All Recommendations — Development skill for Claude Code
Launch a team of implementation agents to apply ALL recommended changes from the most recent review — every severity level (Critical, High, Medium, Low), one agent per file, with false-positive valida.
How to install All Recommendations
Installs to ~/.claude/skills/capitalthought-multipov-docs-all-recommendations/SKILL.md
mkdir -p ~/.claude/skills/capitalthought-multipov-docs-all-recommendations && curl -fsSL https://raw.githubusercontent.com/capitalthought/multipov-docs/HEAD/skills/all-recommendations.md -o ~/.claude/skills/capitalthought-multipov-docs-all-recommendations/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What All Recommendations does
name: all-recommendations description: Launch a team of implementation agents to apply ALL recommended changes from the most recent review — every severity level (Critical, High, Medium, Low), one agent per file, with false-positive validation baked in.
All Recommendations — Batch-Implement Every Review Finding
Launch a team of agents to implement ALL recommended changes from the most recent review — every severity level (Critical, High, Medium, Low). Input: `$ARGUMENTS` (path to a r
Alternatives in Development
- Obsidian Health — Run a vault health check — grouped by severity, detects contradictions, concept gaps, stale claims, and struct 277 ★
- CLAUDE.md Additions — Turbo-recommended additions for ~/.claude/CLAUDE.md 263 ★
- Incident Commander — Incident Commander - structured incident response with severity assessment and blameless post-mortems 127 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
05 Cleanup
Safe dead code cleanup - detect and remove unused imports and dead files with auto-apply for Low/Medium risk
Bt MCP Tools
列出宝塔 MCP 协议的 98 个工具(按 19 类分组),给出风险等级(low/medium/high)和参数签名。当 Agent 已接入 baota-mcp 后需要选择合适工具时使用。
Paper Reader
A Claude Code skill for critical paper reading: 4 modes (deep-read, quick-scan, recommend, lit-review) with ev
Competitive Pulse
Get an instant competitive intelligence briefing — recent moves, positioning shifts, new threats, and recommen
Dawn
Morning briefing — composes /arcanea-status + /pulse + /sis recent + last handover's recommended next stack in
Ad Attack Paths
Launch the ad-attack-planner agent to reason low-privilege-to-Domain-Admin paths from the collected inventory
Related Agents
Dim Investigator
Read-only stage-2 reviewer for /deep-review LOW/MED false-positive dimensions — types, observability, tests, a
Code Review Coordinator
Code review coordinator. Orchestrates multi-level reviews (low/medium/high) with git diff analysis, delegates
Harness Auditor
기존 Claude Code 하네스의 구성 정합성·anti-pattern·권한 안전성·에이전트-플레이북 매핑을 CRITICAL/HIGH/MEDIUM/LOW 4등급으로 진단. /harness-archi