debug
A check fails or behavior is wrong and the cause isn't obvious — reproduce, isolate the root cause, fix narrowly, and prove it.
Skill by bryan824
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/bryan824-debug
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: productivity
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/debug
What's inside
- Skill name
debug- Description
- A check fails or behavior is wrong and the cause isn't obvious — reproduce, isolate the root cause, fix narrowly, and prove it.
- License
- MIT
- Instructions
- 35 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Debug Find the causal defect, not just a patch that hides the symptom. - Capture a pass/fail signal for the reported behavior. Preserve the original scenario while shrinking a reproduction; the small case must still explain it. For intermittent failures, record conditions and observed frequency instead of imposing an arbitrary flake threshold. If reproduction is unavailable, seek decisive traces and name what remains unproven. - Trace callers, state, guards, sinks and configuration. Compare known-good behavior and recent changes when available. Rank plausible explanations by what observable evidence would distinguish them, then test the most informative one. Change one causal variable at a time where possible. - Keep probes identifiable. Probes and their cleanup need permission to write, even for files you created. An approved tool call does not widen which files you may change. Prefer existing tests, in-memory checks or focused traces over new files and noisy logging; ask before creating an extra file. Measure performance against a comparable baseline. Redact secrets before sharing commands, logs or artifacts, and say when redaction limits diagnosis. - Fix the shared cause where it belongs and inspect sibling callers. Do not compensate separately in every path or keep retrying an unchanged theory. Repeated failure calls for a new hypothesis, decomposition or escalation—not a success verdict because an attempt budget ran out. - Re-run the exact original signal and relevant regression checks. Assert the visible result, not merely that nothing threw. Inspect the real rendered/output surface for visual or generated-artifact bugs; synthetic checks alone leave that requirement unverified. If no honest test seam exists, report the design gap. Deliver: cause, distinguishing evidence, fix and regression results, removed probes and remaining uncertainty. Hand the uncommitted change to independent verification. Keep a durable lesson in its existing owner only when it changes current guidance; no mandatory debug diary.
From bryan824/kirin-pi, MIT.
More from bryan824/kirin-pi
- 0.567score
design
bryan824
When intent or consequential choices are unclear — resolve goals, boundaries, contracts, and an approved direction before building.
SkillAFreshness: AClaude Code +9 - 0.567score
harness
bryan824
When maintaining, assessing or redesigning the agent harness itself — skills, agents, extensions, hooks, tools, setup, docs and tests — or absorbing upstream…
SkillAFreshness: AClaude Code +9 - 0.567score
write-skill
bryan824
Creating, revising, or cleaning a skill — keep one useful mindset, a discriminating trigger, and only guidance that earns its context cost.
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-design
bryan824
When creating, restyling, or holistically reviewing web UI — set a coherent aesthetic direction, coordinate its design disciplines, and build or assess the…
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-motion
bryan824
When deciding whether a frontend interaction benefits from motion, or designing or reviewing state, enter/exit, and gesture motion — make movement purposeful…
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-polish
bryan824
When refining component surfaces, elevation, optical alignment, icons, or finish after the structure is sound — remove distracting detail while preserving the…
SkillAFreshness: AClaude Code +9 - 0.567score
rust
bryan824
When writing, refactoring, testing, or configuring Rust — follow Bryan's toolchain, error-handling, crate, API-design, and structure preferences and the…
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-color
bryan824
When defining, changing, or reviewing UI color tokens, themes, contrast, gamut, or light/dark/increased-contrast appearances — preserve semantic meaning and…
SkillAFreshness: AClaude Code +9 - 0.565score
architecture
bryan824
When structure is the problem — improve an existing architecture without changing its goals, or rethink it from first principles when the user explicitly asks.
SkillAFreshness: AClaude Code +9 - 0.565score
teach
bryan824
When the user explicitly wants a guided lesson or course — teach a focused session in chat by default, with a persistent learning workspace only on request.
SkillAFreshness: AClaude Code +9 - 0.561score
frontend-layout
bryan824
When shaping or reviewing a frontend's spatial structure—grouping and aligning content, setting reading order, adapting a component to its container, or…
SkillAFreshness: AClaude Code +9 - 0.561score
frontend-writing
bryan824
When product UI needs words that help someone choose, recover, or complete a flow — make UX copy disappear through clear, consistent, localization-safe…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 3, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bryan824/kirin-pi
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bryan824
- 0.567score
frontend-design
bryan824
When creating, restyling, or holistically reviewing web UI — set a coherent aesthetic direction, coordinate its design disciplines, and build or assess the…
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-motion
bryan824
When deciding whether a frontend interaction benefits from motion, or designing or reviewing state, enter/exit, and gesture motion — make movement purposeful…
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-color
bryan824
When defining, changing, or reviewing UI color tokens, themes, contrast, gamut, or light/dark/increased-contrast appearances — preserve semantic meaning and…
SkillAFreshness: AClaude Code +9 - 0.567score
harness
bryan824
When maintaining, assessing or redesigning the agent harness itself — skills, agents, extensions, hooks, tools, setup, docs and tests — or absorbing upstream…
SkillAFreshness: AClaude Code +9 - 0.567score
write-skill
bryan824
Creating, revising, or cleaning a skill — keep one useful mindset, a discriminating trigger, and only guidance that earns its context cost.
SkillAFreshness: AClaude Code +9 - 0.567score
frontend-polish
bryan824
When refining component surfaces, elevation, optical alignment, icons, or finish after the structure is sound — remove distracting detail while preserving the…
SkillAFreshness: AClaude Code +9
Cite this page
debug skill. Agent Mart. https://agentmart.dev/skills/bryan824-debug (last updated 2026-10-24)