Reducing Cognitive Load
Review dense, clever, stringly typed, weakly typed, over-abstracted, or hard-to-read code, especially data flows and type boundaries.
Install
$ agentstack add skill-jesse-merhi-skills-reducing-cognitive-load ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-jesse-merhi-skills-reducing-cognitive-load) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Reducing Cognitive Load
Use this skill to make code easier to read without turning it into a maze of tiny wrapper functions. The goal is not "more abstraction"; the goal is a smaller mental stack for the next maintainer.
Core Rule
Prefer code that exposes domain concepts, invariants, and data shapes. Avoid code that makes readers reverse-engineer hidden protocols, positional fields, duplicated types, or clever inline transformations.
Workflow
- Look for existing domain types, schemas, API response types, route types, and
shared model types before inventing a local type.
- Decide where each concept belongs:
- boundary/shared type when it crosses module boundaries, is consumed by
multiple modules, or encodes a domain concept
- local named type when it is only a tiny implementation detail
- Model structured data before serialization. If data becomes a string, array,
or hash, serialize once at an explicit boundary.
- Scan for the red flags in [red-flags.md](references/red-flags.md).
- Apply the replacement patterns in [patterns.md](references/patterns.md).
- Use the extraction test in [extraction-test.md](references/extraction-test.md)
before adding helper functions.
- When reviewing a diff, use [review-checklist.md](references/review-checklist.md)
and prefer concrete rewrites over vague "make this cleaner" comments.
Completion Criteria
- The code exposes the domain concept before the encoding detail.
- Shared contracts use shared types instead of duplicated local shapes.
- Serialization boundaries have names and tests when the protocol matters.
- Helpers name concepts, invariants, boundaries, or meaningful duplication.
- The reader can see what is being built before studying how it is encoded.
Context Pointers
- Use [red-flags.md](references/red-flags.md) for common cognitive-load smells.
- Use [patterns.md](references/patterns.md) for typed objects, unions,
serialization boundaries, and protocol tests.
- Use [extraction-test.md](references/extraction-test.md) before extracting a
helper.
- Use [review-checklist.md](references/review-checklist.md) when producing review
findings.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: jesse-merhi
- Source: jesse-merhi/skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.