Skills MCP Plugins Subagents

Browse by category

Coding Skills2061 Marketing Skills1580 Design Skills1479 Security Skills1134 Automation Skills994 Testing Skills985 Media Skills908 Infrastructure Skills902 Data Skills883 Finance Skills840 Automation MCPs799 Planning Skills797 DevTool MCPs797 Documentation Skills757 Coding MCPs738 Productivity Skills721 Productivity MCPs649 Data MCPs505 DevTool Skills503 Infrastructure MCPs482 Security MCPs441 Debugging Skills428 Code review Skills415 Search & RAG MCPs409

The Monday digest

The week's best new agents, skills and MCP servers. One email, every Monday.

Free · unsubscribe anytime.

aaaa.fyi

Every agent skill, MCP server, plugin and subagent — searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

Agent Skills MCP Servers Plugins Subagents Coding Agents

Collections Official publishers Glossary Blog Search Saved Feedback

Privacy Terms llms.txt Sitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/loopkit/systematic-debugging

home/skills/archive228/loopkit/systematic-debugging

systematic-debugging

712stars129forks

How to install systematic-debugging?

archive228/loopkit/systematic-debugging

$npx -y skills add Archive228/loopkit --skill systematic-debugging

Installs into the current project.

Summary

Use for ANY bug, test failure, crash, or unexpected behavior. Forces

Files · 1

SKILL.md

1	# Systematic Debugging
2
3	The single most expensive agent failure: seeing an error and immediately generating a
4	"fix" based on the error type, without reading what actually happened. Don't.
5
6	## The loop
7
8	1. Read the whole error. The entire message and stack trace. A TypeError can mean a
9	hundred different things — the trace tells you which one. Quote the exact line that throws.
10
11	2. Reproduce it first. If you can't reproduce it, you can't verify a fix. Write the
12	smallest input that triggers it. "I think this fixes it" is gambling, not debugging.
13
14	3. Form one hypothesis, name it. "I think the value is null because the upstream call
15	returns 204 with no body." State it before you touch anything.
16
17	4. Change one thing. Test. Repeat. If you change three things and it works, you don't
18	know which one fixed it — and the other two may have added new bugs.
19
20	5. Fix the root cause, not the symptom. A null check that hides a null is not a fix.
21	Find why it's null. The underlying bug will resurface differently if you only patch the crash.
22
23	## Stop conditions
24
25	- If 3 hypotheses fail, STOP and report: what you tried, what you saw, what you suspect.
26	"I've tried X and Y, here's the output, I think it's Z but I'm not sure" beats 20 silent
27	random attempts.
28	- Never add a workaround you don't understand.
29
30	## Output
31
32	End with: the root cause (one sentence), the minimal fix, and the test that now proves it.

Archive228Publisher · 56 listings

Preview

Archive228/loopkit

# Systematic Debugging

The single most expensive agent failure: seeing an error and immediately generating a

"fix" based on the error type, without reading what actually happened. Don't.

## The loop

$ npx -y skills add Archive228/loopkit --skill systematic-debugging

▸ installing to .claude/skills…

✓ systematic-debugging ready

RepoArchive228/loopkit

LicenseMIT

CategoryDebugging

UpdatedJul 2026

Repo stars712

First seenJul 22, 2026

Tags

Skill Debugging

People who liked this also viewed

6 picks

Type

azure-diagnosticsDebug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deploySkillsJul 2026472k1.3k
systematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesSkillsJul 2026197k259k
safe-debugRigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training SkillsMay 2026161k507
explore-runRigor Improve / Rigor Explore run leaf skill for bounded exploratory evidence in deep learning research repositories. Use when the researcher explicitly authorizes exploratory runs such as small-subseSkillsMay 2026161k507
minimal-run-and-auditRigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation SkillsMay 2026161k507
insforge-debugUse when diagnosing problems in an InsForge project — reactive failures (SDK error object, HTTP 4xx/5xx, gateway timeout 502/503/504, edge function failure or timeout, login/OAuth/auth errors, RLS denSkillsJul 202618k31