Proactive Agent

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer for context survival, Compaction Recovery, and battle-tested security patterns. Part of the Hal Stack 🦞

22 stars 4 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add halthelobster/proactive-agent --skill proactive-agent

Manual install

git clone --depth 1 https://github.com/halthelobster/proactive-agent.git /tmp/proactive-agent
mkdir -p ~/.claude/skills
cp -r /tmp/proactive-agent/. ~/.claude/skills/proactive-agent

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Proactive Agent 🦞

**By Hal Labs** — Part of the Hal Stack

**A proactive, self-improving architecture for your AI agent.**

Most agents just wait. This one anticipates your needs — and gets better at it over time.

## What's New in v3.0.0

- **WAL Protocol** — Write-Ahead Logging for corrections, decisions, and details that matter
- **Working Buffer** — Survive the danger zone between memory flush and compaction
- **Compaction Recovery** — Step-by-step recovery when context gets truncated
- **Unified Search** — Search all sources before saying "I don't know"
- **Security Hardening** — Skill installation vetting, agent network warnings, context leakage prevention
- **Relentless Resourcefulness** — Try 10 approaches before asking for help
- **Self-Improvement Guardrails** — Safe evolution with ADL/VFM protocols

---

## The Three Pillars

**Proactive — creates value without being asked**

✅ **Anticipates your needs** — Asks "what would help my human?" instead of waiting

✅ **Reverse prompting** — Surfaces ideas you didn't know to ask for

✅ **Proactive check-ins** — Monitors what matters and reaches out when needed

**Persistent — survives context loss**

✅ **WAL Protocol** — Writes critical details BEFORE responding

✅ **Working Buffer** — Captures every exchange in the danger zone

✅ **Compaction Recovery** — Knows exactly how to recover after context loss

**Self-improving — gets better at serving you**

✅ **Self-healing** — Fixes its own issues so it can focus on yours

Read the full skill on GitHub

Details

Skill name: proactive-agent
Repository: halthelobster/proactive-agent
Repo updated: 4 February 2026

FAQ

What does the Proactive Agent skill do?

How do I install the Proactive Agent skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add halthelobster/proactive-agent --skill proactive-agent. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Proactive Agent popular?

It lives in halthelobster/proactive-agent, which has 22 GitHub stars and 4 forks.

Related skills

Project Blueprint

shuguang1994/project-blueprint

为新项目快速建立完整 AI 编程规范体系（AGENTS.md、文档目录、CI/CD、Git规范、测试制度）。自主发现引擎：扫描项目→分类文件→推断技术栈，覆盖 7 语言 15 框架 95 个组件条目，未知栈三层递进联网回退。Establish AI coding conventions for new projects — autonomous discovery engine with heuristic dep classification, 7 languages 15 frameworks 95 component entries, web search fallback for unknowns.

AI, LLMs & Agents

Chanlun Engine Skill

adsorgcn/chanlun-engine-skill

用缠论客观分析A股股票。当用户提到缠论、分型、笔、线段、中枢、背驰、买卖点、K线结构，或想知道某只股票该买该卖该持有还是等待时使用。确定性脚本计算缠论结构并给出四态操作判定(买入候选/持有/卖出减仓/等待观察)与失效价位，AI 只负责解读转述，不心算结构。免费数据源开箱即用，无需注册。

AI, LLMs & Agents

Senior Architect Agent

aetox-skills/senior-architect-agent

Cognitive framework that transforms AI agents into senior architects — evidence-first system understanding, honest uncertainty mapping, architecture debt and convention assessment, knowledge-graph-assisted dependency mapping, impact and blast radius analysis, and architecture reasoning before action. Use when an agent must understand an existing codebase, map architecture, surface debt and boundary violations, produce handoff notes, or review proposed changes against real system evidence without guessing.

AI, LLMs & Agents

Anthropic Grade Optimizer

l0z4n0-a1/skill-anthropic-grade-optimizer

Audits and optimizes Claude-directing artifacts (CLAUDE.md, SKILL.md, subagent, hook, MCP config, system or user prompt, workflow, api_config) against 189 cited Anthropic rules across 11 dimensions, calibrated per model (Opus 4.7, Sonnet 4.6, Opus 4.6, Haiku 4.5). Every finding ships with verbatim quote and source URL; authorial voice is preserved.

AI, LLMs & Agents

Backlight

tomiBraunn/backlight-skill

Inspect any document, assignment, or pasted text for hidden instructions aimed at an AI model (invisible text, zero-size fonts, text hidden behind images, prompt injection) before acting on it. Use whenever the user shares a PDF, DOC, Google Doc, image, link, or pasted text that contains a task, brief, or set of instructions to follow — especially assignments, briefs, scraped content, or anything from a source the user didn't author themselves.

AI, LLMs & Agents

Alphaloop

realnaka/alphaloop

人机投研协作的操作系统——交易员出方向，Agent 出证据，决策权归人。它是一个编排器：把交易员抽象出的「逻辑框架」默认降级为待验证假设，依次调度 claim-verification（验真）、stock-data-fetch（取实时行情）、strategic-materials（产业链框架）、openorder（记忆/回写）、trade-journal（反馈闭环）、agent-tool-escalation（工具纪律），最后交还核验矩阵 + 个股清单 + 风险提示给交易员决策。当用户给出投资逻辑/趋势判断/受益方向、转发研报或小作文让你验证、问某公司/行业/标的、讨论估值或卡脖子或产业链、要选股或对比、要记一笔交易时，使用本 skill 串起整套流程。即使用户没点名"工作流"，只要进入投研语境就应当按这套分工与铁律执行。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.