skill-set

Plugin skill-set from marketplace ether-plugins in ether-moon/ether-plugins. Commands read from the repo's manifest — 1 month ago.

Skills (14)

• autofixing-and-escalating

  Classifies actionable findings from linters, tests, security scans, audits, and PR reviews, automatically applies unambiguous fixes, and pauses only for decisions required by ambiguous findings before applying the complete chosen resolution. Use when processing one or more externally produced findin

• creating-skills

  Creates, revises, and evaluates agent skills. Use for SKILL.md authoring, trigger tuning, skill evaluations and benchmarks, or retirement decisions. The primary entry point when requests overlap with skill-creator.

• deliberating-with-peer-agents

  Develops designs, implementation plans, and research through parallel independent proposals, repeated peer debate, and evidence-based synthesis. Use when the user wants multiple agents or models to work on the same requirements, exchange objections over several rounds, and reach a joint proposal wit

• driving-with-tests

  Guides implementation and verification through Orient, Red/Green/Refactor, Probe, and Guard. Use for new behavior, bug fixes, refactors, test strategy, test reviews, coverage decisions, baseline checks, or requests to work test-first or practice TDD.

• grilling-plans

  Stress-tests an existing plan, RFC, design, or proposal by presenting all evidence-backed decision questions in one batch and maintaining a decision ledger. Use when a user asks to grill, challenge, sanity-check, poke holes in, or assess whether an existing plan is ready.

• guarding-agent-directives

  Reviews agent directives for necessity, clarity, scope, and authority. Use when adding, revising, or auditing rules in AGENTS.md, CLAUDE.md, or referenced instruction files.

• improving-architecture

  Finds and ranks evidence-backed deep-module and seam refactor candidates in a codebase. Use when a user asks for architecture improvement opportunities, tangled-code analysis, modularity, testability seams, deep or shallow modules, or a ranked refactor shortlist.

• managing-git-workflow

  Safely inspects repository state and executes explicitly authorized commits, pushes, and pull-request creation through a constrained runner. Use when the user asks to commit selected work, push existing commits, create or inspect a pull request, save changes in Git, or publish a branch to GitHub.

• re-explain-clearly

  Re-explains an existing explanation, passage, term, or other supplied content in clearer language when the user says they do not understand, asks what it means, or requests a simpler explanation. Use for equivalent requests in any language; do not use for drafting or revising substantive documents,

• reviewing-with-peer-agents

  Delegates technical review to independent peer agents, validates their findings, and routes actionable results through bounded autofixing and decision escalation. Use when the user explicitly asks Codex, Claude, Gemini, another model, peer LLMs, or a second opinion to review or validate work; not fo

• shipping-pr

  Drives an existing or newly requested pull request through deterministic CI, review, and blocker-resolution cycles until it is verified clean or reaches a terminal stop. Use when the user asks to ship a PR, wait for CI and fix it, run PR autopilot, or keep resolving blockers until the PR is ready.

• writing-clear-prose

  Drafts and revises substantive non-fiction such as reports, proposals, technical documents, and explanatory articles. Use when a user asks to compose or materially improve a document's clarity, structure, specificity, concision, or factual fidelity; do not use for short operational text, creative wo

• writing-korean-clearly

  Improves user-facing Korean prose by making grammar, referents, and logical relationships explicit while keeping responses concise. Use whenever the expected conversational or requested output language is Korean, alongside any task-specific skill; do not use solely because a prompt contains Korean w

• zooming-out-on-code

  Produces a compact, read-only system map of unfamiliar project code in domain vocabulary. Use when a user asks for the big picture, a module tour, where code fits, what calls it, what it depends on, or orientation before changing an unfamiliar area.

Slash commands (7)

• /skill-set:code:zoom-out

  Return a read-only five-part system map of unfamiliar code: responsibility, callers, dependencies, siblings, and unknowns.

• /skill-set:git:commit

  Create a scoped commit without pushing

• /skill-set:git:pr

  Create or find a pull request from committed changes

• /skill-set:git:push

  Push existing commits with remote SHA protection

• /skill-set:plan:grill

  Stress-test an existing plan by asking every evidence-backed decision question in one batch and maintaining a Confirmed, Rejected, and Unresolved ledger.

• /skill-set:pr:fix

  Resolve PR blockers in the current PR worktree through one publication-gated cycle

• /skill-set:pr:ship

  Ship a PR through resumable CI, review, and blocker-resolution cycles

Subagents (4)

• ci-failure-resolver

  Analyzes current-HEAD CI failures and applies authorized, unambiguous fixes in the recorded current PR worktree. Called sequentially by resolving-pr-blockers; never switches branches, pushes, or comments.

• merge-conflict-resolver

  Resolves an authorized merge conflict in the recorded current PR worktree. Called alone for a resolver cycle; never switches branches, pushes, or comments.

• pr-review-feedback

  Processes unresolved actionable PR review threads and unreviewed current-HEAD review bodies and PR issue comments in the recorded current PR worktree. Returns queued publication content; never switches branches, pushes, comments, or resolves threads itself.

• resolving-pr-blockers

  Resolves one authorized PR-blocker cycle in the current PR worktree, then performs a single publication gate. Use for explicit PR fix requests or when shipping-pr delegates a blocked snapshot.