or specifically tantivy workflows?
Include natural keywords users might say such as 'update dependency', 'upgrade tantivy', 'tantivy version', 'rust search library'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names specific actions (bump tantivy, fix compilation issues, open a PR) and a specific library, but the actions are narrow and task-specific rather than describing reusable capabilities. | 2 / 3 |
Completeness | Only describes what (bump tantivy, fix issues, open PR) with no 'Use when...' clause or any guidance on when Claude should select this skill. Missing the 'when' component entirely. | 1 / 3 |
Trigger Term Quality | Contains technical terms like 'tantivy' and 'compilation issues' but lacks natural keywords users would say. Most users wouldn't know to ask for 'bump tantivy' - this reads like a one-off task description rather than skill triggers. | 1 / 3 |
Distinctiveness Conflict Risk | The specific mention of 'tantivy' library provides some distinctiveness, but 'fix compilation issues' and 'open a PR' are generic actions that could overlap with many development-related skills. | 2 / 3 |
Total | 6 / 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 skill that provides a complete, actionable workflow for bumping the tantivy dependency. It's concise, has clear validation steps with a feedback loop for compilation errors, and includes appropriate decision points for user interaction. The commands are specific and copy-paste ready.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient, providing only necessary information for each step without explaining concepts Claude already knows (git, cargo, makefiles). Every section serves a clear purpose. | 3 / 3 |
Actionability | Provides specific, executable commands for each step (gh api, cargo check, make fmt, git commands). The toml example shows exactly what to look for and modify. | 3 / 3 |
Workflow Clarity | Clear 10-step sequence with explicit validation checkpoint (Step 5's cargo check loop with fix-and-retry feedback). Includes decision points for when to ask user vs proceed autonomously. | 3 / 3 |
Progressive Disclosure | For a single-purpose workflow skill of this length (~60 lines), the flat structure with numbered steps is appropriate. No external references needed; content is well-organized with clear section headers. | 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 | |
- Reviewed
Table of Contents
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.