Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/diagnose/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thunderkds/easy-ui-mcp/diagnose)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/diagnose"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/diagnose/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/diagnose"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/diagnose.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00054 | $0.03095 |
| Opus 5.5 | $0.00022 | $0.01238 |
| Sonnet 5.5 | $0.00011 | $0.00619 |
| Haiku 4.5 | $0.00005 | $0.00310 |
Grade A, and why
diagnose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: Bug Diagnosis Specialist
A discipline for hard bugs. Skip phases only when explicitly justified. When exploring, use the project's domain vocabulary to build a clear mental model and check ADRs in the area you touch.
Karpathy Operational Commands (Specific Overrides)
- Think Before Coding: Do not hypothesise without a feedback loop (Phase 1). Generate 3–5 ranked, falsifiable hypotheses before testing any.
- Goal-Driven Execution: Turn the repro into a failing regression test before the fix, when a correct seam exists.
- Surgical Changes: Change one variable at a time. Wrap every debug log in
#region debug logmarkers so cleanup is onegrep. - Fix the root cause, never the symptom: the fix must land where the cause originated, not where the error surfaced. A fix applied at the surfacing site is a failure, not a partial success, even when the symptom disappears. A cause counts as the root cause only when the Checkpoint marked its hypothesis CONFIRMED — never when it is merely asserted.
Phase 1 — Build a feedback loop (this is the skill)
A fast, deterministic, agent-runnable pass/fail signal for the bug. Everything else just consumes it. Be aggressive; refuse to give up. Try in roughly this order:
- Failing test at whatever seam reaches the bug. 2. Curl/HTTP script against a dev server. 3. CLI invocation diffing stdout vs known-good. 4. Headless browser script. 5. Replay a captured trace/payload. 6. Throwaway harness exercising the code path. 7. Property/fuzz loop. 8. Bisection harness (
git bisect run). 9. Differential old-vs-new loop. 10. HITL bash script (last resort).
Iterate on the loop itself — faster, sharper signal, more deterministic. A 2-second deterministic loop is a debugging superpower; a 30-second flaky one is barely a loop. For non-deterministic bugs, raise the reproduction rate (loop 100×, parallelise, inject sleeps) until debuggable. If you genuinely cannot build a loop, stop and say so — list what you tried and ask the user for environment access, a captured artifact, or instrumentation permission. Do not proceed to Phase 3 without a loop.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 156 lines · 54 tokens per session scan A 5c6d70241d74
diagnose is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 3,095 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.
Other skills, from other repositories
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
reenable-test
Guide for investigating, fixing, verifying via TDD, and re-enabling disabled or flaky Chromium tests (C++, Android Java, or WebUI). Use this skill when asked to deflake, fix, or re-enable a disabled or flaky test case, or to verify post-submit stability of a re-enabled test. Don't use for disabling a failing test…
resolve-author-fix
Find the root cause, implement a focused fix, and prove behavior with targeted tests and recordings.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
validate-fix
Prove a fix works before declaring done — re-run the failing test, run the full suite, typecheck, lint, and harden against recurrence. Use after implementing a bug fix, when user says "is this fixed?", or before closing an investigation.