draft-slts — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited draft-slts (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Generates well-formed Student Learning Targets (SLTs) for a course or module based on topic, audience, and learning goals. Follows education research best practices and Andamio protocol conventions.
Resolve file paths based on your execution context:
${CLAUDE_PLUGIN_ROOT} is set): Read knowledge from ${CLAUDE_PLUGIN_DATA}/knowledge/ (user data), falling back to ${CLAUDE_PLUGIN_ROOT}/knowledge/ (seed data). Read research from ${CLAUDE_PLUGIN_ROOT}/knowledge/research/.knowledge/ relative to the project root (research is at knowledge/research/).Before drafting SLTs, read the knowledge base for patterns that should influence your work. If any knowledge file does not exist, skip it and proceed without prior patterns — note "No prior data available" in output.
### Tips from Previous Courses
**Effective verbs at this level:** compare, distinguish, implement (12 successes)
**Patterns to avoid:** "understand X" (flagged 8 times), task-focused phrasingThe user will describe a course or module they want to create. Gather the following information (ask if not provided):
Always read knowledge/research/slt-research-report.md for full research context before drafting.
Every SLT must follow this structure:
I can + [measurable verb] + [specific outcome] + [observable evidence/context]
Examples:
Use verbs that match the cognitive level appropriate for the content:
| Level | Verbs | When to Use |
|---|---|---|
| Remember | list, name, identify, recall | Foundational facts, terminology |
| Understand | explain, describe, summarize, compare | Conceptual understanding |
| Apply | use, demonstrate, implement, execute | Procedural skills |
| Analyze | distinguish, examine, compare, contrast | Breaking down complex topics |
| Evaluate | judge, justify, critique, assess | Making judgments |
| Create | design, construct, develop, produce | Building something new |
Progression principle: Early modules should include more Remember/Understand/Apply. Later modules can include Analyze/Evaluate/Create.
Never use these unmeasurable verbs:
These cannot be assessed. Replace with specific, observable actions.
Generate SLTs in this exact format:
# SLTs: [Course Name]
## Module 1: [Module Title]
- 1.1: I can [verb] [specific outcome] [evidence/context].
- 1.2: I can [verb] [specific outcome] [evidence/context].
- 1.3: I can [verb] [specific outcome] [evidence/context].
## Module 2: [Module Title]
- 2.1: I can [verb] [specific outcome] [evidence/context].
- 2.2: I can [verb] [specific outcome] [evidence/context].
## Module 3: [Module Title]
- 3.1: I can [verb] [specific outcome] [evidence/context].
- 3.2: I can [verb] [specific outcome] [evidence/context].
- 3.3: I can [verb] [specific outcome] [evidence/context].Before outputting, verify each SLT:
Suggest the user:
/assess-slts to get quality feedback00-course.md with lesson types and assignments based on the finalized SLTs~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.