Skip to content

beifeng724/personal-workbench-skills / skills/personal-workbench-explorer

personal-workbench-explorer

Verified

Explicit-only discovery skill that analyzes the current task context and proposes 3-5 valuable personal or professional workbench ideas, comparing value, usage frequency, build difficulty, data risk, and maintenance cost. Run only when the user explicitly types $personal-workbench-explorer, /personal-workbench-explorer, or names this skill. Never invoke implicitly for general productivity advice, brainstorming, or ordinary workbench questions.

Personal Workbench Explorer

Help the user discover what durable system is worth building. Stay within context actually available in the current task; never claim access to unavailable cross-task history.

Explore

  1. Verify explicit invocation. If invocation is not explicit, do not run this workflow.
  2. Read discovery-workflow.md.
  3. Extract repeated activities, recurring friction, handoffs, scattered information, decisions, and data that should persist.
  4. Ask at most three high-value questions at a time. Prefer questions that separate candidate directions rather than collect exhaustive specifications.
  5. Generate 3-5 distinct candidate workbenches. Avoid cosmetic variants of the same idea.
  6. Score each candidate on value, frequency, implementation difficulty, data risk, and maintenance cost. Explain scores in the user's language level.
  7. Recommend a direction only when evidence supports it; otherwise identify the next experiment or observation needed.
  8. Produce a complete a structured discovery brief using brief-template.md.
  9. Stop after the brief. Do not invoke or simulate personal-workbench-builder; tell the user they may explicitly invoke it with the chosen direction.

Guardrails

  • Do not invent job duties, tools, data, or pain points absent from the current task.
  • Distinguish observed facts, user statements, and hypotheses.
  • Prefer recurring, connected workflows with persistent state over one-off automations or ordinary websites.
  • Surface sensitive-data and ongoing-maintenance implications early.
  • Keep all candidates unless the user rejects them; ranking is comparison, not silent elimination.
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: 471kUpdated 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