← 返回 Skills 市场

Charisma Research Loop

Name: Charisma Research Loop
Author: dman3629

作者 Derezar Master · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

328

总下载

当前安装

版本数

在 OpenClaw 中安装

/install charisma-research-loop

功能描述

Generate daily high-signal charisma/engagement insights with a self-improving novelty loop. Use when sending recurring tips on charisma, body language, orati...

使用说明 (SKILL.md)

Charisma Research Loop

Use this workflow to avoid shallow repeated advice and continuously improve insight quality.

Output contract

Produce exactly 5 insights per run.
Make each insight specific, testable, and action-oriented.
Include these fields for each insight:
1. Theme
2. Insight
3. Why it works
4. 24h experiment
5. Failure mode / misuse risk

Theme rotation

Rotate themes so consecutive runs are not repetitive. Use this pool:

Body language and non-verbal signaling
Oration and vocal delivery
Social psychology and status dynamics
Ethical persuasion and influence
Manipulation detection and defense
Conversation architecture and storytelling
Presence under pressure (meetings, conflict, negotiation)

Source depth rules

Prefer synthesis over quotes.
Pull from mixed source types each run (discussion + educational + behavioral science).
Do not rely on only surface-level generic tips.
Convert raw source material into deeper mechanisms and practical tests.

Self-improving loop (mandatory)

Before generating a new run:

Read /root/.openclaw/workspace/memory/charisma-insight-ledger.md.
Identify what was already sent recently and mark those clusters as DONE in today’s section when superseded.
Choose at least 3 new angles not used in the most recent 3 runs.
Generate the new 5-insight set.
Append a compact run log to the ledger:
- timestamp
- themes used
- novelty score (1-10)
- repeated ideas avoided
- one improvement for next run

Delivery

Send concise email brief with the 5 insights.
Create/update calendar task/event containing same 5 insights.
Keep wording practical, direct, non-fluffy.

安全使用建议

Before installing, ask the skill author to: 1) explicitly declare the config path(s) it will read/write (and explain why /root/.openclaw/... is required); 2) explain how email/calendar delivery is performed and what credentials or connectors are used (and list required env vars or integrations); 3) confirm what data is stored in the ledger and for how long; 4) prefer a skill-scoped writable path (not an absolute root path) or let you choose the ledger location; and 5) consider sandboxing or reviewing the first few ledger entries and backups before granting write permission. If the author cannot clarify these points, treat the skill as higher risk because it can read/write persistent agent memory and send external messages without declared boundaries.

功能分析

Type: OpenClaw Skill Name: charisma-research-loop Version: 1.0.0 The skill's instructions in `SKILL.md` outline a self-improving loop that involves reading from and appending to a specific file (`/root/.openclaw/workspace/memory/charisma-insight-ledger.md`) within the agent's designated memory space. It also instructs the agent to send emails and create calendar events for delivery of insights. These actions are directly aligned with the skill's stated purpose of generating and delivering daily insights with a self-improving mechanism. There is no evidence of intent to exfiltrate sensitive data, execute arbitrary commands, establish persistence, or perform any other malicious activities. The file and network access capabilities are used for their plausible and stated purpose.

能力评估

⚠ Purpose & Capability

Generating rotating, self-improving insight sets and logging them is coherent with the skill name/description. However, the SKILL.md requires reading and appending /root/.openclaw/workspace/memory/charisma-insight-ledger.md even though the skill declares no required config paths — the ledger path is not declared or justified in the metadata.

⚠ Instruction Scope

Instructions explicitly tell the agent to read and modify an absolute root workspace path and to send email briefs and create/update calendar events. Those file I/O and external-delivery actions extend beyond simple content generation and are not scoped or constrained in the metadata (no declared config paths, no declared delivery endpoints or credentials).

✓ Install Mechanism

This is instruction-only with no install spec or code to write to disk, so there is no installer-related risk. The primary risk comes from the instructions themselves.

⚠ Credentials

The skill requests no environment variables or credentials but requires delivering emails and calendar entries — actions that normally require account access or connectors. The absence of declared credentials or explanation for how delivery will occur is a mismatch. Also, the ledger path is under /root, implying elevated workspace access.

⚠ Persistence & Privilege

The skill mandates appending a run log to a workspace ledger (persistent state). Writing to the agent's root-level workspace file without declaring or asking for permission expands persistence and privilege; while persisting its own run log can be legitimate, the absolute path and lack of declared authorization are concerning.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install charisma-research-loop
安装完成后，直接呼叫该 Skill 的名称或使用 /charisma-research-loop 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: deep charisma insights with novelty/self-improving loop and theme rotation.

元数据

Slug charisma-research-loop

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题