跳到正文
FunCoding

搜索

搜索文档、Skill 和 MCP

update-aegis

Use when the user says `aegis:update`, asks to update or upgrade an installed Aegis method-pack, wants the latest Aegis version, or asks whether Aegis is current on this host.

代码质量与审查1.3kskills/update-aegis/SKILL.md

安装

把这段话发给 Claude Code、Codex 或 Cursor。智能体会先检查安全性,你确认后才安装。

读取 https://funcoding.ai/skills/ganyuanran/aegis/update-aegis/install.md ,按里面的步骤帮我安装这个 Skill。

SKILL.md

Update Aegis

Update the installed Aegis Method Pack for the current AI coding host.

This skill is host maintenance. Do not edit the target project just because the user asked to update Aegis.

Default Semantics

  • aegis:update updates the current host's registered Aegis installation.
  • Updating every registered host requires an explicit --all request.
  • If more than one host is registered and the current host cannot be identified, ask one concrete question before updating.
  • Do not update a development checkout when the installed method-pack root is a separate path.
  • Do not perform background automatic updates. The local registry may record updateMode, but this skill only performs explicit user-triggered updates.

Evidence First

From the installed method-pack root, inspect the host-scoped registry:

python scripts/aegis-update.py status --json

If the registry is missing, register the current host before updating. Use the host's install guide and actual discovery path rather than guessing.

If ~/.config/aegis/config.toml already declares method_pack_root, prefer that canonical root when registering additional hosts. Host-specific discovery paths, copied skill directories, plugin caches, or adapter payloads should be treated as generated / host-managed views into the same Aegis body, not as separate editable checkouts.

Codex example:

python scripts/aegis-update.py register \
  --host codex \
  --sync-mode junction \
  --discovery-root ~/.agents/skills/aegis \
  --reload-hint "restart Codex"

Copy-based host example:

python scripts/aegis-update.py register \
  --host codebuddy \
  --sync-mode copy-skills \
  --discovery-root ~/.codebuddy/skills \
  --reload-hint "restart CodeBuddy"

Prefixed direct-child host example:

python scripts/aegis-update.py register \
  --host copilot \
  --sync-mode junction \
  --discovery-shape direct-child \
  --discovery-root <target-repo>/.github/skills \
  --discovery-name-prefix aegis- \
  --reload-hint "restart Copilot session or reopen the repository"

Kimi Code CLI automatic installations are plugin-managed. Do not use the Aegis updater against Kimi's managed plugin copy. In Kimi, run the native update or reinstall flow, verify the selected managed plugin, then reload:

/plugins install https://github.com/GanyuanRan/Aegis
/plugins info aegis
/reload

If Kimi requires confirmation or removal before replacing the managed copy, follow its exact plugin-manager prompt. Then locate the managed root from /plugins info aegis and run:

cd <aegis-method-pack-root>
python scripts/aegis-doctor.py --json --host-profile kimi-code-auto

Kimi Code CLI Explicit Compatibility Installation example:

python scripts/aegis-update.py register \
  --host kimi-code \
  --sync-mode junction \
  --reload-hint "restart Kimi Code CLI"

When --discovery-root is omitted for kimi, kimi-code, or kimi-code-cli, the updater uses $KIMI_CODE_HOME/skills or, when KIMI_CODE_HOME is unset, ~/.kimi-code/skills. Use this updater path only when the Aegis Kimi plugin is disabled or uninstalled and the user has selected explicit compatibility mode.

Plugin-managed hosts can be registered, but the updater reports that the host plugin manager owns the update path:

python scripts/aegis-update.py register \
  --host opencode \
  --sync-mode plugin-managed \
  --reload-hint "restart OpenCode"

Update Commands

Current or explicitly selected host:

python scripts/aegis-update.py update --host <host> --json

All registered hosts, only when the user explicitly asks for all-host update:

python scripts/aegis-update.py update --all --json

Preview without touching files:

python scripts/aegis-update.py update --host <host> --dry-run --json

If the installed checkout has local changes, do not overwrite them. Either ask the user how to proceed or, with explicit permission, preserve them with:

python scripts/aegis-update.py update --host <host> --stash --json

Completion Evidence

Treat the update as complete only when the updater reports the selected host and the post-update doctor verification succeeds. For link-based discovery roots (junction, symlink, or repo-only), the updater passes discoveryRoot through to aegis-doctor.py --discovery-root; when a registered direct-child view declares discoveryNamePrefix, the updater also passes --discovery-name-prefix. For copy-based hosts, it verifies that copied Aegis skill directories exist after the copy step, then runs doctor against the method-pack root.

When multiple registered hosts share the same methodPackRoot, the updater now reuses a single method-pack checkout update and then refreshes each host's exposure or verification path separately.

Report:

  • selected host / installation id
  • previous and final commit when available
  • whether the install was updated or already current
  • sync mode used
  • doctor verification result
  • restart or reload hint

If the updater skips a plugin-managed host, state that the host plugin manager owns the update path and give the reload or reinstall hint.

For Kimi automatic installations, completion also requires /plugins info aegis, /reload or /new, the kimi-code-auto doctor profile, and the host-native automatic-entry checks from docs/README.kimi-code.md. File discovery or a generic doctor result alone is not sufficient.

相似的 Skill

claude-api
anthropics/skills180k

claude-api

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).

代码质量与审查

ponytail-review
DietrichGebert/ponytail158k

ponytail-review

Quality review of a change: is the logic right, is it safe, does it hold under real load, is risky code tested, is it fast enough, and is every line needed. Reads the connected code, not only the diff. Each finding is explained in plain English. Use for "review this", "code review", "review the last commit", "review my PR", "is this over-engineered", /ponytail-review.

代码质量与审查

code-review-and-quality
addyosmani/agent-skills103k

code-review-and-quality

Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.

代码质量与审查

documentation-and-adrs
addyosmani/agent-skills103k

documentation-and-adrs

Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.

代码质量与审查

code-simplification
addyosmani/agent-skills103k

code-simplification

Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.

代码质量与审查

understand
Egonex-AI/Understand-Anything86k

understand

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

代码质量与审查