CtrlK
BlogDocsLog inGet started
Tessl Logo

benchmark-testing

Create and launch benchmark test projects to exercise vercel-plugin skill injection across realistic scenarios. Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts.

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/benchmark-testing/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 lean and actionable with concrete commands, a copy-paste template, and a well-organized example table, but the batch-launch workflow lacks any validation or verification checkpoint. Adding a verify step after spawning would raise workflow clarity above the batch-operation cap.

Suggestions

Add a validation checkpoint after launching panes (e.g. confirm each pane opened and the plugin loaded via a quick `wezterm cli list` / settings check) so the batch operation has a feedback loop.

Replace the {01-slug,02-slug,...} placeholder in step 1 with a concrete enumeration or a small loop that generates the slugs, to make the command fully executable.

Consider moving the large example-prompts table into a references file so SKILL.md stays a concise overview with one-level-deep navigation.

DimensionReasoningScore

Conciseness

The body is lean — numbered workflow steps, a tight bullet list of critical details, a copy-paste command template, prompt guidelines, an example table, and cleanup — with no padding or explanation of concepts Claude already knows. It is not a 5 because the opening line restates the frontmatter description, and not a 3 because there is no real over-explanation.

4 / 5

Actionability

It provides concrete executable commands (mkdir brace expansion, npx add-plugin loop, wezterm cli spawn template) and a copy-paste-ready 'Working command template' with an example prompts table. It is not a 5 because the directory creation uses a {01-slug,02-slug,...} placeholder and the template retains a YOUR PROMPT HERE token, and not a 3 because the guidance is genuinely executable rather than pseudocode.

4 / 5

Workflow Clarity

The three steps are clearly sequenced, but this is a batch operation (looping over directories spawning multiple panes) with no validation or verification checkpoint, which caps workflow clarity at 3 per the batch/destructive rule. It is not a 2 because the sequence is coherent, and not a 4+ because a feedback loop (e.g. confirm each pane launched / plugin installed) is missing.

3 / 5

Progressive Disclosure

The single SKILL.md is well-organized into clear sections (Workflow, Prompt Guidelines, Cleanup) with no nested or buried references and no bundle files present. It is not a 5 because it slightly exceeds the under-50-line simple-skill threshold and the inline example table could arguably live in a separate reference, and not a 3 because structure and signaling are solid.

4 / 5

Total

15

/

20

Passed

Description

51%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 clearly states what the skill does with several concrete actions and a distinct niche, but it omits any 'Use when...' trigger guidance and relies on technical jargon rather than natural user phrasings. Adding explicit trigger terms would lift the completeness and trigger-term-quality scores.

Suggestions

Append a 'Use when...' clause with natural trigger phrases, e.g. 'Use when stress-testing or benchmarking vercel-plugin skill injection across realistic scenarios.'

Replace internal jargon ('skill injection across realistic scenarios') with language a user would actually say, such as 'run benchmark tests' or 'spawn multiple Claude Code sessions'.

Briefly mention the cleanup step so the action coverage is more comprehensive.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts' — with only minor coverage gaps (e.g. cleanup is omitted). It is not a 3 because it lists more than 1-2 actions, and not a 5 because coverage is not comprehensive.

4 / 5

Completeness

The 'what' is clear ('Create and launch benchmark test projects... Sets up isolated directories, installs the plugin, and spawns WezTerm panes'), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is concrete, and not a 4 because 'when' is entirely absent rather than weakly present.

3 / 5

Trigger Term Quality

Phrases like 'vercel-plugin skill injection across realistic scenarios' and 'benchmark test projects' are internal/technical jargon rather than natural terms a user would say; common natural variations and synonyms are missing. It is below the 3 anchor because it lacks the everyday phrasings users actually use, and not a 1 because it does name the domain concretely.

2 / 5

Distinctiveness Conflict Risk

The niche is fairly distinct — 'vercel-plugin skill injection', 'WezTerm panes', 'Claude Code' — with minor overlap risk against closely related testing/benchmark skills. It is not a 5 because an explicit distinct trigger phrase is missing, and not a 3 because the WezTerm/vercel-plugin combination is specific enough to avoid broad overlap.

4 / 5

Total

13

/

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
vercel/vercel-plugin
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.