Teach

Teaching is how and why composed for a learner: what the subsystem does and the reasons it is shaped that way, in an order a person can absorb.

Workflow

Ask the learner's baseline: one question — familiar with the domain, the language, or neither. Size the explanation to the answer.
How first (how skill): the walkthrough, entry to exit, cited to file:line, at the depth the baseline supports.
Then why (why skill): the 2-4 decisions that shaped it, each with its evidence and the alternative it beat. Human rulings quoted verbatim.
Check the landing: ask the learner to predict one behavior — "if X happens, what does the subsystem do?" A correct prediction ends the lesson; a wrong one names the layer to redo. The check is for pacing, not grading.

Rules

One new concept per paragraph; jargon defined at first use in one clause.
Cite code for behavior, cite records for reasons; label anything you inferred.
Stop when the learner can predict behavior — completeness is not the goal, transfer is.

Files1

1 files · 1.0 KB

Select a file to preview

Overall Score

68/100

Grade

C

Adequate

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

92

Quality

62

Clarity

75

Completeness

48

Summary

This skill teaches an agent how to explain a subsystem to a learner through a structured "how and why" approach. It guides the agent to assess baseline knowledge, walk through code with citations, explain design decisions with evidence, and validate understanding through prediction checks. The skill is purely instructional and involves no file writes, destructive operations, or security-sensitive actions.

Detected Capabilities

read code filesanalyze code structurecompose narrative explanationscite code referencesquery learner for context

Trigger Keywords

Phrases that agents use to match this skill to user intent.

explain subsystemteach architectureonboard new developerknowledge transfercode walkthrough

Referenced Domains

External domains referenced in skill content, detected by static analysis.

github.com

Use Cases

Onboard new team members to unfamiliar subsystems
Transfer knowledge about code architecture and design decisions
Explain complex system behavior with progressive depth matching learner background
Validate learner comprehension through prediction-based checks
Document reasoning behind architectural choices through guided walkthroughs

Quality Notes

Clear, concise workflow with four well-defined steps that are easy to follow
Rules section provides helpful guardrails (one concept per paragraph, cite code, define jargon) that ensure quality explanations
Skill is minimal and focused — it avoids unnecessary detail and over-specification
No supporting examples or scaffolds provided to help agents understand what good output looks like
Lacks concrete guidance on how to assess 'baseline knowledge' or what depth thresholds trigger different explanation levels
No error handling or fallback patterns documented — what if the learner gives ambiguous answers or the subsystem is too large?
Missing explicit guidance on citation format (e.g., 'file.ts:42-55') or how to locate relevant code sections
Does not address how to prioritize which decisions to explain when many exist (e.g., top N most impactful)

Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

teach