SKILLEMALL.ai
GitHub ↗ RU Sign in

DD blended-learning-instructional-design

为高校及职业院校教师生成混合式教学设计方案、课程教学日历 Word 文档，以及 HTML 交互式说课课件与说课 PPT。当用户提到混合式教学、混合式教学设计、混合式教学设计大赛、线上线下融合课程、翻转课堂、超星学习通教学设计、说课课件、教学日历等关键词时调用本技能；即使用户未说出上述关键词，只要需求本质是“为一门课程设计线上线下融合的教学方案（含教学日历、说课课件或说课 PPT）”，也应主动调用本技能。

ClawHub Hermes author: Dever Lee v3.5.81 MIT-0 23 files · 11 scripts body ≈ 2 451 tokens Open the sourceclawhub.ai↗ analyzed 6 d ago

为高校及职业院校教师生成混合式教学设计方案、课程教学日历 Word 文档，以及 HTML 交互式说课课件与说课…

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureWordPowerPointLearningtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
D
77/100
safety, quality, tests
Safety 60%
86
Quality 40%
63
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 14

✓ No critical or high findings

Medium and low: 14
  • low Obfuscation obf-base64-blob assets/templates/templates.json:1
    Long base64-looking blob (quoted — discussed, not commanded)
    {"混合式教学设计方案模版.docx": "UEsD…AAA
    quoted
  • low Secrets in code secret-high-entropy-token assets/templates/templates.json:1
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    {"混合式教学设计方案模版.docx": "UEsD…AAA
    quoted
  • low Obfuscation obf-base64-blob references/bloom_reference.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "EAiNIqcROLCz+giSS…d87/x3fZ…jqn+HP6N…H7t+MCHt/jxkN…9qN+TI3it/Hchgc9a0X6a+g2TDkjWJt
    quoted
  • low Secrets in code secret-high-entropy-token references/bloom_reference.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "EAiNIqcROLCz+giSS…d87/x3fZ…jqn+HP6N…H7t+MCHt/jxkN…9qN+TI3it/Hchgc9a0X6a+g2TDkjWJt
    quoted
  • low Obfuscation obf-base64-blob references/design_plan_guide.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "DO6u…IX9+OrP4…uJF+dQdb…vSn+T2gB9
    quoted
  • low Secrets in code secret-high-entropy-token references/design_plan_guide.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "DO6u…IX9+OrP4…uJF+dQdb…vSn+T2gB9
    quoted
  • low Obfuscation obf-base64-blob references/faq.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "Vujv…dsO+nOd/X91s…Z6j+6BCZ…wzQ/Yw7F…n69
    quoted
  • low Secrets in code secret-high-entropy-token references/faq.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "Vujv…dsO+nOd/X91s…Z6j+6BCZ…wzQ/Yw7F…n69
    quoted
  • low Obfuscation obf-base64-blob references/footer_note.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "nQQk…Vut+aMkX…K3t/vZ8i…DvE+m+T41u…Nph
    quoted
  • low Secrets in code secret-high-entropy-token references/footer_note.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "nQQk…Vut+aMkX…K3t/vZ8i…DvE+m+T41u…Nph
    quoted
  • low Obfuscation obf-base64-blob references/methodology.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "uX1i…ZSe+E01g5D6Af+ZstE…RKE+Voo9…8bk+h3Th…p2z/S6feT5LzDB
    quoted
  • low Secrets in code secret-high-entropy-token references/methodology.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "uX1i…ZSe+E01g5D6Af+ZstE…RKE+Voo9…8bk+h3Th…p2z/S6feT5LzDB
    quoted
  • low Obfuscation obf-base64-blob references/output_preview.json:7
    Long base64-looking blob (quoted — discussed, not commanded)
    "data": "f0Z9…X7x/PEEpGzqts1P/1U2z…BN1/pE/iSYH…rdv+LV65…6NU++38Fs…Epr
    quoted
  • low Secrets in code secret-high-entropy-token references/output_preview.json:7
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "data": "f0Z9…X7x/PEEpGzqts1P/1U2z…BN1/pE/iSYH…rdv+LV65…6NU++38Fs…Epr
    quoted

Files scanned: 23. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 203 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning description-no-when neither description nor a "## When to Use" section says when to use the skill
  • note frontmatter-key unknown frontmatter key "displayName"

Process rating: all ten parameters 41/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Consistency. Frontmatter name (blended-learning-instructional-design) differs from the folder (blended-learning-instructional-design-3-5-81)
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 100Steps. 47 steps
  • 100Execution cost. Instruction body is 2451 tokens
  • 100Running it twice. No mutating operations
  • low 10 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (8 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • -32 of 11 scripts are never mentioned in SKILL.md
  • +2Single-language instructions
  • +3Description length 203: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 47 items
  • +4Has examples (2 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.

External checks

ClawHub: suspicious
The skill is a coherent Chinese teaching-material generator, but it deserves review because normal use can automatically install Python packages and send course-search queries to external search engines.
LLM: suspicious (high) · VirusTotal: · 1 Oct 2026