skill-name

Clear description of what this skill does and when to use it. Include trigger keywords and contexts inline, e.g. "Use when user wants to X, Y, or Z."

1.53x

Quality

—

Does it follow best practices?

Impact

98%

1.53x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

22%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The SKILL.md body is an unfilled template: organized into sections but populated entirely with placeholders instead of real commands, examples, workflows, or working references. Actionability and workflow clarity are at the floor, while conciseness and progressive disclosure are middling because the structural skeleton is reasonable but hollow.

Suggestions

Fill in the placeholder script descriptions, commands, and example outputs with real, executable content (e.g. actual script names and their invocations).

Replace 'Step 1 / Step 2' troubleshooting placeholders with concrete symptoms and solutions, and add validation checkpoints for any destructive or batch operations.

Point the References and Examples sections at real files in references/, scripts/, and assets/, or remove those sections if no bundle files exist.

Dimension	Reasoning	Score
Conciseness	The body avoids concept-explanation padding, but it is largely template scaffolding with placeholder sections ('Expected output here', 'Description of the problem', 'Important note 1') that earn no place, fitting the 'mostly efficient but could be tightened' anchor rather than the fully lean level 3.	2 / 3
Actionability	No executable guidance exists: commands reference non-existent scripts ('python3 scripts/script.py'), outputs are 'Expected output here', and script descriptions are 'Description of what this script does', matching the 'vague or abstract; no concrete code/commands; describes rather than instructs' anchor.	1 / 3
Workflow Clarity	There is no real multi-step sequence — troubleshooting and usage steps are placeholders ('Step 1', 'Step 2', 'Description of the problem'), and no validation or verification checkpoints are present, matching the 'steps unclear or missing; no validation mentioned' anchor.	1 / 3
Progressive Disclosure	Sections are reasonably organized and clearly labeled, but referenced paths ('examples/' directory, example.com links) do not point to real bundle files (none exist in references/, scripts/, or assets/), fitting the 'some structure but references not clearly signaled / could be better organized' anchor.	2 / 3
	Total	6 / 12 Passed

Description

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an unfilled template description rather than a real skill description: it instructs the author on what to write instead of stating capabilities and triggers. Every dimension scores at the floor because no concrete, distinguishable, or trigger-bearing content is present.

Suggestions

Replace the template text with the actual capabilities of the skill, listing concrete actions (e.g. 'Extract text and tables from PDF files, fill forms, merge documents').

Add a real 'Use when...' clause with natural trigger terms users would say (e.g. 'Use when working with PDFs, forms, or document extraction').

Use third person and pick a specific domain so the description is distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	The description names no concrete actions; it is meta-instructional placeholder text ('Clear description of what this skill does and when to use it. Include trigger keywords and contexts inline') rather than describing any capability, matching the 'vague or no actions' anchor.	1 / 3
Completeness	Both 'what' and 'when' are absent as real content; the description is a template telling the author what to write ('Include trigger keywords... e.g. Use when user wants to X, Y, or Z') rather than answering either question, so it misses both what AND when.	1 / 3
Trigger Term Quality	No natural user keywords appear — only the literal phrase 'trigger keywords' and 'X, Y, or Z' placeholders, so no terms a user would actually say are present.	1 / 3
Distinctiveness Conflict Risk	The text is maximally generic ('what this skill does and when to use it') with no domain signals, so it would conflict with virtually every other skill.	1 / 3
	Total	4 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 6 missing	Warning

	Total	15 / 16 Passed

Repository: resciencelab/opc-skills
Commit: 282acb4

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.