all publishers

yansircc

@yansircc source repo

22 published skills

  1. ▌
    Rtk · yansircc bundle
    Use when you need to run, inspect, or participate in roundtable-kernel sessions through the bundled `rtk` runtime. Covers autonomous runs, live chair/critic handoff, durable session truth, and common commands such as `help`, `show`, `wait`, `next`, and `apply`.
    3 repo stars
  2. ▌
    Spike · yansircc
    Minimum viable loop validation — before committing to a complex task, identify the core assumption and build the smallest possible falsifiable experiment. Throwaway, isolated, single-point penetration. Triggers: spike, minimum loop, preflight, tracer, verify first, feasibility check. Should also be proactively suggested when facing complex tasks with unverified core assumptions.
    3 repo stars
  3. ▌
    Debate · yansircc
    Adversarial debate — spawn an agent team with opposing positions to converge on truth through falsification
    3 repo stars
  4. ▌
    Negate · yansircc
    Negation mode — test whether a conclusion can survive counter-argumentation
    3 repo stars
  5. ▌
    Pickup · yansircc
    Quickly pick up a project and understand the current development state
    3 repo stars
  6. ▌
    Essence · yansircc
    Compression mode — output the shortest generative program of the problem. Derive, don't retrieve.
    3 repo stars
  7. ▌
    Rethink · yansircc
    Informed reset mode — redesign with known information to break anchoring bias
    3 repo stars
  8. ▌
    Refactor · yansircc
    Analyze and optimize code following software engineering best practices
    3 repo stars
  9. ▌
    CI Review · yansircc
    Configure CI-based AI PR review in GitHub Actions with Claude Code and/or OpenAI Codex. Includes agent setup, auth/config, review execution, output filtering, and PR comment posting. Triggers: ci review, code review CI, setup review workflow, ai review pipeline.
    3 repo stars
  10. ▌
    Codex CLI · yansircc
    OpenAI Codex CLI command reference for building executable codex commands
    3 repo stars
  11. ▌
    Interview · yansircc
    Co-creation mode — AI uses structured questioning to help users sharpen vague ideas
    3 repo stars
  12. ▌
    Claude CLI · yansircc
    Claude CLI command reference for building executable claude commands
    3 repo stars
  13. ▌
    Greenfield · yansircc
    Activate code hygiene mode — eliminate dead code and keep the codebase lean with every change
    3 repo stars
  14. ▌
    Less Is More · yansircc
    Less Is More: Addition by Subtraction
    3 repo stars
  15. ▌
    Pawl Foreman · yansircc bundle
    AI agent foreman — orchestrate multi-step tasks and supervise agents using pawl. Supports Claude Code / Codex mixing. Triggers: orchestrate, supervise, foreman, start working, assign work.
    3 repo stars
  16. ▌
    Publish Skill · yansircc
    Guide for packaging and publishing skills to a Claude Code plugin marketplace. Use when users say "publish skill", "publish to marketplace", "add skill to marketplace", "package skill as plugin", or "distribute skill".
    3 repo stars
  17. ▌
    Skill Creator · yansircc
    Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
    3 repo stars
  18. ▌
    Buyer Discovery · yansircc bundle
    Discover evidence-backed B2B buyer organizations and contact actions for a product and target market using agent-authored search strategy, DataForSEO search, Cloudflare crawl evidence, site classification gates, relation judgment, contact extraction, lead action planning, and a read-only Node/Svelte progress UI. Use when Codex needs to find, dedupe, crawl, screen, visualize, or export potential overseas B2B buyer organizations, source sites, contact facts, or outreach actions for a seller.
    3 repo stars
  19. ▌
    Claude Delegate · yansircc bundle
    Delegate a bounded task to a local Claude-compatible CLI runtime through a stable adapter that returns normalized JSON plus durable artifacts.
    3 repo stars
  20. ▌
    Effect Ecosystem · yansircc bundle
    Use when a task directly changes or reviews Effect v4 code, Effect configuration, Layers, runtimes, Schema, or Effect ecosystem APIs, or explicitly requests an Effect compliance scan. Do not trigger merely because a repository depends on Effect or for unrelated UI, prose, CSS, or ordinary TypeScript changes.
    3 repo stars
  21. ▌
    Learn From Mistakes · yansircc bundle
    Record mistakes from bug fixes so agents never repeat them. Auto-validates on write. Triggers: learn from mistake, record mistake, remember this bug, don't repeat.
    3 repo stars
  22. ▌
    Sm · yansircc bundle
    Manage the local SM skill registry, Producer-owned skill artifacts, Agent grants, immutable projections, and the Svelte dashboard. Use when an agent needs to inspect, add, generate, update, publish, authorize, build, apply, verify, or troubleshoot skills governed by ~/.sm for Codex, Claude, or Pi, or when the user asks to open or show the skill-management page so they can inspect or operate it themselves.
    3 repo stars