CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

The risk profile of this skill

The canonical home for this skill is deepread in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

86%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, highly actionable instruction-only skill with a clear multi-mode workflow and clean one-level reference disclosure. Minor tightening of the Anti-Patterns section and an explicit pre-synthesis completeness checkpoint would raise it further.

Suggestions

Add an explicit validation checkpoint before synthesis (e.g. 'verify every major claim in the argument tree has a ledger entry before synthesizing') to make the workflow's quality gates fully explicit.

Consider condensing the Anti-Patterns list, since several items restate guidance already embedded in the workflow and evidence-ledger sections.

DimensionReasoningScore

Conciseness

The body is largely efficient and confined to skill-specific methodology (argument-tree units, evidence ledger, confidence labels, anti-patterns) with no generic padding about what documents are, though a few lists and the Anti-Patterns section could be trimmed slightly.

4 / 5

Actionability

Provides copy-paste-ready, concrete templates: defined atomic units, an evidence-ledger table with required fields, exactly four confidence labels, exactly five relationship types, and a good/bad central-claim example — fully executable guidance for an instruction-only skill.

5 / 5

Workflow Clarity

A clear seven-step sequenced workflow with real checkpoints (extraction gating in step 1, the reasoning-fallacy checklist in step 5, the learning loop in step 7), but a couple of validation checkpoints are implicit rather than explicit (e.g. no explicit 'verify argument tree completeness before synthesis' gate).

4 / 5

Progressive Disclosure

SKILL.md is an overview that offloads the detailed Feynman procedure and knowledge-map structure to one-level-deep, clearly signaled references (references/feynman.md and references/knowledge-map.md, both present as real files), keeping the body navigable.

5 / 5

Total

18

/

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, trigger-rich description that clearly states both capability and activation conditions with concrete natural language. It would benefit from a few extra synonyms (close reading, mind map, .pdf) and an explicit disambiguation against research/summary skills.

Suggestions

Add natural synonyms users say, e.g. 'close reading', 'mind map', and the '.pdf' extension, to widen trigger coverage.

Add a short boundary clause in the description (e.g. 'not for web source discovery or citation briefs') to reduce overlap with deep-research and research-summarizer skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('extract claims and evidence; build a knowledge map; or learn through Feynman explanation and recall') plus five named reading modes, giving comprehensive coverage rather than a single vague verb.

5 / 5

Completeness

Explicitly answers both halves: 'what' via the action list and modes, and 'when' via the concrete 'Use when the user asks to deeply read... extract claims... build a knowledge map... or learn through Feynman explanation' trigger phrasing.

5 / 5

Trigger Term Quality

Good natural-term coverage ('deeply read a book, article, PDF', 'knowledge map', 'Feynman explanation and recall'), but misses common synonyms and extensions a user might say such as 'close reading', 'mind map', and '.pdf'.

4 / 5

Distinctiveness Conflict Risk

The deep-reading / argument-reconstruction / recall niche is distinct and uses specific triggers, but it sits adjacent to research and summarization skills and the description itself does not state boundaries, leaving minor overlap risk.

4 / 5

Total

18

/

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
alirezarezvani/claude-skills
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.