Debug

Skill sssstwee/tastedistill/plugins/tastedistill/claude-skills/debug

Local-first memory and workflow plugin for AI coding agents: Codex, Claude Code, agent preferences, project lessons, and delivery rules.

Install

npx -y skills add sssstwee/tastedistill --skill debug

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Diagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.

SKILL.md

2.7 KB, as published. Nobody here has run it

Debug: Prove The Cause

Use this skill when the task starts from a symptom.

Prefix your first response line with ⚗️ inline, not as its own paragraph.

Before the workflow, apply ../../shared-rules/personalization.md for explicit TasteD/TasteDistill invocations. Apply ../../shared-rules/runtime-hygiene.md when debugging uses helper scripts, browser checks, local servers, screenshots, traces, or other generated artifacts.

Outcome Contract

Outcome: proven root cause, minimal fix or handoff, and verification evidence.
Done when: every observed symptom fits the explanation and the fix is checked by a reproducible test or runtime observation.
Evidence: repro steps, logs, traces, state, source paths, generated artifacts, tests, screenshots, and command output.

Workflow

List the observed symptoms.
Reproduce the issue or define the missing evidence.
Trace from symptom to source.
State a one-sentence root-cause hypothesis with evidence.
Make the smallest fix that addresses the cause.
Run the narrow regression check.
Search for the same bug shape if the root cause is reusable.

Coding Guardrails

For fixes, apply ../../shared-rules/coding-guardrails.md:

Think before coding: do not edit until the root-cause hypothesis is specific and evidence-backed.
Simplicity first: fix the cause directly; avoid broad rewrites, new abstractions, or speculative compatibility.
Surgical changes: keep the patch to the failure path; search siblings only for the same bug shape.
Goal-driven execution: prove the original symptom changed with a reproducible check.

CodeGraph

For root-cause analysis in a Git repository, ../../shared-rules/personalization.md should already have ensured the local CodeGraph index. When codegraph_* tools are available, prefer codegraph_trace for "how does X reach Y", codegraph_callers / codegraph_callees for one-hop flow, and codegraph_context for nearby implementation context. Read target files directly before editing.

Stop Rules

Same symptom after a fix means the hypothesis failed.
Do not stack patches without new evidence.
Do not claim UI, native, or generated-artifact bugs are fixed from compile output alone.
If the fix expands into a refactor, pause and name the scope change.

Output Shape

Root cause:
Fix:
Confirmed:
Tests:
Regression guard:
Remaining risk: