CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

speed

Launch RSVP speed reader for text

Quality

73%

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/speed/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 tight, highly actionable instruction body for a simple single-purpose skill: exact paths, an exact snippet, and an exact launch command with a clear step order. The only weaknesses are small — an ambiguous placeholder-replacement detail, a macOS-only command, and the referenced HTML asset missing from the bundle.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and directive: numbered steps, exact file path, exact command, and no explanations of concepts Claude already knows. The only gloss — "ORP (Optimal Recognition Point)" — is a brief, relevant expansion, matching the 'every token earns its place' anchor rather than the 'minor instances of over-explanation' anchor at 4.

5 / 5

Actionability

Concrete guidance is present: "Read ~/.claude/skills/speed/data/reader.html", an exact <script> replacement snippet, and the command "open ~/.claude/skills/speed/data/reader.html". Minor gaps keep it below fully copy-paste-ready: the replacement snippet confusingly re-includes the placeholder it replaces, the text-escaping/replace mechanism is left implicit, and `open` is macOS-only with no stated fallback.

4 / 5

Workflow Clarity

A clear four-step sequence (get text → prepare content → write and launch → confirm) with fallback logic for the text source, and no destructive or batch operation requiring validation. It sits at anchor 4 rather than 5 because the placeholder-replacement instruction is slightly ambiguous and there is no check that the generated file opened correctly.

4 / 5

Progressive Disclosure

The skill is under 50 lines, well-sectioned (Instructions, Arguments), and correctly keeps all instructional content inline with a single clearly-signaled asset reference. It misses the 5 anchor because the referenced asset (~/.claude/skills/speed/data/reader.html) is not present in the actual bundle, leaving a minor completeness gap in the file structure.

4 / 5

Total

17

/

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 single clear capability but is minimal: no trigger guidance, no natural-language variations, and only one action. It is functional yet leaves Claude without any 'when to use this' signal, which is its biggest structural gap.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to speed read text, read faster, or RSVP-read a passage or the previous response."

Include natural keyword variations and synonyms such as "speed reading", "Spritz", and "read this faster" so the description matches how users actually phrase the request.

Expand the capability statement slightly (e.g. mention it renders in a browser with play/pause controls and adjustable speed) to move from one action to several concrete ones.

DimensionReasoningScore

Specificity

"Launch RSVP speed reader for text" names the domain (speed reading) and one concrete action (launch), matching the '1-2 concrete actions, but not comprehensive' anchor. It is not score 4 because it lists only a single action rather than several specific ones, and not score 2 because a concrete action is explicitly stated.

3 / 5

Completeness

The description clearly answers 'what' (launch an RSVP speed reader) but contains no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It cannot be 4 because the 'when' is entirely absent rather than merely imprecise.

3 / 5

Trigger Term Quality

"RSVP" and "speed reader" are relevant keywords, but common natural variations users would say — "speed reading", "read faster", "Spritz" — are absent, and RSVP itself is technical jargon. This fits the 'some relevant keywords but missing common variations or synonyms' anchor rather than the good-coverage anchor at 4.

3 / 5

Distinctiveness Conflict Risk

Speed reading is a clear niche with minimal overlap risk against typical skills, so it is mostly distinct. It falls short of the 5 anchor because no distinct trigger phrases are given and "for text" is generic padding rather than a differentiator.

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/speed/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.