debugging
Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and…
Skill by Leostruka
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/leostruka-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, devops
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/debugging
What's inside
- Skill name
debugging- Description
- Use when the user says 'diagnose', 'debug this', reports something broken/throwing/failing/slow, when encountering a bug/test failure/unexpected behavior and a fix is not yet obvious, or when CI is failing and the cause needs to be found across builds, jobs, or environments.
- License
- MIT
- Instructions
- 49 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (7)
- SKILL.md
- ci.md · modes/
- local.md · modes/
- condition-based-waiting.md · reference/
- defense-in-depth.md · reference/
- root-cause-tracing.md · reference/
- hitl-loop.template.py · scripts/
SKILL.md (first lines)
# Debugging **Core principle:** ALWAYS find root cause before attempting fixes. Symptom fixes are failure. `NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST.` Two modes; full detail in `modes/<mode>.md` — read it when you enter. | Mode | When | Detail | |---|---|---| | **Local** | Bug/test failure/slowness in the codebase, fix not obvious | `modes/local.md` | | **CI** | Pipeline failing across builds/jobs/environments | `modes/ci.md` | ## Local — the discipline (summary) 1. **Phase 1 — build a feedback loop FIRST.** A tight pass/fail signal that goes red on *this* bug is the whole skill; bisection and instrumentation just consume it. Spend disproportionate effort here. Without it you cannot propose fixes — that is the Iron Law. 2. Then trace data flow, form hypotheses, test one at a time, fix root cause. 3. Redact every secret in shown output (`<REDACTED>`); quote only signal lines. Red flags — return to Phase 1: "quick fix for now", "just try changing X", "add multiple changes", proposing before tracing, 3+ fix attempts, each fix revealing a new problem elsewhere. Reference: `reference/root-cause-tracing.md`, `reference/condition-based-waiting.md`, `reference/defense-in-depth.md`, `scripts/hitl-loop.template.py`. ## CI — essentials - **Access:** `gh run list/view` (GitHub), `glab ci list/view` (GitLab), CircleCI MCP, jenkins-cli, or parse the dashboard/logs manually. - **Flow:** identify project+CI → check pipeline status (skip if green) → fetch failure logs (`gh run view <id> --log-failed`) → check for flaky tests (intermittent across runs/seeds) → reproduce locally → fix → verify by re-running the workflow. - Distinguish real failures from flaky: same test failing intermittently or on retry → flag as flakiness, not the fix target. - Never push "fixes" to make CI green without a reproduced local failure. ## Cross-skills - `gates` — verification evidence before declaring fixed. - `research` deep-mode — when the bug spans modules you can't trace in a pass. - `computer-use` — when the failure is in a GUI/desktop app and needs screen evidence (screenshot, UIA tree) the shell can't see.
From Leostruka/devin-bundle, MIT.
More from Leostruka/devin-bundle
- 0.565score
cu-realtime
Leostruka
Use when computer-use or terminal automation needs the fastest reaction the runtime allows - event waits instead of screenshot polling, text perception…
SkillAFreshness: AClaude Code +9 - 0.565score
ask-bundle
Leostruka
Use when deciding which skill or flow fits your situation — the meta-router entry point for this bundle (direct specialist skills, multi-skill flows, local…
SkillAFreshness: AClaude Code +9 - 0.565score
code-review
Leostruka
Use when completing a task, reviewing a branch or PR, before merging, when the user asks to 'review since X', when publishing a GitHub PR review with inline…
SkillAFreshness: AClaude Code +9 - 0.565score
animation-direction
Leostruka
Use when turning narrated video/audio into synced code-rendered motion graphics — narration -> timestamped transcript -> scene plan -> approval gate ->…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture
Leostruka
Use when designing modules, seams, and adapters, when evaluating module depth and identifying deepening opportunities in a codebase, or when modernizing…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture-diagrams
Leostruka
Use when the deliverable is a physical diagram artifact (.svg/.png) — C4 models, dense class diagrams, network topology rendered via PlantUML.
SkillAFreshness: AClaude Code +9 - 0.565score
computer-use
Leostruka
Use when you need to see or control the local screen (screenshots, screen recording with video + contact sheet for catching transient bugs/animations, mouse…
SkillAFreshness: AClaude Code +9 - 0.565score
context-hygiene
Leostruka
Use when context is growing large or the agent forgets earlier instructions, when deciding clear vs compact, when processing documents/logs >50k tokens, when…
SkillAFreshness: AClaude Code +9 - 0.565score
ai-tools
Leostruka
Use when running local, offline-first ML tooling — mechanistic interpretability PoCs like refusal-direction ablation on local safetensors or the HF cache, or…
SkillAFreshness: AClaude Code +9 - 0.560score
ascii-art
Leostruka
Use when generating animated ASCII art for artifacts the agent produces - README banners (SVG), CLI splash screens, loading/404 states or decorative pieces in…
SkillAFreshness: AClaude Code +9 - 0.539score
creative-engineering
Leostruka
Use when the user asks to apply a visual "style", "theme", or "effect" to code — frontend (CSS/GLSL), native shaders, or media processing…
SkillAFreshness: AClaude Code +9 - 0.539score
data-analyst
Leostruka
Use when the user asks to query a database, analyze data, create charts/visualizations, explore data patterns, or asks business questions about data.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- Oct 10, 2026 (18 days ago)
- Last release
- Oct 24, 2026 (4 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Leostruka/devin-bundle
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Leostruka
- 0.565score
architecture
Leostruka
Use when designing modules, seams, and adapters, when evaluating module depth and identifying deepening opportunities in a codebase, or when modernizing…
SkillAFreshness: AClaude Code +9 - 0.565score
code-review
Leostruka
Use when completing a task, reviewing a branch or PR, before merging, when the user asks to 'review since X', when publishing a GitHub PR review with inline…
SkillAFreshness: AClaude Code +9 - 0.565score
ask-bundle
Leostruka
Use when deciding which skill or flow fits your situation — the meta-router entry point for this bundle (direct specialist skills, multi-skill flows, local…
SkillAFreshness: AClaude Code +9 - 0.565score
ai-tools
Leostruka
Use when running local, offline-first ML tooling — mechanistic interpretability PoCs like refusal-direction ablation on local safetensors or the HF cache, or…
SkillAFreshness: AClaude Code +9 - 0.565score
animation-direction
Leostruka
Use when turning narrated video/audio into synced code-rendered motion graphics — narration -> timestamped transcript -> scene plan -> approval gate ->…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture-diagrams
Leostruka
Use when the deliverable is a physical diagram artifact (.svg/.png) — C4 models, dense class diagrams, network topology rendered via PlantUML.
SkillAFreshness: AClaude Code +9
Cite this page
debugging skill. Agent Mart. https://agentmart.dev/skills/leostruka-debugging (last updated 2026-10-24)