deepread

Use when the user asks to deeply read a book, article, PDF, or document set; extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall. Covers quick, deep, map, Feynman, and whole-book reading modes.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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 well-structured, actionable instruction-only skill with a clear sequenced workflow and validation checkpoints. Its main defect is referencing bundle files (knowledge-map.md, feynman.md) that are not present in the skill bundle, breaking progressive disclosure.

Suggestions

Add the referenced bundle files under references/ (knowledge-map.md and feynman.md), or inline the essential feynman/map guidance so the modes are self-contained.

Tighten the Anti-Patterns section by removing items that restate guidance already given in the Workflow steps.

Add one short worked example of a populated evidence-ledger row to make the deep-mode output template copy-paste ready.

Dimension	Reasoning	Score
Conciseness	Lean and efficient throughout — it assumes Claude's competence, defines only domain-specific units (Claim/Reason/Evidence), and avoids explaining basic concepts; a few sections (anti-patterns) partly restate earlier guidance and could be trimmed.	4 / 5
Actionability	Provides concrete, actionable templates — typed argument-tree units, an evidence-ledger field table, four exact confidence labels, a reasoning checklist, and a default output structure — though the feynman/map modes defer to reference files rather than giving inline executable guidance.	4 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with explicit validation checkpoints ('Confirm that extraction is usable before analyzing', 'state the gap and stop claims that depend on the missing material'), a reasoning checklist, and a close-the-loop feedback step in step 7.	5 / 5
Progressive Disclosure	The body is well-organized with one-level-deep, clearly signaled references ('follow references/knowledge-map.md', 'follow references/feynman.md'), but no references/ bundle directory exists, so those links are broken navigation dead-ends.	3 / 5
	Total	16 / 20 Passed

Description

88%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 description that clearly states capabilities and use-when triggers with concrete, natural language and a well-defined niche. The only gap is slightly limited synonym/extension coverage in its trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deeply read a book, article, PDF, or document set', 'extract claims and evidence', 'build a knowledge map', 'learn through Feynman explanation and recall' — plus five named reading modes, giving comprehensive coverage rather than a single generic action.	5 / 5
Completeness	Explicitly answers both 'what' (extract claims/evidence, build a knowledge map, Feynman learning, five reading modes) and 'when' ('Use when the user asks to deeply read...') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Good natural-keyword coverage ('deeply read', 'book', 'article', 'PDF', 'document set', 'knowledge map', 'Feynman'), but it stops short of the comprehensive synonym/extension coverage (e.g. '.pdf', 'PDFs') that defines the top anchor.	4 / 5
Distinctiveness Conflict Risk	The evidence-first deep-reading niche with distinct triggers (Feynman, knowledge map) is mostly distinct, but the broad 'deeply read a book, article, PDF' phrasing carries minor overlap risk with general summarizer skills.	4 / 5
	Total	18 / 20 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: 3 missing	Warning

	Total	15 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/deepread/SKILL.md
Commit: 19392f7

Reviewed: ~5 hours 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.