CtrlK
BlogDocsLog inGet started
Tessl Logo

comparison-base

Internal reusable workflow for resolving the correct Git comparison base for branch reviews and change analysis. Finds the PR target or canonical Fluid Framework upstream, selects the newest shared target-history commit, and detects substantial divergence.

60

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/comparison-base/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%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 well-structured, actionable Git workflow with explicit sequencing, validation checkpoints, and error-recovery feedback loops. It is token-efficient and assumes Claude's competence, with only minor trim opportunities and no need for external reference files.

DimensionReasoningScore

Conciseness

The body is dense and procedural with no padding about concepts Claude already knows; a few prose passages around remote push-precedence resolution could be trimmed, but overall efficient.

4 / 5

Actionability

Provides concrete, executable commands (git fetch, gh pr list, git merge-base --all, git rev-list --count) with real flags; minor gaps remain where commands are templated around runtime variables.

4 / 5

Workflow Clarity

A clearly sequenced three-step process with explicit validation checkpoints ('Verify $BASE_COMMIT is non-empty and is an ancestor of both', 'stop as soon as one source produces exactly one validated match') and feedback loops (shallow-repo deepen-and-retry, multi-ancestor and >50-commit divergence prompts).

5 / 5

Progressive Disclosure

No bundle files exist and the single-file workflow is well organized into Inputs, Steps 1–3, Outputs, and Edge Cases; structure is good, though everything is inlined with no external reference split, leaving it just shy of an ideal overview-plus-references layout.

4 / 5

Total

17

/

20

Passed

Description

58%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 specific and distinct, clearly conveying a narrow Git-workflow niche, but it omits an explicit 'Use when...' trigger clause and relies on technical jargon over natural user phrasings, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause stating when another workflow should invoke this skill (e.g., 'Use when a workflow needs to compare a branch against its merge target').

Include a couple of natural trigger phrases or synonyms users might say ('review a branch', 'find the diff base', 'compare against main') alongside the technical terms.

Tighten 'Internal reusable workflow for resolving the correct Git comparison base' to lead with the action rather than framing.

DimensionReasoningScore

Specificity

Names the domain and lists several concrete actions ('Finds the PR target or canonical Fluid Framework upstream, selects the newest shared target-history commit, and detects substantial divergence'); not quite a comprehensive multi-action inventory, so 4 rather than 5.

4 / 5

Completeness

The 'what' is clearly stated, but there is no explicit 'Use when...' trigger clause — only a weak implied 'when' via 'for branch reviews and change analysis', which caps completeness at 3 per the rubric.

3 / 5

Trigger Term Quality

Relevant domain terms ('branch reviews', 'change analysis', 'Git comparison base', 'PR target') are present but lean technical with no synonyms or natural user phrasings beyond the core terms.

3 / 5

Distinctiveness Conflict Risk

The niche is narrow and specific (Git comparison base resolution for Fluid Framework branch reviews), making conflicts unlikely; it is not quite a self-evident standalone trigger, so 4 rather than 5.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
microsoft/FluidFramework
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.