diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions.
Skill by tt-a1i
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/tt-a1i-diagnosing-bugs
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
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
diagnosing-bugs- Description
- Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
- License
- MIT
- Instructions
- 135 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (3)
- SKILL.md
- openai.yaml · agents/
- hitl-loop.template.sh · scripts/
More from tt-a1i/matt-skills-with-to-goal
- 0.699score
to-goal
tt-a1i
Turn approved planning evidence or partially completed work into a portable, verifiable execution goal.
SkillBFreshness: B★ 187Claude Code +9 - 0.699score
execute-spec-in-fork
tt-a1i
Orchestrate approved, bounded work through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions…
SkillBFreshness: B★ 187Claude Code +9 - 0.699score
goal-crafter
tt-a1i
Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an…
SkillBFreshness: B★ 187Claude Code +9 - 0.695score
spec-executor
tt-a1i
Execute approved, bounded work in an isolated implementation conversation and return a structured evidence receipt.
SkillBFreshness: B★ 187Claude Code +9 - 0.695score
roundtable
tt-a1i
Convene a roundtable of sub-agents that debate a decision or proposal from opposing perspectives — parallel independent statements, anonymous cross-review…
SkillBFreshness: B★ 187Claude Code +9 - 0.622score
grilling
tt-a1i
Grill the user relentlessly about a plan, decision, or idea.
SkillAFreshness: A★ 187Claude Code +9 - 0.619score
to-tickets
tt-a1i
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker…
SkillAFreshness: A★ 187Claude Code +9 - 0.619score
improve-codebase-architecture
tt-a1i
Scan a codebase for deepening opportunities, present them as a report — HTML on request — then grill through whichever one you pick.
SkillAFreshness: A★ 187Claude Code +9 - 0.619score
triage
tt-a1i
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
SkillAFreshness: A★ 187Claude Code +9 - 0.619score
handoff
tt-a1i
Compact the current conversation into a portable handoff document, with an optional live clarification path for compatible Codex tasks.
SkillAFreshness: A★ 187Claude Code +9 - 0.616score
ask-matt
tt-a1i
Ask which skill or flow fits your situation.
SkillAFreshness: A★ 187Claude Code +9 - 0.584score
codebase-design
tt-a1i
Shared vocabulary for designing deep modules.
SkillBFreshness: B★ 187Claude Code +9
Signals
- Stars
- 187
- Forks
- 21
- Open issues
- 7
- Last commit (this folder)
- Oct 7, 2026 (21 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.750score
diagnosing-bugs
mattpocock
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 302.4KClaude Code +9 - 0.393score
diagnosing-bugs
mrclrchtr
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 103Claude Code +9 - 0.362score
diagnosing-bugs
dengmuming
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 7Claude Code +9 - 0.361score
diagnosing-bugs
caterpi11ar
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 8Claude Code +9 - 0.351score
diagnosing-bugs
transitive-bullshit
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 4Claude Code +9 - 0.350score
diagnosing-bugs
KenSuh
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 3Claude Code +9 - 0.345score
diagnosing-bugs
Hop-Syder
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 3Claude Code +9 - 0.340score
diagnosing-bugs
little3tar
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.337score
diagnosing-bugs
SwiftyJunnos
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.337score
diagnosing-bugs
dhruvsaxena1998
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.337score
diagnosing-bugs
mattweihl
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9 - 0.337score
diagnosing-bugs
tuliopaim
Diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 1Claude Code +9
More from tt-a1i
- 0.837score
simplify-codebase
tt-a1i
Simplification audit or authorized codebase simplification whose stated objective is to remove accidental complexity.
SkillAFreshness: A★ 88.7KClaude Code +9 - 0.837score
archify
tt-a1i
Create validated architecture, workflow, sequence, data-flow, lifecycle/state, ERD, class, tree, timeline, and waterfall diagrams as explorable standalone…
SkillAFreshness: A★ 88.7KClaude Code +9 - 0.834score
archify-tuning
tt-a1i
Improve Archify diagram accuracy, visual quality and complete authoring speed with fewer repairs.
SkillAFreshness: A★ 88.7KClaude Code +9 - 0.823score
archify-review
tt-a1i
Review Archify issues, PRs, or code through value, cost, and impact to support evidence-based maintenance decisions.
SkillAFreshness: A★ 88.7KClaude Code +9 - 0.699score
execute-spec-in-fork
tt-a1i
Orchestrate approved, bounded work through a same-directory Codex App fork: create and name the execution task, ask it to run spec-executor, route decisions…
SkillBFreshness: B★ 187Claude Code +9 - 0.699score
goal-crafter
tt-a1i
Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an…
SkillBFreshness: B★ 187Claude Code +9
Cite this page
diagnosing-bugs skill. Agent Mart. https://agentmart.dev/skills/tt-a1i-diagnosing-bugs (last updated 2026-10-24)