功能描述

Assist community moderation with summaries, spam detection suggestions, and draft replies for Discord or Telegram. Use when a user wants moderation help, rule reminders, or daily summaries without automatic enforcement actions.

使用说明 (SKILL.md)

Community Mod Pack

Name: Community Mod Pack
Author: codedao12

Goal

Summarize community activity and surface moderation signals with draft responses only.

Best fit

Use when the user needs daily or weekly channel summaries.
Use when the user wants spam or rule-violation signals.
Use when the user wants draft moderator replies or rule reminders.

Not fit

Avoid when the user asks to auto-ban, kick, or delete messages.
Avoid when the community rules are missing or unclear.
Avoid when privacy constraints prohibit analysis.

Quick orientation

references/overview.md for workflow and quality bar.
references/auth.md for access and token handling.
references/endpoints.md for optional integrations and templates.
references/webhooks.md for async event handling.
references/ux.md for intake questions and output formats.
references/troubleshooting.md for common issues.
references/safety.md for safety and privacy guardrails.

Required inputs

Channel logs or message exports within the allowed window.
Community rules and enforcement preferences.
Languages to moderate.
Escalation contacts and severity thresholds.

Expected output

Activity summary with key topics and notable threads.
Flagged messages with reasons and confidence.
Draft responses or rule reminders.
Suggested follow-up actions for human moderators.

Operational notes

Provide confidence and cite the rule that was triggered.
Avoid making final enforcement decisions.
Keep outputs in draft form.

Security notes

Respect privacy and minimize data retention.
Avoid sharing personal data beyond the moderator context.

Safe mode

Analyze and draft only; no enforcement actions.
Use read-only access to logs when possible.

Sensitive ops

Muting, banning, deleting messages, or modifying roles is out of scope.

安全使用建议

This skill is internally coherent for moderation assistance, but it requires sensitive inputs (channel logs or bot/read-only tokens). Before using it: 1) Prefer exporting logs and providing only the minimum time window and channels needed rather than full real-time/continuous access. 2) If you must supply a bot token, limit scopes to read-only and create a short-lived token that you can rotate afterwards. 3) Confirm with the skill/user interface how logs are handled and retained — avoid sharing full message bodies or unnecessary PII. 4) Do not provide admin-level credentials or long-lived tokens. 5) Test on a small, non-production dataset first and have a human review any flagged items before taking actions. If the skill later asks to send data to external endpoints or to perform enforcement actions, stop and re-evaluate before continuing.

功能分析

Type: OpenClaw Skill Name: community-mod-pack Version: 1.0.0 The skill bundle is benign. All files consistently describe a community moderation assistance tool focused on summaries, spam detection, and draft replies, explicitly prohibiting automated enforcement actions. Instructions emphasize read-only access, data privacy, and secure token handling, with no evidence of malicious intent, data exfiltration, or harmful prompt injection attempts against the agent in SKILL.md or any reference files.

能力评估

✓ Purpose & Capability

Name/description match the instructions: the skill is designed to ingest channel logs, surface moderation signals, and draft replies for human moderators. The declared requirements (none) are consistent with an instruction-only skill that expects the user to supply logs or tokens as needed.

ℹ Instruction Scope

SKILL.md and references clearly limit the agent to read-only analysis, summarization, and draft outputs and explicitly forbid enforcement actions. However the runtime instructions assume ingestion of message logs or read-only API access — these are sensitive inputs (user identifiers, message content). The instructions do not direct the agent to transmit data to external endpoints beyond optional Discord/Telegram APIs, but they also rely on user-supplied logs/tokens which is the main privacy surface.

✓ Install Mechanism

No install spec and no code files are present; this is instruction-only and will not write binaries to disk. That minimizes direct supply-chain risk.

ℹ Credentials

No environment variables or credentials are declared as required. The references/auth.md recommends using read-only bot tokens or exports if provided — this is reasonable, but the skill does not formally declare or constrain those credentials. Users should not provide broad-scoped tokens by default.

✓ Persistence & Privilege

always is false and there is no install or persisted configuration. The skill does not request permanent platform privileges or modify other skills, so its system presence is minimal.

版本历史

v1.0.0

Initial release of community-mod-pack: - Provides draft moderation summaries, spam detection suggestions, and reply drafts for Discord or Telegram communities. - Focuses on surfacing moderation signals and suggesting rule-based actions without performing enforcement. - Requires community rules, message exports, moderation preferences, and language info as inputs. - Outputs include activity summaries, flagged messages with reasoning, and draft moderator responses. - Designed to respect privacy, minimize data retention, and avoid any automated enforcement or sensitive operations.

元数据

Slug community-mod-pack

版本 1.0.0

许可证 —

累计安装 2

当前安装数 2

历史版本数 1

常见问题