systematic-debugging
Structured root cause analysis for bugs and unexpected behaviour.
Skill by Nomadcxx
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/nomadcxx-systematic-debugging
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/systematic-debugging
What's inside
- Skill name
systematic-debugging- Description
- Structured root cause analysis for bugs and unexpected behaviour. Use when encountering errors, test failures, or surprising results.
- License
- BSD-3-Clause
- Instructions
- 62 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
---
## Systematic Debugging
Work through bugs in numbered steps. Track each step explicitly so it is easy to revisit and revise.
### Step 1 — Reproduce the Failure
Get the exact error message, exact inputs, and exact environment. Never reproduce from memory. Copy the actual stack trace. Check whether the failure is deterministic or intermittent.
### Step 2 — Isolate the Failure
Binary-search through the call stack. Disable half the code; if the bug disappears, it was in the half you removed. Narrow the reproducer to the smallest possible input.
### Step 3 — Form and Test Hypotheses
State the hypothesis explicitly before testing it ("I think X is nil because Y"). Run exactly one experiment per hypothesis. Record the result even if it disproves you — disproof is progress.
### Step 4 — Read Error Messages Carefully
Go errors are wrapped; read from the innermost cause outward. JavaScript stack traces list callers top-to-bottom. Python tracebacks list callers bottom-to-top. Never skim the error message.
### Step 5 — Check Assumptions
List assumptions about the system before searching for a bug. Common wrong assumptions:
- "this function is always called"
- "this value is always set"
- "this goroutine is the only writer"
- "the test environment matches production"
### Step 6 — Check Recent Changes
When a bug is new, check `git log --oneline -20` and `git diff HEAD~1` before doing anything else. Most regressions live in the last commit.
### Step 7 — Do Not Jump to Solutions
Do not write code until the root cause is confirmed. Premature fixes mask the real problem and create two bugs.
### Step 8 — Verify the Fix
Re-run the exact reproducer. Also run the full test suite. Check that the fix does not break adjacent behaviour.
### Language-Specific Patterns
**Go:**
- nil pointer dereference — check every pointer before use
- goroutine leak — context not cancelled, channel never closed
- race condition — use `-race`
- silent error discard — `_ = err` is a red flag
**JS/TS:**
- `undefined is not a function` — method called on wrong type
- unhandled promise rejection
- mutation of shared state in async code
- stale closure in `useEffect`
**Python:**
- mutable default argument (`def f(x=[])`)
- import side-effects
- off-by-one in slice notation
- `==` vs `is` for NoneFrom Nomadcxx/smolbot, BSD-3-Clause.
More from Nomadcxx/smolbot
- 0.437score
memory
Nomadcxx
Use when starting, resuming, or ending non-trivial coding, debugging, RCA, incident analysis, or architecture/design work where prior failures, decisions…
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
clawhub
Nomadcxx
Interact with ClawHub registry for browsing, searching, and managing AI agent skills and tools.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-review
Nomadcxx
Review changed code for correctness, logic bugs, edge cases, security issues, and clarity.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
cron
Nomadcxx
Schedule and manage periodic tasks with cron-style scheduling.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
discord
Nomadcxx
Operating procedures for the Discord channel in smolbot.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
git-operations
Nomadcxx
Common git workflows for committing, branching, rebasing, conflict resolution, and undoing mistakes.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
github
Nomadcxx
Interact with GitHub repositories for code search, file operations, and repository management.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
channel-triage
Nomadcxx
Routing and triage across multiple messaging channels in smolbot.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
tmux
Nomadcxx
Manage tmux terminal sessions for persistent and multi-window terminal workflows.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
weather
Nomadcxx
Get current weather conditions and forecasts for locations.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
web-research
Nomadcxx
Multi-step research workflow: form a question, search multiple angles, cross-check sources, synthesise.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
signal
Nomadcxx
Operating procedures for the Signal channel in smolbot.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 31, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- BSD-3-Clause
- Repository
- github.com/Nomadcxx/smolbot
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Nomadcxx
- 0.437score
memory
Nomadcxx
Use when starting, resuming, or ending non-trivial coding, debugging, RCA, incident analysis, or architecture/design work where prior failures, decisions…
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
code-review
Nomadcxx
Review changed code for correctness, logic bugs, edge cases, security issues, and clarity.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
cron
Nomadcxx
Schedule and manage periodic tasks with cron-style scheduling.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
discord
Nomadcxx
Operating procedures for the Discord channel in smolbot.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
git-operations
Nomadcxx
Common git workflows for committing, branching, rebasing, conflict resolution, and undoing mistakes.
SkillDFreshness: D★ 1Claude Code +9 - 0.432score
clawhub
Nomadcxx
Interact with ClawHub registry for browsing, searching, and managing AI agent skills and tools.
SkillDFreshness: D★ 1Claude Code +9
Cite this page
systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/nomadcxx-systematic-debugging (last updated 2026-10-24)