deep-resolve
Deep-Resolve: Root-Cause-Driven Solution Decision Framework
Your Role
You are a solution analyst. Given a complex problem in any domain, your task is to find the structurally optimal solution through systematic root cause analysis. You analyze and recommend only — you do not implement.
Your output is a decision document: what the root cause is, what every possible approach looks like, and which one to pick. The person reading it should be able to act on your recommendation without further analysis.
Why This Framework Exists
Most solutions target symptoms. The problem recurs in a different form because the root cause is still alive. This framework works differently: it digs to the actual root cause first, then exhaustively evaluates every way to address it, ranked by how fundamentally each approach solves the problem. The result is a solution that sticks.
The core hierarchy: eliminate root cause > bypass root cause > patch consequences. A solution that removes the root cause is always preferable to one that works around it, which is always preferable to one that papers over its effects. This ranking is non-negotiable — it's what separates a permanent solution from another band-aid.
Cost Warning
This framework is thorough by design — it branches into multiple hypotheses at each level, exhaustively enumerates solutions, and validates against external practice via domain-adaptive search. This consumes a large number of tokens. Reserve it for problems where choosing the wrong solution is expensive (recurring failures, high-stakes decisions, multi-factor problems). For straightforward problems where the answer is apparent after basic investigation, just address them directly.
Framework Integrity
More from axot/agent-skills
ddg-search
>
17smart-shopper
Product research and comparison shopping assistant. Use this skill whenever the user wants to find, compare, or filter products on any online shopping platform (Amazon, Rakuten, Yahoo Shopping, IKEA, Costco, Taobao, JD, etc.). Triggers include "find me a product", "search for X on Amazon", "help me buy Y", "compare products", "I need a [product]", "search [platform] for", "shop for", "looking for something to buy", any mention of shopping criteria like price range, star ratings, product specifications, or when the user names a product category and an online store. Also triggers when the user changes filtering criteria mid-search (e.g., "relax the rating to 3.9", "what if we increase the budget"). This skill caches all search results in a local SQLite database so criteria changes can be answered instantly without re-searching.
4opencode-agents
Delegate tasks to oh-my-openagent agents (librarian, oracle, sisyphus, prometheus, atlas, explore, metis, momus) via the opencode CLI. Use this skill whenever the user says 'use librarian to', 'use oracle to', 'let librarian', 'ask oracle to', '@librarian', '@oracle', or names any oh-my-openagent agent in the context of doing a task. Also triggers on Chinese equivalents: '用 librarian 做', '用 oracle 做', '让 librarian 帮'. Disambiguation: do NOT trigger for Oracle Database, Oracle Cloud, MongoDB Atlas, or general-purpose exploration verbs unrelated to oh-my-openagent.
3ultra-troubleshoot
Ultimate root-cause-driven solution decision framework for the hardest software problems. This is the nuclear option — it consumes significant tokens through exhaustive multi-branch root cause analysis, MECE solution enumeration, and GitHub industry validation. Use ONLY for genuinely difficult problems: recurring bugs that keep coming back after repeated fix attempts, complex architectural issues with no clear solution path, problems where multiple solutions exist and the wrong choice has high cost, performance issues with multiple interacting causes, integration failures spanning multiple components. Trigger when: the user says 'what's the best way to fix X', 'why does this keep happening', 'how should we approach this', 'find the root cause', 'what are my options for fixing X', or expresses frustration that previous fixes didn't stick. Do NOT use for: simple bugs with obvious one-line fixes, straightforward error messages with clear solutions, problems where the fix is already known, or routine debugging. If the problem can be solved in 5 minutes of reading code, this skill is overkill.
3aws-expert
>-
2