CtrlK
BlogDocsLog inGet started
Tessl Logo

rehabilitation-analyzer

分析康复训练数据、识别康复模式、评估康复进展,并提供个性化康复建议

53

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/rehabilitation-analyzer/SKILL.md

The canonical home for this skill is rehabilitation-analyzer in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is a thorough, well-structured instruction skill with concrete formulas, thresholds, and a clear multi-step workflow plus error handling. Its main weaknesses are verbosity from redundant full-output examples and the absence of any progressive disclosure into separate reference files.

Suggestions

Move the full report templates and the three worked-output examples into a references/ file (e.g. references/report-templates.md) and keep only a compact example inline in SKILL.md.

Collapse the two overlapping 使用示例/场景 sections into a single concise set of representative triggers and outputs.

Add inline validation checkpoints within the analysis steps (e.g. after step 2, confirm sufficient data points before continuing) rather than relying solely on the separate 错误处理 section.

DimensionReasoningScore

Conciseness

The body is mostly relevant domain content but is padded with three full worked-output examples ('示例1/2/3'), two complete report templates, and a redundant scenario list; not a 2 because section structure and algorithmic detail are genuinely useful rather than concept re-explanation.

3 / 5

Actionability

Concrete executable guidance appears via formulas ('依从性 = 实际训练次数 / 计划训练次数 × 100%', '7日移动平均疼痛 = sum(近7天疼痛) / 7'), explicit thresholds (优秀≥90%, 改善≥20%), file paths, and field names; not a 5 because formulas are textual/pseudocode rather than copy-paste runnable code.

4 / 5

Workflow Clarity

A clear seven-step sequence (第1步…第7步) with validation in step 1 ('检查文件是否存在', '验证数据结构完整性') and a dedicated 错误处理 section with recovery suggestions; not a 5 because validation feedback loops live in a separate section rather than inline per-step.

4 / 5

Progressive Disclosure

Good section headers exist but all content (full report templates, algorithm details, worked examples) is inlined in one ~600-line file with no reference files; the simple-skill exception does not apply given the size, and no bundle files exist to offload detail.

3 / 5

Total

14

/

20

Passed

Description

58%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 clearly states what the skill does with several concrete actions and a distinct rehabilitation niche, but omits any 'Use when' trigger guidance and lacks natural user-facing keyword variations. It is functional but would benefit from explicit trigger phrases.

Suggestions

Add a 'Use when...' clause naming natural triggers (e.g. 'Use when the user asks about 康复进展, 康复分析, 训练依从性, or wants a rehab progress report').

Include common synonyms and phrasings users would actually say (e.g. '康复训练分析', '功能改善', '疼痛趋势') to improve trigger-term coverage.

Make actions slightly more concrete (e.g. '计算ROM改善速率', '评估训练依从性') to approach comprehensive specificity.

DimensionReasoningScore

Specificity

Quotes the domain ('康复训练数据') and lists four concrete actions ('分析...识别康复模式...评估康复进展...提供个性化康复建议'); not a 5 because the actions are fairly high-level verbs rather than the granular operations seen in the anchor 5 example.

4 / 5

Completeness

A clear 'what' is present but no 'when'/'Use when' trigger guidance exists, so per the judging guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Relevant domain terms appear ('康复训练', '康复进展', '康复模式') but common natural phrasings users would say and synonyms are missing, and there are no file extensions; not a 4 because keyword coverage is incomplete.

3 / 5

Distinctiveness Conflict Risk

The rehabilitation niche is mostly distinct with only minor overlap risk against closely related health skills; not a 5 because no explicit distinct triggers are provided.

4 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (639 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-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.