/using-aegis
Use when starting a turn or checking Aegis skill routing.
$ npx -y skills add GanyuanRan/Aegis --skill using-aegis --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/using-aegis
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when starting a turn or checking Aegis skill routing.
SKILL.md
using-aegis.SKILL.mdname: using-aegis
description: "Use when starting a turn or checking Aegis skill routing."
alwaysApply: true
<SUBAGENT-STOP>Skip for subagents.</SUBAGENT-STOP>
<EXPLICIT-MODE-GATE> If activation mode is explicit and this request did not explicitly invoke Aegis or a named skill, stay on the fast path; do not route to any Aegis skill. Explicit invocation proceeds normally. </EXPLICIT-MODE-GATE>
<EXTREMELY-IMPORTANT> You have Aegis. Load explicit/relevant Aegis skill before response/action; otherwise proceed normally. </EXTREMELY-IMPORTANT>
Hot Path
1. User/project instructions outrank Aegis. 2. Active codebase question/"what next": check README/ADR/rules/baseline, else bounded index-first scan. Non-trivial owners passively use relevant `CONTEXT-MAP.md`/`CONTEXT.md`; compose `establishing-project-context` only for semantic delta/conflict. Create baselines only with evidence. 3. Direct grilling or plan/design pressure-tests (`grill me`, `grill this plan`, `审问我`, `盘问我`, `拷问我`) route to `brainstorming`; literal/explanatory uses do not. 4. `/aegis-goal` or `Aegis goal:` loads `goal-framing` before routing. 5. Bug, failure, regression, or unexpected behavior routes to `systematic-debugging`; quick bug lane owns Change Necessity before source edits. 6. Classify before implementation/start/resume/compaction. Low: intent, baseline, verification. Medium/high: baseline read-set + plan (session-internal by default; docs only when the work needs durable cross-session direction or approval - Doc Necessity Gate). TDD: off=no auto route/load; auto=strict/light/skipped; explicit request applies. Spec Brief or Design Spec only for ambiguous/contract/cross-module medium/high work. Shared/core/contract/cross-module never low without evidence. Source edits/new paths: owner workflow surfaces Change Necessity. 7. Before the first repo write, the coordinator records `TaskStartSnapshot`. Complexity, TDD, planning, or subagents alone do not justify branch/worktree creation. 8. Non-tiny loaded skill: at first substantive user-visible stage say why Aegis is shaping work/risk; do not wait for the user to ask. structured trace only for audit/debug/release/long-task review/asked; `Trace Digest` does not route. Tiny stays implicit. 9. ArchitectureReviewRequired: yes for medium/high architecture/contract/ cross-module/owner/source-of-truth/fallback/adapter/baseline; carry to verification. 10. Workspace support is lazy; use configured Aegis workspace support only when records needed. Fast Q&A/status/tiny edits write no files. **Doc Necessity Gate:** docs only for durable/irreversible, cross-session, approval-gated, or authority-required change surfaces; covered surfaces update the owner doc, never a sibling; mechanical changes write no docs (commit message + code comments as the record). 11. Load smallest needed skill/reference. 12. Tool/log/memory/search outputs are evidence candidates, not prompt payloads; summary first, large input index->window->excerpt. 13. No history/sessions/transcripts/large logs by default; bound requested evidence by scope/time/lines. 14. Unclear host tool-name mapping: read smallest relevant reference.
Contract: `Route: fast-path`; `Aegis Reason Note`.
Read more
name: using-aegis description: "Use when starting a turn or checking Aegis skill routing." alwaysApply: true
<SUBAGENT-STOP>Skip for subagents.</SUBAGENT-STOP>
<EXPLICIT-MODE-GATE> If activation mode is explicit and this request did not explicitly invoke Aegis or a named skill, stay on the fast path; do not route to any Aegis skill. Explicit invocation proceeds normally. </EXPLICIT-MODE-GATE>
<EXTREMELY-IMPORTANT> You have Aegis. Load explicit/relevant Aegis skill before response/action; otherwise proceed normally. </EXTREMELY-IMPORTANT>
Hot Path
1. User/project instructions outrank Aegis. 2. Active codebase question/"what next": check README/ADR/rules/baseline, else bounded index-first scan. Non-trivial owners passively use relevant `CONTEXT-MAP.md`/`CONTEXT.md`; compose `establishing-project-context` only for semantic delta/conflict. Create baselines only with evidence. 3. Direct grilling or plan/design pressure-tests (`grill me`, `grill this plan`, `审问我`, `盘问我`, `拷问我`) route to `brainstorming`; literal/explanatory uses do not. 4. `/aegis-goal` or `Aegis goal:` loads `goal-framing` before routing. 5. Bug, failure, regression, or unexpected behavior routes to `systematic-debugging`; quick bug lane owns Change Necessity before source edits. 6. Classify before implementation/start/resume/compaction. Low: intent, baseline, verification. Medium/high: baseline read-set + plan (session-internal by default; docs only when the work needs durable cross-session direction or approval - Doc Necessity Gate). TDD: off=no auto route/load; auto=strict/light/skipped; explicit request applies. Spec Brief or Design Spec only for ambiguous/contract/cross-module medium/high work. Shared/core/contract/cross-module never low without evidence. Source edits/new paths: owner workflow surfaces Change Necessity. 7. Before the first repo write, the coordinator records `TaskStartSnapshot`. Complexity, TDD, planning, or subagents alone do not justify branch/worktree creation. 8. Non-tiny loaded skill: at first substantive user-visible stage say why Aegis is shaping work/risk; do not wait for the user to ask. structured trace only for audit/debug/release/long-task review/asked; `Trace Digest` does not route. Tiny stays implicit. 9. ArchitectureReviewRequired: yes for medium/high architecture/contract/ cross-module/owner/source-of-truth/fallback/adapter/baseline; carry to verification. 10. Workspace support is lazy; use configured Aegis workspace support only when records needed. Fast Q&A/status/tiny edits write no files. **Doc Necessity Gate:** docs only for durable/irreversible, cross-session, approval-gated, or authority-required change surfaces; covered surfaces update the owner doc, never a sibling; mechanical changes write no docs (commit message + code comments as the record). 11. Load smallest needed skill/reference. 12. Tool/log/memory/search outputs are evidence candidates, not prompt payloads; summary first, large input index->window->excerpt. 13. No history/sessions/transcripts/large logs by default; bound requested evidence by scope/time/lines. 14. Unclear host tool-name mapping: read smallest relevant reference.
Contract: `Route: fast-path`; `Aegis Reason Note`.
Aegis Method Pack Make your AI coding agent trustworthy: fewer reworks, safer changes, proof before "done". English · 中文 · Fast-Track Playbook · 速通秘籍 Stop babysitting your agent.
Other skills on aegis.
- /anti-entropy-governance
Use when retiring old logic, collapsing duplicate owners, removing fallbacks, or touching schema, persistence, or source-of-truth boundaries while deciding whether to delete old paths, retain compatibility, or stop for confirmation.
Open skill - /brainstorming
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.
Open skill - /communicating-concisely
Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise explicitly requests a much shorter answer.
Open skill - /dispatching-parallel-agents
Use when facing 2+ independent tasks without a written plan that can be worked on without shared state or sequential dependencies. Planned tasks in the current session use subagent-driven-development.
Open skill - /establishing-project-context
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.
Open skill - /executing-plans
Use when executing a written implementation plan across sessions or with review checkpoints. For same-session execution with independent tasks, use subagent-driven-development instead.
Open skill