systematic-debugging
Use when diagnosing a failure, flaky behavior, or unexpected output before attempting a fix.
Skill by RakuenSoftware
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/rakuensoftware-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. 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
- Use when diagnosing a failure, flaky behavior, or unexpected output before attempting a fix.
- License
- AGPL-3.0
- Instructions
- 18 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- condition-based-waiting.md · references/
- root-cause-tracing.md · references/
SKILL.md (first lines)
# Systematic Debugging Start with evidence, not guesses. 1. Reproduce the failure with the smallest command, input, or trace available. 2. Read the failing path until you can explain where expected state diverges from actual state. 3. Form one hypothesis that predicts an observable result. 4. Test the hypothesis with a targeted command, log, assertion, or code read. 5. Apply a fix only after the evidence identifies the cause. After three failed fixes, stop changing code and re-check the model of the system. Repeated patches without a new observation usually mean the cause is elsewhere. Useful references: - `references/root-cause-tracing.md` - `references/condition-based-waiting.md`
From RakuenSoftware/aimee, AGPL-3.0.
More from RakuenSoftware/aimee
- 0.789score
writing-skills
RakuenSoftware
Use when creating or editing an aimee skill.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
delegate-routine-work
RakuenSoftware
Use when a bounded subtask is summarization, mechanical review, fixture inspection, proposal triage, verification, or boilerplate.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
search-project-knowledge
RakuenSoftware
Use when you need a project fact, document, relationship, investigation note, or prior finding that may already be captured.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
find-symbols
RakuenSoftware
Use when locating where a symbol, function, type, command, or constant is defined or referenced, instead of grep/find/read chains.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
receiving-code-review
RakuenSoftware
Use when evaluating reviewer feedback, review delegates, or suggested code changes.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
keeping-it-simple
RakuenSoftware
Use when tempted to add broad abstractions, future-proofing, or extra product surface beyond the requested change.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
condition-based-waiting
RakuenSoftware
Use when waiting for servers, jobs, files, tests, queues, or external processes.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
using-skills
RakuenSoftware
Use when deciding whether a task matches an available skill before starting work.
SkillAFreshness: A★ 188Claude Code +9 - 0.775score
verification-before-completion
RakuenSoftware
Use before claiming work is done, fixed, passing, complete, or ready to merge.
SkillAFreshness: A★ 188Claude Code +9 - 0.775score
recall-before-asking
RakuenSoftware
Use before asking the user about infrastructure, preferences, conventions, prior decisions, or past incidents.
SkillAFreshness: A★ 188Claude Code +9 - 0.644score
test-driven-development
RakuenSoftware
Use before changing behavior or fixing a bug when a focused test can prove the change.
SkillAFreshness: A★ 188Claude Code +9
Signals
- Stars
- 188
- Forks
- 68
- Open issues
- 0
- Last commit (this folder)
- Jun 3, 2026 (4 months ago)
- Last release
- Oct 16, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- AGPL-3.0
- Repository
- github.com/RakuenSoftware/aimee
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from RakuenSoftware
- 0.789score
writing-skills
RakuenSoftware
Use when creating or editing an aimee skill.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
delegate-routine-work
RakuenSoftware
Use when a bounded subtask is summarization, mechanical review, fixture inspection, proposal triage, verification, or boilerplate.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
search-project-knowledge
RakuenSoftware
Use when you need a project fact, document, relationship, investigation note, or prior finding that may already be captured.
SkillAFreshness: A★ 188Claude Code +9 - 0.782score
find-symbols
RakuenSoftware
Use when locating where a symbol, function, type, command, or constant is defined or referenced, instead of grep/find/read chains.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
receiving-code-review
RakuenSoftware
Use when evaluating reviewer feedback, review delegates, or suggested code changes.
SkillAFreshness: A★ 188Claude Code +9 - 0.781score
keeping-it-simple
RakuenSoftware
Use when tempted to add broad abstractions, future-proofing, or extra product surface beyond the requested change.
SkillAFreshness: A★ 188Claude Code +9
Cite this page
systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/rakuensoftware-systematic-debugging (last updated 2026-10-24)