LeoYeAI/agent-master-skills / skills/ai-shifu-course-creator
ai-shifu-course-creator
VerifiedConvert raw course material into optimized, runnable MarkdownFlow teaching scripts and deploy them as live courses through a five-phase pipeline covering segmentation, orchestration, generation, optimization, and deployment.
examples/fallback-mode.md
View on GitHub# Fallback Mode Example
Demonstrates degraded-input handling across phases.
## Phase 1 Fallback: Conflicting Sources
```json
{
"course_material": "doc-a: retries should stop after 3 attempts...\ndoc-b: retries can continue until queue drains...",
"course_profile": {
"audience_level": "intermediate"
}
}
```
Output includes uncertainty markers and rerun hints:
```json
{
"structured_segments_json": [
{
"segment_id": "S10",
"segment_type": "concept",
"core_point": "Retry stop conditions differ across sources.",
"source_span": {"start": 0, "end": 95},
"uncertainty": "high"
}
],
"rerun_hints": [
"Provide authoritative policy for max retry attempts."
]
}
```
## Phase 2 Fallback: Incomplete Input
```json
{
"course_material": "doc-1: classify by latency tiers\n\ndoc-2: classify by resource contention\n\ndoc-3: missing section ordering",
"generation_constraints": {
"lesson_granularity": "medium"
}
}
```
Pipeline produces partial but runnable output:
```json
{
"course_index": [
{
"lesson_id": "L03",
"lesson_title": "Choose a Classification Axis",
"core_question": "When should you prefer latency tiers over contention classes?",
"uncertainty": "medium"
}
],
"rerun_plan": {
"lessons_to_rerun": ["L03"],
"reason": "conflicting taxonomy across doc-1 and doc-2"
}
}
```
```md
## L03 Objective
Select a first-pass classification rule.
---
?[%{{classification_axis}} latency first | contention first]
---
Current evidence is partial; confirm one canonical taxonomy before final pass.
```
## Phase 3 Fallback: Minimal Segments
```json
{
"course_material": "structured_lesson_segments",
"teaching_constraints": {
"max_interactions": 2,
"allow_cross_lesson_dependency": false
}
}
```
```json
{
"lesson_id": "L07",
"fallback_mode": true,
"assumptions": [
"No cross-lesson variable carryover is used."
],
"upgrade_notes": [
"Add richer evidence chain after full source context is available."
]
}
```
## Phase 4 Fallback: No Source Material
```json
{
"existing_mdf_script": "## Goal\nPick a fix.\n---\n?[%{{fix_choice}} option A | option B]\n---\nUse {{unknown_variable}} now.",
"course_material": "",
"optimization_constraints": {
"fallback_mode": true,
"minimize_scope": true
}
}
```
```json
{
"risk_and_issue_report": {
"overall_risk": "high",
"blocking_issues": ["variable_or_syntax_risk"],
"coverage_status": "unknown_without_source"
},
"follow_up": [
"Provide source material for full coverage audit."
]
}
```
## Acceptance Notes
- Each phase degrades gracefully instead of failing hard.
- Uncertainty is marked explicitly, never silently merged.
- Rerun hints guide the user toward resolution.
- Output schemas remain compatible across standard and fallback modes.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |