teaching-developer-concepts
Skill1 starsChanged 3 months agoMITView on GitHub
Use when a specific developer capability gap is known and the learner needs a concise explanation, targeted examples, and practice that leads toward demonstration.
In this repository65 other files it gives its agents.
- analyzing-change-blast-radiusSkill
- analyzing-developer-career-opportunitiesSkill
- art-directing-web-interfacesSkill
- assessing-developer-proficiencySkill
- auditing-dependency-riskSkill
- auditing-pixel-perfect-frontendSkill
- bootstrapping-modern-web-appsSkill
- brag-slimSkill
- building-brand-guidelinesSkill
- building-conversion-product-pagesSkill
- building-developer-career-roadmapsSkill
- building-hybrid-game-assetsSkill
- building-premium-nextjs-interfacesSkill
- building-project-showcasesSkill
- building-regression-testsSkill
- building-reliable-node-api-boundariesSkill
- choosing-application-architectureSkill
- craft-premium-motionSkill
- creating-character-sprite-pipelinesSkill
- defining-brand-strategySkill
- designing-action-combatSkill
- designing-developer-portfolio-evidenceSkill
- designing-relational-data-modelsSkill
- designing-software-boundariesSkill
- designing-test-strategiesSkill
- designing-ui-systemsSkill
- designing-visual-identitiesSkill
- documenting-architecture-decisionsSkill
- editing-for-clarity-and-toneSkill
- engineering-gsap-animationsSkill
- evaluating-developer-proficiencySkill
- evolving-postgres-schemas-safelySkill
- humanizing-generated-proseSkill
- implementing-reference-faithful-uiSkill
- investigating-codebase-semanticallySkill
- managing-implementation-slicesSkill
- mapping-existing-codebase-structureSkill
- naming-brands-and-productsSkill
- optimizing-frontend-motion-performanceSkill
- orchestrating-cinematic-web-motionSkill
- planning-codebase-changes-with-evidenceSkill
- planning-engineering-workSkill
- planning-launch-distributionSkill
- planning-safe-refactorsSkill
- planning-written-communicationSkill
- preparing-project-launchSkill
- profiling-postgres-query-performanceSkill
- reconstructing-images-as-threejsSkill
- reviewing-api-securitySkill
- reviewing-apple-platform-interfacesSkill
- reviewing-pull-requestsSkill
- reviewing-web-securitySkill
- selecting-working-methodsSkill
- shipping-github-vercel-changesSkill
- testing-integration-boundariesSkill
- testing-playable-gamesSkill
- testing-web-applications-end-to-endSkill
- threat-modeling-applicationsSkill
- tracing-code-execution-pathsSkill
- translating-figma-to-nextjsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Start from a named capability, the learner's current evidence, the target criterion, and any misconception already observed.
- Distinctive: line 18
Prefer contrast when it reveals a boundary: correct vs fragile state ownership, safe vs unsafe query construction, observed vs derived …
- Distinctive: line 22
ask for retrieval or explanation in the learner's own words.
- Distinctive: line 23
use a short code-reading or reasoning exercise when appropriate.
- Distinctive: line 30
When current external research is available, recommend a small number of high-quality resources tied to the exact gap.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Teaching Developer Concepts
Teach only what is needed to close the current capability gap and move the learner toward practice or evaluation. Optimize for transfer to action, not content volume.
Anchor on one capability gap
Start from a named capability, the learner's current evidence, the target criterion, and any misconception already observed. If the gap is not known, diagnose it before teaching broadly.
State the learning objective as something the learner should be able to explain, reason about, debug, or implement.
Explain the smallest useful model
Introduce the core mental model first. Use terminology that matches the target domain, then connect abstractions to concrete behavior with one or two focused examples.
Prefer contrast when it reveals a boundary: correct vs fragile state ownership, safe vs unsafe query construction, observed vs derived state, or interface vs implementation detail.
Move quickly into practice
After the explanation:
- ask for retrieval or explanation in the learner's own words;
- use a short code-reading or reasoning exercise when appropriate;
- progress to a small implementation/debugging task when the target capability requires performance;
- give feedback against the same named criterion.
Increase difficulty only when the evidence supports it.
Recommend resources selectively
When current external research is available, recommend a small number of high-quality resources tied to the exact gap. Distinguish primary documentation from tutorials and community material. Do not turn the response into a course catalog.
Handoff to demonstration
Finish by stating what evidence would show the learner is ready for a formal assessment or authentic project task. Learning activity itself is not proficiency evidence unless the learner demonstrates the required behavior.
Ownership boundaries
This method owns gap-targeted microlearning, explanation, examples, practice, and resource guidance. It does not diagnose the whole career baseline, sequence the roadmap, redefine proficiency criteria, or award a formal level.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

