systematic-debugging
Use when encountering any bug, test failure, build failure, or unexpected behavior before proposing fixes.
Skill by leo110047
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/leo110047-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: documents, testing, productivity, agent-building
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 encountering any bug, test failure, build failure, or unexpected behavior before proposing fixes. Prefer the Goldband investigate workflow for full root-cause work. This portable skill only defines the shared debugging contract used by both hosts.
- License
- MIT
- Instructions
- 56 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
# Systematic Debugging Shared debugging policy. The Goldband investigate workflow owns full investigation. A fix requires a stated observed symptom, reproduction path, and evidence source. ## Scope Investigate a concrete defect before proposing its fix. During a review-only request, verify and report findings without changing code. A bug report or keyword does not authorize implementation or override the user's task. ## Gotchas - A fix attempt is a completed corrective action based on a stated root-cause hypothesis, followed by relevant verification. - Inspection and reruns without a corrective action do not count; neither do tool, sandbox, or permission failures that prevent the action from completing or verification from running. - After two consecutive attempts under the same hypothesis leave the same verification blocked by the same failure class, stop editing and return to diagnosis. Cosmetic output changes do not reset the count; a different failure class or new evidence-backed hypothesis does. - The first plausible cause is a hypothesis; compare against working versions and recent changes. - A non-reproducible issue requires more diagnostics, not a guess. - Urgency does not waive root-cause work. ## Workflow Handoff Use the investigate workflow, when installed, for multi-component failures, production incidents, flaky tests, unclear ownership, or work that needs a written investigation record. Use this skill alone for small local failures or when the workflow is not installed. ## Required Sequence 1. Reproduce the issue and capture the exact failure. 2. Gather concrete evidence from errors, logs, diffs, configs, tests, or runtime state before proposing a fix. 3. Form one root-cause hypothesis. 4. Apply the healthiest complete fix that addresses that root cause and reduces recurrence risk. 5. Verify with the command, test, or runtime path that proves the issue is fixed. ## Evidence Requirements - Exact failure text or observed behavior. - Reproduction command or path. - Evidence for the chosen root cause. - Fix summary tied to that root cause. - Verification command and result.
From leo110047/goldband, MIT.
More from leo110047/goldband
- 0.566score
claude-config-verification
leo110047
Use when modifying the goldband config repo across Claude Code or Codex assets (`skills/`, `hooks/`, `commands/`, `rules/`, `claude/`, `.claude-plugin/`…
SkillAFreshness: AClaude Code +9 - 0.566score
freeze-mode
leo110047
Use when you need a read-only investigation window for production or sensitive systems and want Claude blocked from non-read-only tools plus non-read-only…
SkillAFreshness: AClaude Code +9 - 0.563score
careful-mode
leo110047
Use before running destructive or prod-facing CLI commands.
SkillAFreshness: AClaude Code +9 - 0.563score
goldband
leo110047
Route Goldband tasks through the formal capability interface for review, investigation, QA, planning, browser, design, safety, context, knowledge…
SkillAFreshness: AClaude Code +9 - 0.560score
evidence-based-coding
leo110047
Ground code, configuration, and completion claims in evidence for the current candidate and relevant environment.
SkillAFreshness: AClaude Code +9 - 0.560score
subagent-development
leo110047
Use when a task can be isolated into a fresh-context subagent or parallelized safely, and its result needs review against the original requirements.
SkillAFreshness: AClaude Code +9 - 0.560score
ci-cd-integration
leo110047
Use when setting up or changing CI pipelines, GitHub Actions workflows, build/test/deploy gates, release automation, CI secrets handling, or build caching.
SkillAFreshness: AClaude Code +9 - 0.560score
prompt-hygiene
leo110047
Use when creating or editing prompts, system prompts, agent instructions, workflow prompts, cron prompts, briefing prompts, design-tool prompts…
SkillAFreshness: AClaude Code +9 - 0.560score
security-checklist
leo110047
Use when working on authentication, authorization, input validation, secret handling, sensitive data storage, API hardening, deployment security, or security…
SkillAFreshness: AClaude Code +9 - 0.560score
planning-workflow
leo110047
Use when turning a request into an implementation plan, especially before multi-file changes, refactors, or work that needs explicit phases and verification.
SkillAFreshness: AClaude Code +9 - 0.560score
frontend-design
leo110047
Use when creating, restyling, or reviewing frontend pages, components, dashboards, tools, posters, artifacts, or application screens.
SkillAFreshness: AClaude Code +9 - 0.560score
performance-optimization
leo110047
Use for slowness or memory pressure, performance claims, and changes to bulk processing, materialization, caching, or parallel execution where workload growth…
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 5
- Last commit (this folder)
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/leo110047/goldband
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from leo110047
- 0.566score
freeze-mode
leo110047
Use when you need a read-only investigation window for production or sensitive systems and want Claude blocked from non-read-only tools plus non-read-only…
SkillAFreshness: AClaude Code +9 - 0.566score
claude-config-verification
leo110047
Use when modifying the goldband config repo across Claude Code or Codex assets (`skills/`, `hooks/`, `commands/`, `rules/`, `claude/`, `.claude-plugin/`…
SkillAFreshness: AClaude Code +9 - 0.563score
goldband
leo110047
Route Goldband tasks through the formal capability interface for review, investigation, QA, planning, browser, design, safety, context, knowledge…
SkillAFreshness: AClaude Code +9 - 0.563score
careful-mode
leo110047
Use before running destructive or prod-facing CLI commands.
SkillAFreshness: AClaude Code +9 - 0.560score
ci-cd-integration
leo110047
Use when setting up or changing CI pipelines, GitHub Actions workflows, build/test/deploy gates, release automation, CI secrets handling, or build caching.
SkillAFreshness: AClaude Code +9 - 0.560score
subagent-development
leo110047
Use when a task can be isolated into a fresh-context subagent or parallelized safely, and its result needs review against the original requirements.
SkillAFreshness: AClaude Code +9
Cite this page
systematic-debugging skill. Agent Mart. https://agentmart.dev/skills/leo110047-systematic-debugging (last updated 2026-10-24)