Poor
0 critical
20 warnings
7 suggestions
82 passed
Domain scores
Anti-Slop
100
Accessibility
100
Enterprise
100
Issues
Warnings (20)
14.1-no-success-criterialine 1
No concrete success criteria found for eval readiness
Fix: Add pass/fail criteria or measurable outcomes (e.g., 'must return valid JSON', 'output < 100 lines')
19.5-pipeline-no-stagesline 6
Pipeline pattern detected but no stage documentation found
Fix: Document the pipeline stages, checkpoints, and data flow between stages
4.5-desc-no-triggersline 2
Description lacks triggering conditions
Fix: Add phrases like 'Use when...', 'Triggers on...', or 'Applies to...' to help Claude select this skill
1.2-desc-whatline 3
Description missing WHAT clause (action verb) - recommended by agentskills spec
Fix: Consider starting with what the skill does, e.g., 'Creates...', 'Generates...', 'Validates...'
1.2-desc-whenline 3
Description missing WHEN clause - recommended by agentskills spec
Fix: Consider adding 'Use when...' or 'Activate when...' to description
7.3-mcp-no-versionline 1
MCP skill without protocol version specification
Fix: Specify protocol version (e.g., 2024-11-05)
7.6-no-negative-casesline 1
Skill lacks negative case coverage (no error handling, limitations, or edge cases documented)
Fix: Add a '## Limitations' or '## Error Handling' section describing when the skill won't work or how it handles failures
12.3-workflow-vague-stepline 114
Step is too brief to be actionable: "仍失败再按部署方式重启进程"
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 124
Step is too brief to be actionable: "针对特定渠道："
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 144
Step is too brief to be actionable: "检查依赖项："
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 155
Step is too brief to be actionable: "检查配置："
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 159
Step is too brief to be actionable: "检查必填字段："
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 163
Step is too brief to be actionable: "使用自动连接 skill："
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 168
Step is too brief to be actionable: "检查机器人是否发布（重要..."
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 193
Step is too brief to be actionable: "**诊断**：执行过的命令与关..."
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 194
Step is too brief to be actionable: "**处理**：已执行恢复动作"
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 195
Step is too brief to be actionable: "**结果**：当前状态是否恢复"
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 196
Step is too brief to be actionable: "**建议**：后续预防或观察项"
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 203
Step is too brief to be actionable: "**批量操作**：暂不支持批量..."
Fix: Add specific details: what, where, and how
12.3-workflow-vague-stepline 230
Step is too brief to be actionable: "检查依赖项：`pip list`"
Fix: Add specific details: what, where, and how
Suggestions (7)
17.1-no-input-contractline 6
No input contract found; unclear what data the skill expects
Fix: Document what the skill expects as input (format, required fields, constraints)
17.2-no-output-contractline 6
No output contract found; unclear what the skill produces
Fix: Document what the skill produces (format, structure, side effects)
14.2-no-examplesline 1
No input/output examples found
Fix: Add example input/output pairs or <example> blocks to make the skill testable
3.4-gerund-namingline 2
Skill name could use gerund form for clarity
Fix: Consider gerund-style names like 'processing-pdfs' or 'analyzing-logs' (per best practices)
18.1-no-confidence-signalline 1
No confidence signal found for orchestrator decision-making
Fix: Add confidence indicators (e.g., confidence: high/medium/low) so orchestrators can route or retry
18.3-no-structured-outputline 1
No structured output format defined for machine consumption
Fix: Define a structured output format (JSON, YAML, or table) so downstream tools can parse results
7.3-mcp-no-transportline 1
MCP skill without transport type specification
Fix: Specify transport type (stdio, sse, or websocket)
OWASP Agentic (Cat 26)
Agent surface detected — performs consequential actions
2 warning
-
26.09-ASI09-destructive-no-gate
warning
destructive op "delete" has no confirmation/approval gate within +/-10 lines
line 48
Fix: add an explicit human-approval gate (STOP:, AskUserQuestion, confirm) before the destructive op
-
26.10-ASI10-safeguard-disable
warning
safeguard-disabling instruction "--force" with no explicit user-approval note
line 15
Fix: require explicit user approval before disabling a safeguard, or remove the bypass
ASI-01: skippedASI-02: skippedASI-03: skippedASI-04: skippedASI-05: skippedASI-06: skippedASI-07: skippedASI-08: skippedASI-09: failASI-10: failASI-11: skipped
Badges
skillcheck
✕ passed
skillcheck
antislop 100
skillcheck
WCAG AA
skillcheck
WCAG AAA
skillcheck
enterprise