CtrlK
BlogDocsLog inGet started
Tessl Logo

evaluate-plugin

Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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.

A concise, actionable skill body centered on a clear `plugin-eval` command surface and a branched workflow. The main weaknesses are missing validation/feedback checkpoints in the workflow and a referenced file that is not present in the bundle.

Suggestions

Add an explicit validation step (e.g., confirm the report JSON parsed successfully before summarizing findings) and an error-recovery loop for failed `plugin-eval` runs.

Provide at least one concrete example value for `<plugin-root>` or note how to locate the plugin root, so commands are copy-paste ready.

Verify the referenced `../../references/chat-first-workflows.md` exists in the bundle, or remove/replace the pointer with inline guidance.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: a compact numbered workflow, a dense command block, and a single reference pointer with no concept over-explanation.

5 / 5

Actionability

Provides concrete, flagged `plugin-eval` commands (start/analyze/compare/report/benchmark), but `<plugin-root>` is an unsubstituted placeholder and the tool's availability is assumed, leaving a minor gap from copy-paste readiness.

4 / 5

Workflow Clarity

A clear 7-step sequence with conditional branches for benchmarking and trend comparison; however, it lacks explicit validation checkpoints or error-recovery feedback loops for the analysis output.

4 / 5

Progressive Disclosure

Good structure with a single well-signaled one-level reference (chat-first-workflows.md), but the referenced file is absent from the bundle and the short body inlines content that is appropriately scoped, leaving minor organization gaps.

4 / 5

Total

17

/

20

Passed

Description

95%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.

A strong, well-targeted description that states a concrete capability and supplies explicit, natural-language trigger phrases covering the main request variants. Minor specificity upside exists in enumerating analysis sub-capabilities.

DimensionReasoningScore

Specificity

Names the domain (local Codex plugin) and several concrete actions (evaluate, audit, benchmark, compare versions) but does not enumerate the full set of analysis capabilities, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (evaluate a Codex plugin in engineer-friendly language) and 'when' (concrete 'Use when...' trigger phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Six natural quoted trigger phrases users would actually say ('evaluate this plugin', 'audit this plugin', 'what should I fix first') give comprehensive coverage including synonyms and report requests.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Codex plugin evaluation) with specific triggers unlikely to fire for unrelated skills, minimizing conflict risk.

5 / 5

Total

19

/

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
openai/plugins
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.