Focus
What this guide teaches
The goal is not to memorize tool names. The goal is to understand how teaching tasks should be analyzed and matched to the right kind of skill support.
Process Guide
This page is not centered on a single final `skill.md` file. It teaches how teachers can understand, sequence, and practice skill usage through workflow thinking: define the task, choose the right skill type, build checkpoints, interpret the meaning of each skill entry, and revise the process until it becomes teachable.
Focus
The goal is not to memorize tool names. The goal is to understand how teaching tasks should be analyzed and matched to the right kind of skill support.
Principle
A polished slide deck or handout can hide weak reasoning. This guide emphasizes the path behind the output: task framing, source preparation, tool pairing, validation, and revision.
Build A Skill
A skill usually starts because the same kind of task keeps returning: making slides, organizing a handout, cleaning data, finding references, or checking whether an AI explanation is accurate. That repetition is the signal that the task can be compressed into a reusable method.
In practice, a skill is a packaged teaching method. Its value is not that the text looks sophisticated. Its value is that someone else can reuse the logic with less confusion.
If these four points are unclear, the skill will likely remain a private note rather than a reusable teaching tool.
State whether the skill is mainly for documents, slides, data work, literature support, or validation.
List the materials users usually bring, such as topic, data, PDF, references, audience, or time limit.
Describe what a useful result should look like: structure, pacing, format, or evidence quality.
State how the result will be checked for readability, teachability, reproducibility, or source accuracy.
A practical first draft should be small. Run it against one real task, note where the instructions are vague, which inputs tend to break the flow, and what outputs still feel weak. Then feed those lessons back into the skill.
A strong skill usually shows why certain constraints were added, which warnings came from failure, and which checkpoints were introduced to stop repeated mistakes. That is why teaching a skill should include how it was shaped, not only what the final file says.
Learning Stages
Decide whether the teaching need is explanation, presentation, data interpretation, or live demonstration.
Choose document, slide, spreadsheet, literature, validation, or orchestration support based on the task instead of starting with a fixed tool.
Separate each workflow into input, processing, output, and review so the method can be taught clearly.
Learning improves when each run is reviewed for clarity, efficiency, and error detection, not just for completion.
Generic Skill Types
| Skill type | Generic role | What the learner should practice | Common mistake |
|---|---|---|---|
| `presentations` | Turns content into live teaching rhythm and visual pacing | Practice selection, sequencing, and slide-level signal control | Treating slides as a full handout |
| `documents` | Turns concepts and procedures into readable teaching material | Practice structure, explanation depth, and conversion from spoken process to written guidance | Focusing only on formatting instead of instructional clarity |
| `spreadsheets` | Organizes fields, calculations, comparisons, and chart logic | Practice data cleaning, column design, interpretation, and translation into teaching language | Jumping to presentation before analysis is ready |
| `pdf` | Extracts reusable knowledge from existing materials | Practice summarizing, regrouping, and rewriting for new audiences | Using the original PDF as the final teaching product |
| `crossref-apa-bibliography` | Builds the research and citation backbone | Practice source retrieval, comparison, and citation consistency | Listing references without showing how they support the teaching argument |
| `openai-docs` | Provides official capability and product grounding | Practice verification, version awareness, and source checking | Treating informal online claims as official documentation |
| `external-agent-orchestrator` | Plans tool roles and sequence across a workflow | Practice decomposition, coordination, and return-path validation | Looking only at the final result instead of tool timing and role assignment |
| `execution-recovery-guardrails` | Turns failure points into teachable validation rules | Practice checkpoint design and error recovery logic | Seeing failure as a side issue instead of part of the teaching process |
Skill.md Guide
Instead of pasting raw configuration text, this section translates the core instructional meaning behind each skill entry: what kind of task it handles, what usually goes in, what comes out, and what a teacher should learn to notice while using it.
presentations:PresentationsUsed for turning a teaching topic into a live-facing slide structure.
Typical inputTopic, audience, time limit, examples, or data points.
Typical outputA slide deck with clear pacing, section order, and message-per-slide discipline.
Teaching checkpointThe learner should ask whether each slide carries one primary teaching signal.
documents:documentsUsed for turning steps, concepts, and examples into reusable written teaching material.
Typical inputInstructional steps, case explanations, workshop notes, or procedural guidance.
Typical outputA structured handout, guide, plan, or explanatory document.
Teaching checkpointThe learner should check whether the text still works when the teacher is not present to explain it.
spreadsheets:SpreadsheetsUsed for score tables, survey scales, schedules, and educational data handling.
Typical inputRaw columns, test scores, attendance, rubric data, or comparative records.
Typical outputClean fields, summary tables, charts, and interpretable comparisons.
Teaching checkpointThe learner should verify that the data is already interpretable before moving it into a talk or handout.
pdf:pdfUsed for extracting reusable ideas from existing PDF-based material.
Typical inputResearch papers, slide exports, handouts, or report appendices in PDF form.
Typical outputSummaries, extracted sections, restructured content, or teaching-ready rewrites.
Teaching checkpointThe learner should check whether the PDF has been transformed into teachable material instead of merely copied.
crossref-apa-bibliographyUsed for research support and citation management in scholarly sharing.
Typical inputTopic keywords, DOI, author names, or journal references.
Typical outputAPA references, source lists, and a clearer citation backbone.
Teaching checkpointThe learner should know which references actually support the teaching claim being made.
openai-docsUsed for official capability checks, API guidance, and product-grounded explanations.
Typical inputModel questions, product comparisons, API usage, or official feature lookups.
Typical outputTraceable official explanations and lower-risk teaching statements.
Teaching checkpointThe learner should practice verifying claims before presenting them as fact.
external-agent-orchestratorUsed for multi-tool sequencing, role assignment, and validation flow design.
Typical inputComplex tasks, multiple tool roles, verification rules, and cost constraints.
Typical outputA clearer workflow showing who does what, in what order, and where results are checked.
Teaching checkpointThe learner should be able to explain the role of each tool, not just show the end product.
execution-recovery-guardrailsUsed for turning repeated mistakes into teachable recovery logic.
Typical inputFailure cases, repeated errors, broken steps, or unstable process points.
Typical outputChecklists, recovery rules, and a more stable repeatable workflow.
Teaching checkpointThe learner should ask whether failure has been converted into a rule others can follow.
Scenario Paths
Teacher Questions
Practice Cycle
Build the smallest workable version. One page, three slides, or one analysis view is enough.
Add validation. Check sources, sequence, chart meaning, and whether the workflow can be followed by others.
Rebuild the same topic for a different setting so the learner practices transfer instead of repetition.
Common Errors
Teaching Aim
The intended outcome is a way of thinking: identify the task, choose the right support type, sequence the workflow, set checkpoints, and refine the result through repeated practice.