CtrlK
BlogDocsLog inGet started
Tessl Logo

simple-pr

Create a simple PR from staged changes with an auto-generated commit message

82

1.67x
Quality

72%

Does it follow best practices?

Impact

99%

1.67x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/simple-pr/SKILL.md

The canonical home for this skill is simple-pr in quickwit-oss/quickwit

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a tight, actionable seven-step workflow with concrete commands and meaningful validation checkpoints, well-structured for a simple skill. The main gaps are a missing commit-message template/example, a small step cross-reference error, and no error-recovery guidance for the network operations.

Suggestions

Add a concrete commit-message template or worked example in Step 4 so the generated message is copy-paste ready rather than described abstractly.

Fix the Step 6 cross-reference ("message from step 3") to point to Step 4 where the message is actually generated.

Add a brief error-recovery note for push/PR failures (e.g., rebase on origin/main and retry) to introduce a feedback loop into the network steps.

DimensionReasoningScore

Conciseness

The body is lean and step-structured with concrete commands, but includes minor over-explanation Claude already knows (e.g., "This ensures we're working from the latest code.").

4 / 5

Actionability

Every step ships an executable command (git status, git diff --cached, gh pr create, etc.), with only minor gaps: no concrete commit-message template and a cross-reference ("message from step 3") that should read step 4.

4 / 5

Workflow Clarity

The seven steps are clearly sequenced with real abort/confirmation checkpoints (Step 1 staged+branch checks, Step 4 user confirmation), but there is no error-recovery feedback loop for push or PR-creation failures.

4 / 5

Progressive Disclosure

At under 50 lines, single-purpose, and with no need for external references, the well-organized numbered-section structure meets the simple-skill exception for a top score.

5 / 5

Total

17

/

20

Passed

Description

66%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 and specific about what the skill does, with natural trigger terms, but it omits any explicit "when to use it" guidance, which caps completeness and slightly raises conflict risk. Adding a "Use when..." clause would lift the two weaker dimensions.

Suggestions

Append a trigger clause such as "Use when the user wants to open a PR from already-staged changes" to satisfy the "when" half of completeness.

Add the "pull request" synonym so trigger-term coverage includes the long form users often say.

Tighten distinctiveness by naming the precondition (e.g., "when changes are already staged and the user is on main") to reduce overlap with broader git-workflow skills.

DimensionReasoningScore

Specificity

Names concrete actions — "Create a simple PR from staged changes" and "auto-generated commit message" — with a specific source constraint rather than generic phrasing, sitting above the anchor-3 "1-2 concrete actions" baseline but short of comprehensive multi-action coverage.

4 / 5

Completeness

The "what" is clear (create a PR from staged changes with an auto-generated commit message), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Includes natural terms a user would say — "PR", "staged changes", "commit message" — but omits common synonyms like "pull request", so coverage is good rather than comprehensive.

4 / 5

Distinctiveness Conflict Risk

The "staged changes" + "auto-generated commit message" scope carves a distinct niche with only minor overlap risk against other git/PR skills, though the absent trigger guidance leaves some ambiguity.

4 / 5

Total

15

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
quickwit-oss/tantivy
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.