SKILLEMALL.ai
GitHub ↗ RU Sign in

BC curriculum-designer

Design customized curricula for PODs with REAL resource links. Staged implementation with checkpointing and fallback logic. Use when user says 'Design curriculum', 'Create curriculum for POD', or 'Build learning plan'.

LeoYeAI/openclaw-master-skills Agent Skills author: LeoYeAI MIT 3 files · 1 script body ≈ 5 394 tokens Open the sourcegithub.com↗ analyzed 25 h ago

Design customized curricula for PODs with REAL resource links.

As a process C 62/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice

ProcedureGoogle DocsGoogle SheetsYouTubeLearningMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
94
Quality 40%
75
Run on models
none yet
Process rating
C
62/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • low Secrets in code secret-high-entropy-token curriculum-designer.sh:14
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    GOG_FOLDER_ID="1upJ…VL9"
    detector
  • low Exfiltration exfil-secret-in-url curriculum-designer.sh:117
    Credential passed in a URL query string (normal for some APIs — verify the host is the intended service) (placeholder value)
    local result=$(curl -s "https://www.googleapis.com/youtube/v3/search?part=…&q=…&type=video&maxResults=5&videoDuration=…&key=…" 2>/dev/null)
    placeholder
  • low Exfiltration net-credential-use curriculum-designer.sh:117
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service)
    local result=$(curl -s "https://www.googleapis.com/youtube/v3/search?part=…&q=…&type=video&maxResults=5&videoDuration=…&key=…" 2>/dev/null)
    known service
  • low Secrets in code secret-high-entropy-token SKILL.md:59
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    - **Output Folder:** `1upJ…VL9` (Curriculum Designer)
    quoted
  • low Dangerous commands cmd-cron-mention SKILL.md:639
    Mentions editing / listing crontab
    crontab -e
  • low Dangerous commands cmd-cron-mention SKILL.md:670
    Mentions editing / listing crontab
    crontab -l

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5394 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 62/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 11 mutating operations with no state check
  • 50Failures and branches. 0 branches, has a failure section
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 5394 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 111 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (14 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)
  • -214 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 218: enough signal without eating the budget
  • +4Structure: 55 headings
  • +3Step-by-step instructions: 111 items
  • +3Output format is stated explicitly
  • +4Has examples (25 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.