CtrlK
BlogDocsLog inGet started
Tessl Logo

bump-tantivy

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

Install with Tessl CLI

npx tessl i github:quickwit-oss/quickwit --skill bump-tantivy
What are skills?

72

4.71x

Quality

58%

Does it follow best practices?

Impact

99%

4.71x

Average score across 3 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/bump-tantivy/SKILL.md
SKILL.md
Review
Evals

Evaluation results

100%

100%

Automate the Tantivy Dependency Bump

Bump workflow automation script

Criteria
Without context
With context

Branch guard present

0%

100%

Pull before start

0%

100%

Correct SHA API call

0%

100%

Short SHA length

0%

100%

Correct Cargo.toml target

0%

100%

cargo check directory

0%

100%

make fmt directory

0%

100%

License regeneration command

0%

100%

License file move

0%

100%

Branch naming format

0%

100%

Commit message format

0%

100%

PR title and body

0%

100%

Without context: $0.3841 · 1m 40s · 19 turns · 25 in / 5,858 out tokens

With context: $0.2652 · 54s · 18 turns · 274 in / 3,309 out tokens

98%

74%

Review a Tantivy Dependency Bump

Detecting bump workflow violations

Criteria
Without context
With context

Branch state issue

50%

100%

SHA fetch method

0%

100%

Full SHA in Cargo.toml

83%

83%

cargo check directory

0%

100%

Missing make fmt

0%

100%

Missing license regeneration

0%

100%

Missing license file move

0%

100%

Wrong branch name

20%

100%

Wrong commit message

50%

100%

Wrong PR title/body

25%

100%

Without context: $0.2892 · 1m 49s · 10 turns · 49 in / 5,829 out tokens

With context: $0.2679 · 1m 8s · 12 turns · 15 in / 4,067 out tokens

100%

59%

Tantivy Bump Runbook for New Contributors

Error handling policy and workflow runbook

Criteria
Without context
With context

Branch precondition

60%

100%

Pull before changes

100%

100%

Correct SHA fetch command

0%

100%

Short SHA format

0%

100%

License regeneration step

0%

100%

License file move

0%

100%

Autonomous error fix policy

100%

100%

Escalation policy

100%

100%

Iterative cargo check

70%

100%

Branch naming convention

0%

100%

Commit message format

25%

100%

Complete PR command

0%

100%

Without context: $0.1926 · 1m 8s · 10 turns · 63 in / 3,565 out tokens

With context: $0.1954 · 47s · 13 turns · 47 in / 2,782 out tokens

Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.