원클릭으로 Manus에서 모든 스킬 실행

시작하기

using-aegis

스타11

포크2

업데이트2026년 7월 3일 04:39

Use when starting a turn or checking Aegis skill routing.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

gabrielmoreira

gabrielmoreira/agent-skills-mirror

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

파일 탐색기

7 개 파일

SKILL.md

readonly

name	using-aegis
description	Use when starting a turn or checking Aegis skill routing.

Skip for subagents.

You have Aegis. Load explicit/relevant Aegis skill before response/action; otherwise proceed normally.

Hot Path

User/project instructions outrank Aegis.
Active codebase question/"what next": check baselines (README/ADR/rules/docs/aegis/baseline), else bounded index-first scan. Create baselines only with evidence.
/aegis-goal or Aegis goal: loads goal-framing before routing.
Bug, failure, regression, or unexpected behavior routes to systematic-debugging; quick bug lane owns Change Necessity before source edits.
Classify before implementation/start/resume/compaction. Low: intent + baseline check + TDD Route + verification. Medium/high: baseline read-set + plan. TDD Route auto=strict/light/skipped; off=no auto, verification stays. Spec Brief or Design Spec only for complexity, ambiguity, contracts, or cross-module impact. Contract/shared/core/cross-module changes are never low without evidence. Source edits/any new source-code path: owner workflow surfaces Change Necessity.
Aegis Reason Note / Visibility Non-Omission: if Aegis skill is loaded and not tiny fast-path, first substantive user-visible stage gives one natural sentence: why Aegis is shaping the task + quality risk reduced; do not wait for user to ask where Aegis was used. Tiny fast-path may stay implicit. structured trace only for audit/debug/release/long-task review/asked; Trace Digest on-demand. Trace does not route; behavior/owner skill route first.
Mark ArchitectureReviewRequired: yes for medium/high architecture, contract, cross-module, owner, source-of-truth, fallback/adapter, or project-baseline tasks; carry to verification-before-completion.
Workspace support is lazy; use configured Aegis workspace support only when records needed. Fast Q&A/status/tiny edits write no files.
Load smallest needed skill/reference.
Tool/log/memory/search outputs are evidence candidates, not prompt payloads; summary first; large inputs use bounded index->window->excerpt.
No historical sessions/transcripts/history.jsonl/.codex/sessions/~/.claude/projects/large logs by default; read requested evidence with scope/time/line bounds.
Unclear host tool-name mapping: read smallest relevant reference.

Contract: Route: fast-path; Aegis Reason Note.

이 저장소의 다른 Skills

같은 저장소

executing-plans

gabrielmoreira/agent-skills-mirror

Use when you have a written implementation plan to execute in a separate session with review checkpoints

2026-07-0411

verification-before-completion

gabrielmoreira/agent-skills-mirror

Use when about to claim work is complete, fixed, passing, verified, release-ready, or ready to commit, merge, publish, or hand off.

2026-07-0411

claw-orchestrator

gabrielmoreira/agent-skills-mirror

Manage persistent coding sessions across Claude Code, Codex, Gemini, Cursor, and OpenCode engines. Use when orchestrating multi-engine coding agents, starting/sending/stopping sessions, running multi-agent council collaborations, cross-session messaging, ultraplan deep planning, ultrareview parallel code review, autoloop autonomous workspace iteration, ultraapp building deployable web apps from a structured Q&A interview, switching models/tools at runtime, or exposing the orchestrator's 65 tools as an MCP server to Hermes Agent / Claude Desktop / Cursor / Cline / Continue / Zed / Windsurf / Goose. Triggers on "start a session", "send to session", "run council", "ultraplan", "ultrareview", "autoloop", "ultraapp", "Forge tab", "build a web app", "one-click app", "AppSpec", "autonomous iteration", "iterate until goal", "deep paper review", "auto research", "switch model", "multi-agent", "coding session", "session inbox", "cursor agent", "opencode", "mcp server", "clawo-mcp", "hermes mcp", "model context protocol

2026-07-0311

baoyu-wechat-summary

gabrielmoreira/agent-skills-mirror

Summarizes WeChat group chat highlights into a structured digest using the local wx-cli binary (https://github.com/jackwener/wx-cli). Generates a normal digest by default; a roast (毒舌) version is opt-in. Maintains per-group history (history.json + history-digests.jsonl), per-user profiles, and per-group fact memory (memory.md) across runs, with privacy guardrails baked in. Use when the user asks to "总结群聊", "群聊精华", "群聊摘要", "summarize group chat", "group chat digest", mentions a WeChat group name with a time range, says "帮我看看 XX 群最近聊了什么", "XX 群有什么值得看的", or asks to "回溯画像" / "初始化画像" / "backfill profiles". Adds the roast version when the user says "毒舌版", "roast 版", "再来个毒舌的", or similar.

2026-07-0311

systematic-debugging

gabrielmoreira/agent-skills-mirror

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

2026-07-0211

test-driven-development

gabrielmoreira/agent-skills-mirror

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.

2026-07-0211

name	using-aegis
description	Use when starting a turn or checking Aegis skill routing.

Skip for subagents.

You have Aegis. Load explicit/relevant Aegis skill before response/action; otherwise proceed normally.

Hot Path

User/project instructions outrank Aegis.
Active codebase question/"what next": check baselines (README/ADR/rules/docs/aegis/baseline), else bounded index-first scan. Create baselines only with evidence.
/aegis-goal or Aegis goal: loads goal-framing before routing.
Bug, failure, regression, or unexpected behavior routes to systematic-debugging; quick bug lane owns Change Necessity before source edits.
Classify before implementation/start/resume/compaction. Low: intent + baseline check + TDD Route + verification. Medium/high: baseline read-set + plan. TDD Route auto=strict/light/skipped; off=no auto, verification stays. Spec Brief or Design Spec only for complexity, ambiguity, contracts, or cross-module impact. Contract/shared/core/cross-module changes are never low without evidence. Source edits/any new source-code path: owner workflow surfaces Change Necessity.
Aegis Reason Note / Visibility Non-Omission: if Aegis skill is loaded and not tiny fast-path, first substantive user-visible stage gives one natural sentence: why Aegis is shaping the task + quality risk reduced; do not wait for user to ask where Aegis was used. Tiny fast-path may stay implicit. structured trace only for audit/debug/release/long-task review/asked; Trace Digest on-demand. Trace does not route; behavior/owner skill route first.
Mark ArchitectureReviewRequired: yes for medium/high architecture, contract, cross-module, owner, source-of-truth, fallback/adapter, or project-baseline tasks; carry to verification-before-completion.
Workspace support is lazy; use configured Aegis workspace support only when records needed. Fast Q&A/status/tiny edits write no files.
Load smallest needed skill/reference.
Tool/log/memory/search outputs are evidence candidates, not prompt payloads; summary first; large inputs use bounded index->window->excerpt.
No historical sessions/transcripts/history.jsonl/.codex/sessions/~/.claude/projects/large logs by default; read requested evidence with scope/time/line bounds.
Unclear host tool-name mapping: read smallest relevant reference.

Contract: Route: fast-path; Aegis Reason Note.