CtrlK
BlogDocsLog inGet started
Tessl Logo

bump-tantivy

Bump tantivy to the latest commit on main branch, fix compilation issues, and open a PR

87

4.71x
Quality

81%

Does it follow best practices?

Impact

99%

4.71x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

The body is a lean, highly executable 10-step workflow with concrete commands, explicit guardrails (branch check, fix-complexity escalation), and a built-in compile-fix feedback loop. The only minor weakness is a couple of steps (commit, push) that describe actions rather than spelling out the commands.

DimensionReasoningScore

Conciseness

The body is almost entirely exact commands and essential parameters with no explanations of concepts Claude already knows; the single trimmable line ('This ensures we're working from the latest code.') does not drop it below the 'lean and efficient' anchor.

5 / 5

Actionability

Steps 1-8 and 10 give copy-paste-ready commands (e.g. `gh api repos/quickwit-oss/tantivy/commits/main --jq '.sha'`, `gh pr create --title ...`), but Step 9 says 'Stage all modified files and create a commit' without explicit `git add`/`git commit` commands and Step 10's 'Push the branch' omits the push command — minor gaps matching anchor 4 rather than fully executable.

4 / 5

Workflow Clarity

Ten clearly sequenced steps with explicit validation: Step 1 aborts if not on main, and Step 5 is a validate-fix-retry feedback loop ('Repeat until cargo check passes') with escalation guidance for complex fixes, matching the top anchor.

5 / 5

Progressive Disclosure

A short (~78 line) single-purpose skill with no bundle files and no content that belongs in separate files; the well-organized step sections satisfy the simple-skill exception for a top progressive-disclosure score.

5 / 5

Total

19

/

20

Passed

Description

70%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.

The description is concrete, distinctive, and action-oriented, clearly conveying what the skill does. Its main weakness is the complete absence of 'when to use' trigger guidance, which caps completeness, and limited synonym coverage for natural trigger phrases.

Suggestions

Append a trigger clause such as 'Use when the user asks to bump, update, or upgrade the tantivy dependency to the latest commit.'

Include common synonyms (update/upgrade tantivy, dependency bump) so natural user phrasings match the description.

Optionally mention the full scope (formatting and license updates are also performed) to close the specificity gap with the body.

DimensionReasoningScore

Specificity

Lists three concrete actions ('Bump tantivy to the latest commit', 'fix compilation issues', 'open a PR') but omits parts of the workflow the body performs (formatting, license updates), matching the 'several specific actions; minor gaps in coverage' anchor rather than comprehensive coverage.

4 / 5

Completeness

The 'what' is clear (bump, fix compilation, open PR) but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines; it sits at the 'clear what, when missing or weakly implied' anchor, not 4 since 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

Includes natural terms a user would say ('bump', 'tantivy', 'PR', 'compilation issues'), but misses common synonyms such as 'update' or 'upgrade tantivy' and 'dependency', fitting 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Names the specific crate 'tantivy' and a highly specific operation (bump to latest main commit), giving it a clear niche with minimal overlap with any other skill.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
quickwit-oss/quickwit
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.