CtrlK
BlogDocsLog inGet started
Tessl Logo

voice-assigner

角色音色分配原则与音色库

54

Quality

61%

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/voice_assigner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is concise and well-organized with concrete tool-call sequencing, scoring well on conciseness and progressive disclosure. It is held back by missing call-syntax/actionability detail and the absence of a validation checkpoint for the batch assignment workflow.

Suggestions

Add a short example showing the call syntax and arguments for assign_voice (and list_voices output shape) so guidance is copy-paste ready.

Insert a verification step after assignment, e.g. 'Review assignments for duplicate or missing voices and confirm coverage of all characters before summarizing.'

Optionally note how to fall back when no voice matches a character's profile, to complete the actionability gap.

DimensionReasoningScore

Conciseness

The body is lean: compact principle-to-voice mappings ("活泼开朗 → 明亮有活力的音色") and a terse 5-step tool sequence with no padding and no explanation of concepts Claude already knows. This matches the score-3 anchor 'lean and efficient; assumes Claude's competence; every token earns its place'.

3 / 3

Actionability

It names concrete tools (list_voices, get_characters, assign_voice) and gives decision logic, but shows no call syntax, argument formats, or example voice IDs — matching 'some concrete guidance but incomplete; missing key details'. Not score 1 (it instructs rather than describes) and not score 3 (not copy-paste ready with full executable detail).

2 / 3

Workflow Clarity

The 5 steps are clearly sequenced, but this is a batch operation (assigning a voice to every character) with no validation/verification checkpoint (e.g. detecting duplicate/missing assignments); the rubric caps such workflows at 2. Above score 1 (sequence is present) but below score 3 (no explicit validate/feedback step).

2 / 3

Progressive Disclosure

The skill is under 50 lines, single-purpose, and has no external bundle files; per the rubric's simple-skills note, well-organized sections alone warrant a 3. The two clearly-headed sections (分配原则, 使用步骤) organize the content well with no nested references.

3 / 3

Total

10

/

12

Passed

Description

50%

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 identifies a clear domain and a general action but stops there: no concrete action list, no 'Use when...' trigger guidance, and only modest distinctiveness. All dimensions land at the middle anchor, yielding a normalized score of 0.5.

Suggestions

Add a 'Use when...' clause naming natural triggers, e.g. 'Use when generating multi-character voice/TTS content, assigning distinct voices to story or game characters, or building a voice library.'

List concrete actions to lift specificity, e.g. 'Assigns appropriate voices to characters based on gender, age, and personality; maintains a voice library; calls list_voices/get_characters/assign_voice.'

Include common user phrasings (音色, 配音, TTS, 语音合成, 角色配音) so the trigger_term_quality and distinctiveness anchors reach score 3.

DimensionReasoningScore

Specificity

The description names the domain ("角色音色分配") and a general action ("分配"/assign) plus "音色库" (voice library), but lists no concrete operations — matching the score-2 anchor 'names domain and some actions, but not comprehensive'. It is above score 1 because it is not vague ('Helps with documents'), but below score 3 because it does not enumerate multiple specific actions.

2 / 3

Completeness

It answers 'what' (character voice-assignment principles and voice library) but provides no 'when should Claude use it' guidance — per the rubric, a missing 'Use when...' clause caps completeness at 2. Above score 1 because 'what' is stated; below score 3 because 'when' is entirely absent.

2 / 3

Trigger Term Quality

It contains relevant natural keywords a user might say ("角色音色", "音色库", "分配") but no 'Use when...' phrasing or common variations, matching 'some relevant keywords but missing common variations'. Not score 1 because real keywords are present; not score 3 because trigger coverage is thin and no explicit use-when guidance is given.

2 / 3

Distinctiveness Conflict Risk

The niche (assigning voices to character roles) is fairly specific, but without explicit triggers it could still overlap with general TTS/voice skills, matching 'somewhat specific but could still overlap'. Not score 1 (not generic like 'Helps with code and documents') and not score 3 (no distinct explicit triggers).

2 / 3

Total

8

/

12

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

description_field

'description' is very short (12 chars), consider making it more detailed

Warning

Total

15

/

16

Passed

Repository
chatfire-AI/huobao-drama
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.