CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

claude-speed-reader

-Speed read Claude's responses at 600+ WPM using RSVP with Spritz-style ORP highlighting

Quality

45%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/claude-speed-reader/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

11%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 body is an empty template: the description is restated three times, no instructions, steps, or commands are provided, and all actual content is delegated to an external GitHub repository. As written, the skill gives Claude nothing actionable to execute.

Suggestions

Replace the boilerplate Instructions section with actual operating guidance: how to invoke the speed reader (exact commands or code) and how to configure WPM/ORP settings.

Delete the triple repetition of the description across Overview / When to Use / Instructions and the leftover '-' template artifacts; each section should carry distinct, real content.

Move the essential instructions from the external source repository into local bundle files (e.g. references/ or scripts/) and reference them one level deep, so the skill is self-contained.

DimensionReasoningScore

Conciseness

The body repeats the same description three times ("-Speed read Claude's responses at 600+ WPM...", "Use this skill when you need to work with -speed read claude's responses...", "This skill provides guidance and patterns for -speed read claude's responses...") — every sentence is templated padding that adds no information. It is heavily padded but not long-winded concept explanation, fitting the 'several unnecessary padded sections' anchor of 2 rather than the severe verbosity anchor of 1.

2 / 5

Actionability

There is no code, command, or concrete step anywhere; the Instructions section only says "This skill provides guidance and patterns for..." and defers to an external URL. This is the anchor-1 case: it only describes rather than instructs, leaving the reader with nothing executable. The leftover '-' template artifacts further signal auto-generated filler.

1 / 5

Workflow Clarity

No sequence of steps exists — how to launch the RSVP reader, set WPM, or produce the highlighted output is never stated. The simple-skill exception cannot apply because even the single action is ambiguous, matching the 'steps missing or incoherent' anchor of 1.

1 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist, and the only substantive pointer is the external "[source repository](https://github.com/SeanZoR/claude-speed-reader)" link — the real instructions live entirely outside the skill. The section headers are empty shells with the description pasted into them, fitting 'minimal structure... or references are buried' at 2; it is not a 3 because nothing is organized for discovery within the skill itself.

2 / 5

Total

6

/

20

Passed

Description

53%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 states a clear, fairly distinct 'what' with concrete technique keywords, but it completely lacks any 'when to use' trigger guidance and misses natural synonym coverage. It is serviceable but templated and one-dimensional.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when the user wants to read responses faster, skim long output, or mentions speed reading, RSVP, or Spritz.'

Expand the action coverage beyond one capability: what the skill actually does (displays words one at a time at a configurable WPM with ORP highlighting) and any options it exposes.

Include natural synonyms users would say ("read faster", "rapid reading", "speed reading") alongside the technical terms RSVP/ORP/WPM.

DimensionReasoningScore

Specificity

"Speed read Claude's responses at 600+ WPM" names the domain plus 1-2 concrete mechanisms ("RSVP with Spritz-style ORP highlighting"), matching the anchor for a clear but non-comprehensive action list. It does not list several specific actions (no mention of what is displayed, controls, or output format), so it is not a 4; it goes beyond a bare domain name like "Processes PDF files", so it is not a 2.

3 / 5

Completeness

The 'what' is reasonably clear (RSVP speed reading with ORP highlighting at 600+ WPM), but there is no 'Use when...' clause or equivalent trigger guidance — the rubric explicitly caps completeness at 3 in that case. A 4 would require both what and when with at least an implicit 'when', which is entirely absent here.

3 / 5

Trigger Term Quality

It contains some relevant keywords users might say ("speed read", "Claude's responses", "600+ WPM") but misses common variations and synonyms such as "read faster", "rapid reading", or a spelled-out form of RSVP/Spritz. Coverage is partial rather than the good-but-gapped coverage of a 4, yet clearly more than the one-or-two generic keywords of a 2.

3 / 5

Distinctiveness Conflict Risk

"Speed read Claude's responses" with "Spritz-style ORP highlighting" carves a clear niche (response speed-reading) that is unlikely to trigger for the wrong skill. It falls short of a 5 because it offers no explicit trigger phrases and could mildly overlap with generic reading/display or terminal-utility skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

skills/claude-speed-reader/SKILL.md

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.