diagnose
Investigate unexpected behavior and mysterious bugs. Use when the cause of a problem is unknown and the user needs to understand WHY something is happening — symptoms like: sudden unexplained changes in metrics or behavior, works locally but not in staging/production, inconsistent or intermittent failures, correct code producing wrong results, operations succeeding but having no effect, environment-specific failures, duplicate executions, stale data, or any \"why did this change?\" or \"why is this happening?\" situation. Covers infrastructure anomalies (cache hit rates dropping, latency spikes, queue behavior shifts) as well as code bugs. The key signal is confusion about root cause, not a request to implement a known fix. Do NOT use for feature requests, known fixes, planning, or documentation tasks.
git clone --depth 1 https://github.com/avibebuilder/claude-prime /tmp/diagnose && cp -r /tmp/diagnose/.claude/skills/diagnose ~/.claude/skills/diagnoseSKILL.md
Think harder. ## Process Check conversation context and skip completed steps. ### 1. Understand the symptom - Read the bug report, errors, logs, and surrounding code carefully - Clarify reproduction steps, expected behavior, and environment when they are unclear - **Separate confirmed facts from working assumptions.** List them explicitly: - `Fact (confirmed):` the server returns 200 - `Assumption (unconfirmed):` the client receives the full HTML body Misidentifying an assumption as a fact is the most common source of wasted investigation. ### 2. Build hypotheses - Form 2-4 plausible root-cause hypotheses that are **mechanistically distinct** — different failure layers (e.g., server render vs. client hydration vs. network layer), not variations of the same idea - Rank them by likelihood - For each hypothesis, state both sides: - `Confirm if:` [what observation would prove this is the cause] - `Eliminate if:` [what observation would rule this out] A hypothesis you can't falsify in both directions is too vague to test. ### 3. Choose the lightest evidence method Start with the cheapest source of truth that can kill hypotheses: - existing logs, traces, stack traces, metrics, and error output - static code inspection around the suspected path - config, environment, deploy, cache, queue, and permissions state that could explain the symptom - targeted reproduction in the relevant environment Only add new instrumentation when existing evidence is insufficient. - If you need runtime probes, read `diagnose/references/runtime-debugging.md` - Use `#region agent log` / `#endregion` markers for any instrumentation you add - Tag each log point with the relevant `hypothesisId` - Log only the minimum fields needed to discriminate between hypotheses; never log secrets, tokens, passwords, cookies, or full sensitive payloads - If runtime probes require starting the local debug server, ask the user before launching it - For browser/UI bugs, combine with the `agent-browser` skill when reproduction or inspection needs it ### 4. Gather evidence and iterate - Use existing logs, traces, failing tests, or artifacts before asking for a fresh reproduction - When reproduction is needed, ask the user to trigger the bug — tie each request to the hypothesis it tests - Correlate each finding with the hypothesis it supports or eliminates; narrow based on evidence, not confidence - If ambiguity remains, refine hypotheses and add narrower probes — but stop and report when another round is unlikely to produce new discriminating evidence ### 5. Report the diagnosis Output structured diagnosis: ``` ## Diagnosis: [Issue Title] ### Symptoms - [What was observed] ### Evidence - [Finding] — `file:line` or runtime source — hypothesis X - ... ### Root Cause [Confirmed or most likely cause, with evidence] ### Hypotheses Tested | # | Hypothesis | Confirm if | Eliminate if | Result | |---|-----------|-----------|-------------|--------| | A | ... | [what observation would prove this] | [what observation would rule this out] | Confirmed/Eliminated/Inconclusive | ### Recommended Next Steps - [What to do next — usually hand off to `/fix` with this diagnosis] ### Active Instrumentation - [List files with `#region agent log` blocks still in place, or `None`] ``` ## Constraints - NO fixing — investigation and diagnosis only. "Recommended Next Steps" hands off to `/fix` with the diagnosis; it does **not** prescribe specific parameter values, code snippets, or step-by-step implementation instructions. - Evidence over assumptions — if the code looks wrong but runtime evidence says otherwise, trust the runtime - If you add `#region agent log` blocks, leave them in place for `/fix` to verify the repair and call them out in the final report ## Bug <bug>$ARGUMENTS</bug>
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Answer questions about code, architecture, and technical decisions — no implementation. Trigger on questions asking 'why', 'what does this do', 'what is the purpose of', 'explain', 'what's the difference', 'compare', or 'what are the tradeoffs' — even when referencing specific files, code snippets, or inline code. The key signal is the user wants to UNDERSTAND something, not change it. Do NOT trigger for requests to build, fix, plan, review, research, or add/modify code.
Implement, build, create, or add any feature, endpoint, page, component, or functionality. Use this skill whenever the user asks you to write new code or make code changes — whether it's adding an API endpoint, building a UI page, creating an export feature, wiring up a webhook, implementing a search/filter, or any other hands-on coding task. This is the default skill for all 'build this', 'add this', 'create this', 'wire up', 'implement' requests. Covers the full cycle: clarify requirements, plan if needed, write code, verify, and review. Do NOT use for pure research, debugging, documentation, or explanation — only when the user wants working code delivered.
Use when the user wants to save knowledge as a file so others don't have to rediscover it — \"turn this into a doc\", \"write this up\", \"document how X works\", \"we figured this out and want to capture it\", \"nobody should have to figure this out again\". Covers any request to create or update durable written artifacts: onboarding guides, runbooks, ADRs, API docs, architecture notes, postmortems, changelogs, setup guides. The trigger: user wants knowledge captured in a file for future reference, not just a conversation. Do NOT use when still making decisions (→ give-plan), just asking for explanation without a file (→ ask), or writing code (→ cook).
Brainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for a decision they're facing: 'discuss', 'debate', 'brainstorm', 'weigh options', 'tradeoffs', 'should I do X or Y', 'help me decide', 'I'm torn between', 'sanity check my thinking', or 'what do you think about'. The user must be asking for help reasoning through a choice — not asking to build, fix, evaluate, plan, or modify something (even if the topic involves this skill itself). Picks the right decision lens, surfaces tradeoffs and blind spots, pushes back when reasoning is genuinely weak, and never implements.
Fetch up-to-date documentation for any library, framework, API, or service into context. Use when the user wants to look up API references, check function signatures or required fields, find feature-specific docs, or verify how an external tool actually works. Triggers for queries about third-party libraries like Stripe, SQLAlchemy, Tailwind, FastAPI, shadcn, Drizzle, Hono, Better Auth — any time the answer lives in official docs rather than in the project codebase. Use this instead of guessing from trained knowledge, which is stale.
Fix bugs and broken behavior when there is enough evidence to act on a repair path. Use for errors, crashes, incorrect results, API failures (500, 404, 403), CORS problems, database exceptions, broken rendering, duplicated or wrong data, off-by-one mistakes, timezone/date bugs, broken forms, config-caused runtime failures, and regressions. Trigger when the user wants the bug repaired and the conversation already contains a clear failing area, a reproducible failing test, a concrete error path, or a prior diagnosis to implement. Do NOT use for new features, pure explanation, architecture discussion, broad research, or bug reports where the main need is figuring out why the behavior happens — use diagnose for that.
Builds distinctive, production-grade UIs that avoid generic AI aesthetics. Use whenever the user wants to build, restyle, or give visual direction to any interface — pages, dashboards, landing pages, components, onboarding flows, mobile screens, or design systems — even without an explicit 'design' request. Also triggers for: picking an aesthetic direction, improving the look of a dull/generic existing page, adding visual personality, or choosing colors/typography. Includes a bundled design intelligence database for concrete guidance across web (React, Next.js, Vue, Tailwind) and mobile (React Native, Flutter, SwiftUI).