CtrlK
BlogDocsLog inGet started
Tessl Logo

voxtype-install

Guide the user through installing, configuring, and launching voxtype — local on-device voice dictation (speech-to-text that types wherever the cursor is). Use when the user asks to install voxtype, set up voice dictation / voice typing, or asks how to dictate into their editor, terminal, or a coding agent's prompt.

76

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

90%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 efficient, fully executable install guide with a clear three-phase workflow and appropriately deferred detail. Its only weaknesses are minor: no post-install verification step and a slightly duplicated reference link with a small inline config listing that keeps structure just shy of the top anchors.

Suggestions

Add a quick verification step after install (e.g., 'run voxtype --help to confirm it is on PATH') to give the workflow an explicit checkpoint between Install and Configure.

Consolidate the Reference section so the configuration URL appears once, and consider trimming the inline config-key list to the 3–4 most common keys now that a full commented config is available via voxtype init and the linked reference.

DimensionReasoningScore

Conciseness

The body is lean and contains only tool-specific facts Claude cannot know (engine choices, config keys, model download sizes, the three macOS permissions), with no explanation of concepts Claude already knows and no padding. It fits the 'every token earns its place' anchor rather than anchor 4, which expects trimmable over-explanation.

5 / 5

Actionability

Every step is copy-paste ready — 'uv tool install voxtype', the curl one-liner and 'pipx install voxtype' fallbacks, 'voxtype setup', 'voxtype init', 'voxtype', 'voxtype --help', and 'voxtype hotkey'. Common cases (no uv installed, hand-editors, first-run permissions) are all covered, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The Install → Configure → Launch sequence is clearly ordered with useful checkpoints ('all three must be granted, then voxtype restarted'; setup 'must run in the user's own terminal'). It falls short of anchor 5 only because there is no explicit verification step after install (e.g., confirming voxtype runs) before proceeding; it is clearly above anchor 3, whose sequence lacks checkpoints.

4 / 5

Progressive Disclosure

Sections are well-organized and the full configuration detail is deferred to a clearly signaled, one-level-deep reference link ('read the **Configuration & CLI** reference'). It sits between anchors 4 and 5: the ~10-line inline config-key list is reference material that blurs the overview/detail split, and the Reference section repeats the configuration URL, so the well-signaled split of anchor 5 is not fully met.

4 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: it states concrete actions, defines the tool's capability precisely, and provides an explicit, well-phrased 'Use when' clause with natural trigger synonyms. It uses third person and stays concise with no padding or over-claims.

DimensionReasoningScore

Specificity

Names three concrete actions ('installing, configuring, and launching') that comprehensively cover the skill's lifecycle, and precisely defines the capability ('speech-to-text that types wherever the cursor is'). No coverage gaps for this scope, so it fits the anchor-5 example rather than the minor-gaps anchor at 4.

5 / 5

Completeness

Explicitly answers both questions: what ('Guide the user through installing, configuring, and launching voxtype — local on-device voice dictation') and when ('Use when the user asks to install voxtype, set up voice dictation / voice typing...'). This mirrors the anchor-5 example's structure; the anchor-4 case ('when' could be more explicit) does not apply.

5 / 5

Trigger Term Quality

Includes natural phrases users would actually say — 'install voxtype', 'set up voice dictation / voice typing', 'dictate into their editor, terminal, or a coding agent's prompt' — with synonym coverage (dictation, voice typing, dictate). No natural terms are missing, matching the comprehensive-synonyms anchor.

5 / 5

Distinctiveness Conflict Risk

Names a specific tool and a clear niche (on-device voice dictation) with distinct triggers, so it is unlikely to fire for the wrong skill. The anchor-4 'minor overlap risk' case would require broader triggers, which are absent.

5 / 5

Total

20

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pchalasani/claude-code-tools
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.