共 30 个 Skill。
michael-denyer/pstack-claude1.6kSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
AI 与智能体
michael-denyer/pstack-claude1.6kSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
AI 与智能体
michael-denyer/pstack-claude1.6kUse for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how the user works. Drafts or revises a personal -mode skill via plugin-dev:skill-development + unslop, optionally pulling fresh evidence from recent transcripts.
AI 与智能体
michael-denyer/pstack-claude1.6kWatch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
AI 与智能体
michael-denyer/pstack-claude1.6kVet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it. Use when you run a benchmark or report a speedup or regression you measured.
AI 与智能体
michael-denyer/pstack-claude1.6kFind what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', reviewing a small diff you don't trust, or a brief that asserts something about existing code ('make X public', 'X already handles Y') before you design against that assertion.
文档与办公
michael-denyer/pstack-claude1.6kRestate the last message in plain human language, with no jargon. Use for /bro or when asked to say it plainly.
AI 与智能体
michael-denyer/pstack-claude1.6kFind the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
测试
michael-denyer/pstack-claude1.6kGenerate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", "make a driver skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
前端开发
michael-denyer/pstack-claude1.6kmichael-denyer/pstack-claude1.6kDesign an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
AI 与智能体
michael-denyer/pstack-claude1.6kmichael-denyer/pstack-claude1.6kResolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution
测试
michael-denyer/pstack-claude1.6kmichael-denyer/pstack-claude1.6kUse for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which package owns this", "is this the right layer"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.
代码质量与审查
michael-denyer/pstack-claude1.6kUse for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
测试
michael-denyer/pstack-claude1.6kPeriodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
AI 与智能体
michael-denyer/pstack-claude1.6kPrepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
AI 与智能体
michael-denyer/pstack-claude1.6kSpawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.
AI 与智能体
michael-denyer/pstack-claude1.6kGuides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
AI 与智能体
michael-denyer/pstack-claude1.6kpoteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.
AI 与智能体
michael-denyer/pstack-claude1.6kApply when repeated fixes sharing an assumption fail. State the assumption and choose an observation that can challenge it before trying another fix that depends on it.
AI 与智能体
michael-denyer/pstack-claude1.6kApply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
AI 与智能体
michael-denyer/pstack-claude1.6kApply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
AI 与智能体
michael-denyer/pstack-claude1.6kApply when you catch yourself writing the same instruction a second time, or notice a recurring correction. Encode the rule as a lint, metadata flag, runtime check, or script instead of more text.
文档与办公
michael-denyer/pstack-claude1.6kApply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
前端开发
michael-denyer/pstack-claude1.6kApply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
前端开发
michael-denyer/pstack-claude1.6kApply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
AI 与智能体
michael-denyer/pstack-claude1.6kApply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
代码质量与审查
michael-denyer/pstack-claude1.6kApply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
文档与办公