systematic-debugging
Use when diagnosing a bug, failing check, unexpected behavior, or production incident before changing code.
Skill by tsergeytovarov
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/tsergeytovarov-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
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 and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Node.js package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/systematic-debugging~/threads/thread-manager~/threads/types
What's inside
- Skill name
systematic-debugging- Description
- Use when diagnosing a bug, failing check, unexpected behavior, or production incident before changing code. Do NOT use for known mechanical edits without a failure.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (12)
- CHANGELOG.md
- CREATION-LOG.md
- SKILL.md
- condition-based-waiting-example.ts
- condition-based-waiting.md
- defense-in-depth.md
- find-polluter.sh
- root-cause-tracing.md
- test-academic.md
- test-pressure-1.md
- test-pressure-2.md
- test-pressure-3.md
SKILL.md (first lines)
# Systematic Debugging Find the failing boundary and root cause before implementing a fix. Scale the investigation and regression protection to the risk. Read `../using-superpowers/references/risk-policy.md`. ## 1. Establish Evidence - Read the complete error and relevant logs. - Reproduce the symptom or state why reproduction is unavailable. - Check recent changes and environmental differences. - Trace the bad value or state backward across component boundaries. - Add temporary diagnostics only where evidence is missing. Do not propose a fix from the symptom alone. ## 2. Form One Hypothesis State the suspected root cause and the evidence supporting it. Make the smallest reversible experiment that distinguishes this hypothesis from the alternatives. Change one variable at a time. If the experiment fails, update the hypothesis instead of stacking fixes. ## 3. Implement the Root-Cause Fix - Keep the production change narrow. - Remove temporary diagnostics unless they provide lasting operational value. - Avoid unrelated refactoring. ### Regression Protection - High risk or reproduced regression: write one minimal automated regression or contract test first when practical. - Medium risk: add a focused test only when the failure would otherwise be hard to notice again. - Low risk or impractical automation: use a reproducible smoke check. Do not create a test for every helper touched by the fix. ## 4. Verify the Boundary Run the original reproduction and the closest affected checks. Run the full suite only for shared core changes, a release boundary, or an explicit request. After 3 failed fix hypotheses, stop and reassess the architecture or missing evidence with the user. Do not start a blind fourth attempt. ## Supporting Techniques - `root-cause-tracing.md` - `defense-in-depth.md` - `condition-based-waiting.md`
From tsergeytovarov/ai-settings, MIT.
More from tsergeytovarov/ai-settings
- 0.643score
brainstorming
tsergeytovarov
Use when a request leaves material product, architecture, behavior, or scope decisions unresolved.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
using-superpowers
tsergeytovarov
Use when starting a conversation or deciding whether a Superpowers workflow matches the current task.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
product-spec-pipeline
tsergeytovarov
Turn a raw product idea, feature request, improvement, or small product task into a proportionate, verified, and independently reviewed product specification.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
ru-commit-message
tsergeytovarov
Use when the user asks "напиши коммит / сгенерь commit message / опиши этот diff as commit".
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
tg-post-writer
tsergeytovarov
Use when the user asks "напиши пост в тг / оформи это для телеграма / сделай tg-пост про X".
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
subagent-driven-development
tsergeytovarov
Use when the user requests delegated implementation or multiple substantial tasks are genuinely independent without shared state.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
boilerplate
tsergeytovarov
Use when starting a new project from scratch.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
receiving-code-review
tsergeytovarov
Use when receiving code review feedback that may be unclear or technically questionable and needs verification.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
executing-plans
tsergeytovarov
Use when implementing an approved written plan with dependent tasks in the current session.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
requesting-code-review
tsergeytovarov
Use when a completed change is high-risk, crosses subsystem boundaries, or the user explicitly requests independent review.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
dispatching-parallel-agents
tsergeytovarov
Use when 2 or more substantial tasks are independent, have disjoint state, and parallel execution will save meaningful time.
SkillAFreshness: A★ 15Claude Code +9 - 0.638score
feature-architecture
tsergeytovarov
Use when proposing the architecture for a NEW feature on top of an existing codebase — after discovery/recon, when you must commit to one design with a…
SkillAFreshness: A★ 15Claude Code +9
Signals
- Stars
- 15
- Forks
- 4
- Open issues
- 2
- Last commit (this folder)
- Jul 31, 2026 (2 months ago)
- Last release
- Oct 12, 2026 (17 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/tsergeytovarov/ai-settings
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tsergeytovarov
- 0.643score
product-spec-pipeline
tsergeytovarov
Turn a raw product idea, feature request, improvement, or small product task into a proportionate, verified, and independently reviewed product specification.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
tg-post-writer
tsergeytovarov
Use when the user asks "напиши пост в тг / оформи это для телеграма / сделай tg-пост про X".
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
using-superpowers
tsergeytovarov
Use when starting a conversation or deciding whether a Superpowers workflow matches the current task.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
brainstorming
tsergeytovarov
Use when a request leaves material product, architecture, behavior, or scope decisions unresolved.
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
ru-commit-message
tsergeytovarov
Use when the user asks "напиши коммит / сгенерь commit message / опиши этот diff as commit".
SkillAFreshness: A★ 15Claude Code +9 - 0.643score
subagent-driven-development
tsergeytovarov
Use when the user requests delegated implementation or multiple substantial tasks are genuinely independent without shared state.
SkillAFreshness: A★ 15Claude Code +9
Cite this page
systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/tsergeytovarov-systematic-debugging (last updated 2026-10-24)