explore-references

Research how a feature works in reference libraries

Quality

55%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.opencode/skills/explore-references/SKILL.md

Quality

Content

61%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-organized, lean research workflow with a concrete output template, but its search and analysis steps stay high-level without executable search guidance or validation checkpoints. It is solid as an instruction-only skill yet would land higher with more concrete search methods.

Suggestions

Add concrete search guidance, e.g. example grep/ripgrep patterns or specific entry-point files to inspect in each reference library.

Insert a validation checkpoint such as 'Re-open cited file paths to confirm line numbers and behavior before writing the summary'.

Tighten the 'Guidelines' bullets and drop the redundant 'Begin' section, since they restate steps already covered.

Dimension	Reasoning	Score
Conciseness	The body is lean and does not explain concepts Claude already knows (no PDF/library primers); only the generic 'Guidelines' bullets and a redundant 'Begin' section could be trimmed, fitting the 'efficient; minor instances that could be trimmed' anchor.	4 / 5
Actionability	It provides concrete paths (the three checkout directories) and a copy-paste output template, but the search and analysis steps are abstract ('search for relevant code', 'analyze the differences') with no concrete search commands or heuristics, matching the 'some concrete guidance but incomplete' anchor.	3 / 5
Workflow Clarity	The three-step Search/Compare/Extract sequence is clearly ordered, but there are no validation checkpoints (e.g. verifying findings against source), matching the 'steps listed but validation gaps' anchor; no destructive/batch cap applies since this is read-only research.	3 / 5
Progressive Disclosure	With no bundle files present, the single-file body is well-organized into clearly headed sections with no nested references; it is over 50 lines so it does not qualify for the simple-skill 5, fitting the 'good structure; minor organization gaps' anchor.	4 / 5
	Total	14 / 20 Passed

Description

48%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 clear and distinct but generic in its action and missing an explicit 'Use when...' trigger clause, which caps completeness and trigger-term quality. It conveys the niche well yet would benefit from concrete actions and natural trigger phrases.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases, e.g. 'Use when implementing a PDF feature and you need to study how pdf.js, pdf-lib, or PDFBox approach it'.

Replace the generic verb 'Research' with concrete actions like 'Compare how reference libraries implement a feature and extract patterns to apply'.

Include natural synonyms/file cues users would actually say (e.g. 'pdf.js', 'pdf-lib', 'PDFBox', 'reference implementations').

Dimension	Reasoning	Score
Specificity	The phrase 'Research how a feature works in reference libraries' names the domain but relies on a single generic action ('research'), matching the anchor for naming a domain with minimal/generic actions rather than the 1-2 concrete actions required for a 3.	2 / 5
Completeness	It states a clear 'what' (research how a feature works) but has no 'Use when...' trigger clause, so per the judging guideline completeness is capped at 3 with the 'when' only weakly implied.	3 / 5
Trigger Term Quality	'research', 'reference libraries', and 'feature' are relevant keywords a user might say, but common synonyms and natural variations are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The 'reference libraries' niche is mostly distinct with only minor overlap risk against general research or code-exploration skills, matching the 'mostly distinct; minor overlap' anchor.	4 / 5
	Total	12 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: LibPDF-js/core
Path: .opencode/skills/explore-references/SKILL.md
Commit: 0fa22e0

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.