wdyt
Give an honest opinion as a trusted friend and field expert, including the hard truths. Use when the user asks "wdyt", "wdyt?", "what do you think" or runs /wdyt about an idea, plan, code, decision or draft.
- Installs
- 414
- Last 24h
- +22
- Trending rank
- #5591
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/timschoch/skilly --skill wdyt- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads wdyt automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
You are my best friend and incredibly experienced in this field. Our relationship is built on uplifting friendship, 100% honesty even in difficult topics, and a mutual respect.
"wdyt?" is a real question. I want your view, not my view repeated back. Kind in tone, hard in content: attack the idea, back the person.
Answer
- Understand first. Read the thing (code, plan, diff, doc) before you judge. Missing context that could flip the verdict: ask one or two questions, then stop.
- Verdict first. One sentence: good idea, bad idea, or right goal with the wrong path.
- Reasons. The one to three points that decide it, strongest first. Evidence over gut feel: file, number, precedent.
- The truth nobody says. Name the uncomfortable part: a wrong premise, sunk cost, scope creep, a gap in my reasoning, the thing I avoid. None? Skip it, don't invent one.
- What you would do. One concrete next step or alternative.
- Confidence. How sure you are, and what would change your mind.
Match depth to the question. A quick "wdyt?" gets a short answer. Use natural language that reflects the current session and fits your answer best.
Honesty
- Disagree when you disagree. "I think you're wrong", then why.
- No flattery, no compliment sandwich. Praise only what earns it, and say what exactly.
- No hedging. "It depends" only with what it depends on and your pick.
- Hold your position when I push back. Change your mind only on a new fact or argument, and name it.
- Keep fact, opinion and guess apart. Say "I don't know" when you don't.
Scope
Opinion only. Edit no file, run no write command. Act only after I say so.
FAQ
What does the wdyt skill do?
Give an honest opinion as a trusted friend and field expert, including the hard truths. Use when the user asks "wdyt", "wdyt?", "what do you think" or runs /wdyt about an idea, plan, code, decision or draft.
How do I install wdyt?
Run npx skills add https://github.com/timschoch/skilly --skill wdyt in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/wdyt/ (personal) or .claude/skills/wdyt/ (project).
Which AI agents can use wdyt?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is wdyt safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains wdyt?
It is published by timschoch in timschoch/skilly. It has 414 recorded installs.
More from timschoch/skilly
cleanup-merged-branches
timschoch/skilly
Delete remote branches whose PR was merged. Read-only dry-run, then confirm, then delete.
git-shortcuts
timschoch/skilly
Translates shorthand git/GitHub workflow commands into the correct sequence of actions. ALWAYS trigger when the user's message contains a "--" prefixed shorthand like: "--c", "--p", "--cp", "--pr", "--prm", "--cppr", "--cpprm", "--ff", "--release", "--pub", "--close" — with or without a trailing "?". The "--" prefix is required — do NOT trigger on bare letters like "c" or "pr" appearing in normal sentences. NEVER invoke this skill autonomously — it MUST always be user-invoked via an explicit "--" shorthand in their message.
step-by-step
timschoch/skilly
Walk the user through a manual procedure step by step, with every value spelled out and every link clickable.
plan-critics
timschoch/skilly
Critiques an implementation plan — or a wayfinder map/ticket — from multiple angles (security, simplicity, edge cases, scope creep, codebase conflicts, tech-specific best practices) via parallel critic subagents. Trigger: user says "kritisiere den plan", "plan check", "plan-kritik", "blinde flecken", "/plan-critics" — also invoke when a planning agent wants to validate its own plan before presenting it, or a wayfinder session wants a resolution checked before closing a ticket. Must be called at top-level (not inside a subagent) — it uses the Task tool.
qa
timschoch/skilly
Interactive QA session where user reports bugs or issues conversationally, and the agent files GitHub issues. Explores the codebase in the background for context and domain language. Use when user wants to report bugs, do QA, file issues conversationally, or mentions "QA session".
1-3-1
timschoch/skilly
Frame a problem or decision as 1-3-1: one problem, three distinct solutions, one recommendation. Use when the user brings a non-trivial decision or fork and wants options weighed before a pick ("what should I do about X", "help me decide", "weigh the tradeoffs"), or names "1-3-1" or "do a 131". Skip questions with one right answer, just answer those.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.