SkillsAdd

smithery/nguyenthienthanh

bugfix-quick

Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.

Installation

$ npx skills add smithery/nguyenthienthanh --skill bugfix-quick
View on skills.sh ↗ Website ↗

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

frontend-design Same topic
anthropics/skills

Guidance for distinctive, intentional visual design when building new UI or reshaping an existi…

866.4K installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

810.4K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills 697.8K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

617.3K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

576.5K installs
azure-diagnostics Same topic
microsoft/azure-skills

Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe …

568.9K installs

Also in this package

Other skills from smithery/nguyenthienthanh.

npx skills add smithery/nguyenthienthanh
session-continuation 0 scalable-thinking 0 design-expert 0

Browse all from smithery/nguyenthienthanh

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Skill metadata

Parsed from SKILL.md frontmatter.

Allowed toolsRead, Grep, Glob, Edit, Write, Bash

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,698 B
  • docs SUMMARY.md 97 B

History

  1. First recorded snapshot · 0 installs

SKILL.md

AI-consumed reference. Optimized for Claude to read during execution.
Human-readable explanation: see [docs/architecture/HIERARCHICALPLANNING.md](../../../docs/architecture/HIERARCHICALPLANNING.md)
or [docs/getting-started/](../../../docs/getting-started/) depending on topic.

Quick Bugfix

For bugs only. Features/refactors → run-orchestrator.

Core Principle

NO FIXES WITHOUT ROOT CAUSE. Fix at SOURCE, not symptom.

Process (4 Steps)

Step Name Agent Statusline
S1 Investigate lead (inline) — uses Read/Grep/Bash to reproduce bugfix S1
S2 Test RED tester — writes failing test bugfix S2
S3 Fix GREEN architect / frontend / mobile (per artifact, via agent-detector) bugfix S3
S4 Verify tester — runs full suite bugfix S4

Announce per step. When transitioning, surface to the user: ─── Step S{N} · {Name} ─── Dispatching {agent}…. Also update run-state.json#currentstep (one of: investigate, test-red, fix-green, verify) and #activeagent so the statusline reflects reality.

1. Investigate

  • Read error + stack trace
  • Reproduce the bug
  • git log / git diff for recent changes
  • Trace backward: where did bad data originate?
  • Context economy (rules/core/context-economy.md) — Grep for the failing symbol first, then Read with offset+limit on the matched lines only. Don't read the full file unless the bug spans it.

2. Write Failing Test (RED)

  • Test that reproduces the bug exactly
  • Pick the right layer (skills/test-writer/SKILL.md#test-type-selection). If the bug is a UI / user-flow / auth / payment regression → e2e spec via Playwright MCP, not a unit test that won't actually reproduce it. If the bug is in pure logic → unit. The test must fail for the right reason.
  • User confirms test FAILS

3. Fix (GREEN)

  • Minimal, focused change at root cause
  • User confirms test PASSES

4. Verify

  • Run full test suite — and the e2e suite if S2 wrote an e2e spec (npx playwright test / npx cypress run). No regressions in either.
  • Read output, THEN claim result. "Tests passed" with no pass count = 0 tests collected = bug.
  • Wrong: "Should work now" / Right: "Tests pass: [output]"

Red Flags (Return to Step 1)

"Quick fix for now" / "Just try changing X" / "It's probably X" / "Seems fixed"

Output

## Bug Fix: [Description]
**Root Cause:** [Why — traced to source]
**Test Added:** [file + test name]
**Fix Applied:** [file + change summary]
**Verification:** Tests pass, no regressions

If complex → switch to run-orchestrator.

Escalation: If the bug resists quick fix (intermittent, race condition, "works on my machine", multiple plausible causes), escalate to skills/deep-debugging/SKILL.md for scientific-method root-cause analysis.

Related Rules

  • rules/core/tdd-workflow.md — Failing test before fix
  • rules/core/verification.md — Run tests, read output, then claim
  • rules/core/execution-rules.md — Root-cause discipline
  • rules/core/simplicity-over-complexity.md — Minimal fix at root cause, no speculative refactoring during bug fix