Skill Gallery
← Back to list
CheekyCodexConjurer

agent-manager

by CheekyCodexConjurer

AERA: local-first workstation for quantitative research, visualization, and backtesting.

⭐ 0🍴 0📅 Jan 6, 2026
algorithmic-tradingalgorithmic-trading-enginequant-researchquantitative-finance
View on GitHubRun in Manus

SKILL.md

name: agent_manager description: Automatically manage agent lifecycle, proposals, and registry.

Purpose

Maintain an auto-managed registry of agents and keep their scopes current.

Steps

  1. Discover all AGENTS.md and AGENTS.override.md files.
  2. Update .agent-docs/memory/AGENTS_REGISTRY.md and .agent-docs/memory/AGENTS_REGISTRY.json.
  3. Compare coverage with .agent-docs/memory/INDEX.md and architecture maps.
  4. Propose missing agents in .agent-docs/memory/AGENT_PROPOSALS.md.
  5. Explain each proposal objective and ask for approval before scaffolding.
  6. Detect drift by comparing scope file timestamps to agent instructions.
  7. Mark needs_update, stale, or retire_candidate in the registry.
  8. For approved proposals, scaffold new agent instructions from .agent-docs/agents/AGENT_TEMPLATE.md.
  9. Record actions in the Action Log.
  10. Use the agent management checklist for completeness.

Guardrails

  • Use the merge protocol for updates.
  • Do not modify fixed agents; only propose changes.

Score

Total Score

55/100

Based on repository quality metrics

✓SKILL.md

SKILL.mdファイルが含まれている

+20
○LICENSE

ライセンスが設定されている

0/10
○説明文

100文字以上の説明がある

0/10
○人気

GitHub Stars 100以上

0/15
✓最近の活動

3ヶ月以内に更新

+5
○フォーク

10回以上フォークされている

0/5
✓Issue管理

オープンIssueが50未満

+5
✓言語

プログラミング言語が設定されている

+5
✓タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon