Skip to content

staruhub/ClaudeSkills / skills/Geek-skills-deep-research

deep-research

Verified

Use this skill when the user wants an evidence-based research memo, literature review, market/policy/technical landscape, or a multi-source decision brief with citations, trade-offs, and a clear conclusion. Best for tasks that need synthesis across multiple external sources, iterative follow-up research, or a reusable written artifact. Do not use for quick factual lookups, single-source summaries, simple Q&A, summarizing one document the user already provided, plan-only requests where the user explicitly defers the actual research, or when the user wants a short answer with no need for cited evidence (a short but evidence-backed conclusion is still a brief memo, which this skill covers). Chinese trigger examples: "帮我调研", "深度研究", "综述报告", "技术选型分析", "竞品研究", "政策分析".

evals/runbook.md

View on GitHub
# Evals Runbook V8

Use this folder to keep routing and output checks close to the skill.

## Minimal loop
1. Run a routing slice (`routing-evals.json`)
2. Run a few representative output cases
3. Compare with the previous skill version or a simple no-skill baseline
4. Record failures in `run-summary.json` and promote important failures into new eval cases

## What to test
- should-trigger prompts
- should-not-trigger prompts
- short brief memo tasks
- full report tasks
- delta / follow-up tasks
- high-stakes tasks that require stronger grounding

## Mode assertions
Cases with `expected_mode` also assert the P0 orchestration choice (brief / full / delta) after triggering.
A case fails if the skill triggers correctly but picks a different mode.
Cases without `expected_mode` only assert trigger / no-trigger.

## Ground rule
Do not declare V8 better because one demo looked nicer.
Treat it like code: compare runs, check artifacts, and look for regressions.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall