GanyuanRan@Aegis

GanyuanRan@Aegis from gabrielmoreira/agent-skills-mirror.

by @gabrielmoreira 22 skills 2 authors

Skills in this plugin

22
  1. ▌
    Using Aegis · ganyuanran bundle
    Routes requests to Aegis skills based on intent, loading relevant skills for debugging, planning, and goal framing while keeping fast-path responses lightweight.
    1.4k repo stars
  2. ▌
    Goal Framing · gabrielmoreira
    Frames tasks with explicit goals, success evidence, stop conditions, and boundaries before execution, then routes work to the appropriate workflow.
    20 repo stars
  3. ▌
    Brainstorming · ganyuanran bundle
    Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture choices, contract changes, or when grilling/pressure-testing a plan or design. Routine small requests stay on the fast path.
    1.4k repo stars
  4. ▌
    Update Aegis · gabrielmoreira
    Updates the installed Aegis Method Pack on the current AI coding host, including registration, dry-run previews, and post-update verification.
    20 repo stars
  5. ▌
    Writing Plans · ganyuanran bundle
    Use when you have an approved spec or written requirements for a multi-step task that needs a durable plan document before touching code. Small, single-owner, or fast-path tasks do not need this skill.
    1.4k repo stars
  6. ▌
    Writing Skills · ganyuanran bundle
    Use when creating new skills, editing existing skills, or verifying skills work before deployment
    1.4k repo stars
  7. ▌
    Executing Plans · ganyuanran
    Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice plans stay inline. For same-session independent tasks, use subagent-driven-development instead.
    1.4k repo stars
  8. ▌
    Using Git Worktrees · ganyuanran
    Use when a coding task needs a concurrent checkout, unrelated dirty state blocks safe branch switching, or the user or repository explicitly requires a worktree.
    1.4k repo stars
  9. ▌
    Systematic Debugging · ganyuanran bundle
    Use when encountering a bug, test failure, or unexpected behavior, before proposing fixes
    1.4k repo stars
  10. ▌
    Receiving Code Review · ganyuanran
    Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky, disputed, or technically questionable.
    1.4k repo stars
  11. ▌
    Long Task Continuation · ganyuanran
    Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.
    1.4k repo stars
  12. ▌
    Requesting Code Review · ganyuanran bundle
    Use when requesting independent code review, after implementation slices, before merging high-risk work, or when verification exposes evidence, baseline, architecture, compatibility, or retirement uncertainty.
    1.4k repo stars
  13. ▌
    Anti Entropy Governance · ganyuanran
    Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.
    1.4k repo stars
  14. ▌
    Communicating Concisely · ganyuanran
    Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
    1.4k repo stars
  15. ▌
    First Principles Review · ganyuanran
    Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints, fallback growth, duplicate owners, or architecture direction risk. Ordinary bug fixes stay on the fast path.
    1.4k repo stars
  16. ▌
    Test Driven Development · ganyuanran bundle
    Use when the user explicitly requests strict or test-first TDD, or when the current conversation already contains an explicit `TDD Route: strict` decision from another Aegis workflow.
    1.4k repo stars
  17. ▌
    Dispatching Parallel Agents · ganyuanran
    Use when facing 2+ independent tasks without a written plan, with no shared state or sequential dependencies, where parallel delegation beats inline cost; otherwise inline. Planned tasks use subagent-driven-development.
    1.4k repo stars
  18. ▌
    Subagent Driven Development · ganyuanran bundle
    Use when executing a written implementation plan with independent tasks in the current session where delegation beats inline coordination cost; otherwise inline. Ad-hoc 2+ tasks without a plan use dispatching-parallel-agents.
    1.4k repo stars
  19. ▌
    Establishing Project Context · ganyuanran bundle
    Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
    1.4k repo stars
  20. ▌
    Finishing A Development Branch · ganyuanran
    Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly requests merge, PR, or branch lifecycle handling.
    1.4k repo stars
  21. ▌
    Verification Before Completion · ganyuanran bundle
    Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.
    1.4k repo stars
  22. ▌
    Recording Architecture Decisions · ganyuanran
    Use when the user asks to create, write, update, amend, supersede, or evaluate an ADR, architecture decision record, durable architecture decision, decision log, or baseline sync after architecture-changing work.
    1.4k repo stars