← all publishers

shiwenbin1617

@shiwenbin1617 source repo

Report this profile Claim this profile

• 27 skills
• 0 followers
• 5 hours ago last updated

1. ▌
   Setup Pstack 2 · shiwenbin1617

   Configure optional per-role model preferences for pstack on Codex. Use for $setup-pstack or requests to change pstack model routing.
   0
   installs
2. ▌
   Setup Pstack 3 · shiwenbin1617

   Configure which Claude Code models pstack uses per role. Use for /setup-pstack or requests to change pstack model routing.
   0
   installs
3. ▌
   How · shiwenbin1617 bundle

   Explain code flow, subsystem architecture, or ownership and layering. Use why for historical rationale.
   0
   installs
4. ▌
   Why · shiwenbin1617 bundle

   Investigate design rationale, regressions, or historical tradeoffs using cited evidence. Use how for runtime behavior.
   0
   installs
5. ▌
   Arena · shiwenbin1617

   Spawn 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.
   0
   installs
6. ▌
   Swarm · shiwenbin1617

   Fan out N parallel workers, drain them, and return one report. Use for /swarm, 'swarm this', or parallel coverage, races, gauntlets, and exploration.
   0
   installs
7. ▌
   Recall · shiwenbin1617 bundle

   Recover recent work and open decisions from relevant task history when the user asks to recall or resume work.
   0
   installs
8. ▌
   Unslop · shiwenbin1617

   Edit prose to remove filler, canned phrasing, and unnecessary jargon while preserving the author's meaning and voice.
   0
   installs
9. ▌
   Reflect · shiwenbin1617 bundle

   Review a completed task for reusable lessons when the user requests reflection or workflow improvements.
   0
   installs
10. ▌
    Architect · shiwenbin1617 bundle

    Design types, interfaces, and module ownership for a requested architectural change or an unresolved design choice.
    0
    installs
11. ▌
    Automate Me · shiwenbin1617

    Use 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 from the authoring-a-skill playbook + unslop, optionally pulling fresh evidence from recent transcripts.
    0
    installs
12. ▌
    Interrogate · shiwenbin1617 bundle

    Use 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.
    0
    installs
13. ▌
    No Comments · shiwenbin1617

    Review and simplify comments or suppressions within a requested code scope.
    0
    installs
14. ▌
    Poteto Mode · shiwenbin1617 bundle

    Use the pstack workflow when the user explicitly invokes /poteto-mode or requests poteto's style for a task.
    0
    installs
15. ▌
    Setup Pstack · shiwenbin1617

    Configure which models pstack uses per role. Detects the model values this session actually accepts and writes a config file the other pstack skills read. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.
    0
    installs
16. ▌
    Figure It Out · shiwenbin1617

    Plan and execute a complex task when existing playbooks do not cover its dependencies or completion criteria.
    0
    installs
17. ▌
    Show Me Your Work · shiwenbin1617 bundle

    Keep a reviewable decision log for a requested audit or a long-running task that needs a durable handoff.
    0
    installs
18. ▌
    Technical Writing · shiwenbin1617

    Write or edit technical documents, RFCs, and PR descriptions for a clear audience and purpose.
    0
    installs
19. ▌
    Principle Prove It Works · shiwenbin1617

    Choose evidence that verifies the changed behavior and supports the completion claim.
    0
    installs
20. ▌
    Create Verification Skill · shiwenbin1617 bundle

    Generate 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", or when a project has no scripted way to prove UI/CLI/service behavior.
    0
    installs
21. ▌
    Principle Build The Lever · shiwenbin1617

    Choose reusable automation when repeated work or deterministic verification justifies a script or codemod.
    0
    installs
22. ▌
    Typescript Best Practices · shiwenbin1617 bundle

    Guide TypeScript type design, boundary validation, and type-safety reviews when implementing or changing TypeScript code.
    0
    installs
23. ▌
    Maintain Verification Skill · shiwenbin1617

    Periodic 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".
    0
    installs
24. ▌
    Setup Benny · shiwenbin1617

    Configure Benny and prepare its triage and repro automations. Use when installing Benny or changing its Slack, tracker, repository, routing, control, model, or budget settings.
    0
    installs
25. ▌
    Principle Guard The Context Window · shiwenbin1617

    Reduce unnecessary context from repeated reads, large outputs, and duplicated delegation.
    0
    installs
26. ▌
    Principle Never Block On The Human · shiwenbin1617

    Continue authorized work autonomously and ask only for decisions or permissions that materially affect the outcome.
    0
    installs
27. ▌
    Reproduce And Fix Issues · shiwenbin1617 bundle

    Reproduce triaged Slack bugs through a configured app-control adapter, verify existing fixes, and open a bounded draft pull request only after before-and-after proof. Use only from the configured Benny repro automation.
    0
    installs