diagnose
Disciplined diagnosis loop for hard bugs and performance regressions.
Skill by safzanpirani
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/safzanpirani-diagnose
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: testing
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
diagnose- Description
- Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
- License
- unknown
- Instructions
- 114 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (2)
- SKILL.md
- hitl-loop.template.sh · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from safzanpirani/personal-agent-skills
- 0.599score
bun-native
safzanpirani
Bun 1.4+ native API reference so agents stop adding dependencies Bun already replaces.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
papercuts
safzanpirani
A tiny "papercuts" CLI tool that agents can use to complain about bullshit they encounter during work, like dead-end tool calls, broken links, or other…
SkillAFreshness: A★ 3Claude Code +9 - 0.564score
bun-tui
safzanpirani
Make a Bun/TS command-line tool's output look designed — the render layer, in the house style used by `qb` and `see`.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
bun-cli
safzanpirani
Build a single-purpose CLI tool in Bun + TypeScript, in the house style used by `fleet`, `qb` and `see` — pure core, thin frontends, injected dependencies…
SkillBFreshness: B★ 3Claude Code +9 - 0.560score
astcomp
safzanpirani
Deobfuscate and verify JavaScript with a bundled CLI.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
agent-controller-review
safzanpirani
Audits and hardens long-lived subprocess controllers that combine JSON-RPC, persistent run state, live control, and terminal interfaces.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
dlss5-feeder-nr
safzanpirani
Runs still images and videos through the DLSS 5 Neural Rendering feeder on Safzan's Windows RTX host, validates the output, and optionally builds comparisons.
SkillBFreshness: B★ 3Claude Code +9 - 0.551score
personal-skill-sync
safzanpirani
Reconciles Safzan's shared personal agent skills from the canonical public repository into `.agents` and Claude links while preserving runtime-specific…
SkillBFreshness: B★ 3Claude Code +9 - 0.523score
handoff
safzanpirani
Compact the current conversation into a handoff document for another agent to pick up.
SkillBFreshness: B★ 3Claude Code +9 - 0.509score
code-refactor-review
safzanpirani
Reviews code changes for reuse, composition, codebase consistency, and slop.
SkillCFreshness: C★ 3Claude Code +9 - 0.484score
grill-with-docs
safzanpirani
Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as…
SkillCFreshness: C★ 3Claude Code +9 - 0.479score
grill-me
safzanpirani
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillCFreshness: C★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 15, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- 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.
- 0.578score
diagnose
javimosch
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: B★ 56Claude Code +9 - 0.378score
diagnose
VoDaiLocz
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 28Claude Code +9 - 0.363score
diagnose
Sarthib7
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillAFreshness: A★ 10Claude Code +9 - 0.325score
diagnose
fimoklei
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 42Claude Code +9 - 0.324score
diagnose
coder
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 29Claude Code +9 - 0.324score
diagnose
mphinance
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 29Claude Code +9 - 0.319score
diagnose
valorisa
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 17Claude Code +9 - 0.303score
diagnose
deepaktiwari09
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.301score
diagnose
cskwork
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: B★ 1Claude Code +9 - 0.297score
diagnose
tuananh4865
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillBFreshness: BClaude Code +9 - 0.294score
diagnose
saitarrun
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 5Claude Code +9 - 0.294score
diagnose
saitarrun
Disciplined diagnosis loop for hard bugs and performance regressions.
SkillCFreshness: C★ 4Claude Code +9
More from safzanpirani
- 0.599score
bun-native
safzanpirani
Bun 1.4+ native API reference so agents stop adding dependencies Bun already replaces.
SkillAFreshness: A★ 3Claude Code +9 - 0.596score
papercuts
safzanpirani
A tiny "papercuts" CLI tool that agents can use to complain about bullshit they encounter during work, like dead-end tool calls, broken links, or other…
SkillAFreshness: A★ 3Claude Code +9 - 0.564score
bun-tui
safzanpirani
Make a Bun/TS command-line tool's output look designed — the render layer, in the house style used by `qb` and `see`.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
bun-cli
safzanpirani
Build a single-purpose CLI tool in Bun + TypeScript, in the house style used by `fleet`, `qb` and `see` — pure core, thin frontends, injected dependencies…
SkillBFreshness: B★ 3Claude Code +9 - 0.560score
astcomp
safzanpirani
Deobfuscate and verify JavaScript with a bundled CLI.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
dlss5-feeder-nr
safzanpirani
Runs still images and videos through the DLSS 5 Neural Rendering feeder on Safzan's Windows RTX host, validates the output, and optionally builds comparisons.
SkillBFreshness: B★ 3Claude Code +9
Cite this page
diagnose skill. Agent Mart. https://agentmart.dev/skills/safzanpirani-diagnose (last updated 2026-10-24)