← 返回 Skills 市场

Drill Sergeant Skill

Name: Drill Sergeant Skill
Author: ptaramona

作者 ptaramona · GitHub ↗ · v0.1.0 · MIT-0

cross-platform ⚠ suspicious

333

总下载

当前安装

版本数

在 OpenClaw 中安装

/install drill-sergeant-skill

功能描述

Enforce communication discipline in team channels by detecting message violations, issuing corrective actions, and summarizing for leadership.

使用说明 (SKILL.md)

Drill Sergeant

Overview

Run a practical discipline loop for agent operations: scan activity, detect violations, classify severity, and issue concise corrective actions that reduce noise and keep work moving.

Workflow

Define scope and rule set for this run.
Collect message and task signals from allowed sources.
Detect violations using the enforcement checklist.
Deduplicate repeated findings.
Produce corrective actions with owner + due-now wording.
Publish a short summary for leadership.

Operating Rules

Keep outputs short and actionable.
Prefer one consolidated update over many fragmented alerts.
Treat repeats as a process defect; suggest root-cause fixes, not only symptoms.
Escalate only for high-severity or repeated failures.
Never include secrets, internal tokens, private endpoints, webhook URLs, or personal identifiers in public-ready outputs.

Violation Categories

Routing violations (wrong channel/audience)
Duplicate or looped posts
Missing ownership or assignment signals
Stale review states (work complete but not closed)
Status quality failures (vague/optimistic/non-evidenced)
Policy drift (deprecated IDs, formats, or conventions)

Output Contract

For each violation include:

type
severity (low/medium/high)
evidence (short quote or artifact reference)
action (imperative fix)
owner

End with:

Top 3 immediate actions
Escalations (if any)
All clear when no actionable violations exist.

References

Enforcement checklist: references/enforcement-checklist.md
Message templates: references/message-templates.md
Public-safe publishing checklist: references/public-safety-checklist.md

安全使用建议

This skill appears to do what it says, but its runtime instructions are intentionally vague about which message sources to collect. Before installing or enabling it: 1) Confirm exactly which connectors/permissions the agent will use to read messages (Slack, Teams, email, task trackers) and restrict the skill to only those approved channels. 2) Require explicit scope/allowlist in SKILL.md (time window, channel list, message types) and automated redaction rules so outputs cannot include PII, tokens, or internal IDs. 3) Run the skill in a limited sandbox or with read-only, narrow-scoped credentials first and audit the outputs for accidental data leakage. 4) If you need stronger guarantees, ask the author to add explicit collection rules and built-in redaction/filtering before broad deployment.

功能分析

Type: OpenClaw Skill Name: drill-sergeant-skill Version: 0.1.0 The 'drill-sergeant-skill' is a governance and project management tool designed to help AI agents monitor team communication and task hygiene. The bundle consists entirely of Markdown instructions and checklists (SKILL.md, README.md, and reference files) with no executable code, obfuscation, or suspicious network activity. The instructions explicitly emphasize public safety and the exclusion of secrets, tokens, or PII (public-safety-checklist.md).

能力评估

ℹ Purpose & Capability

Name/description match the included artifacts (checklists, templates, operating rules). The skill is instruction-only and does not declare unrelated credentials or binaries, which is proportionate. However, the skill implicitly requires access to team messages/tasks (connectors or platform permissions) but does not document or restrict which sources are allowed — this is reasonable for a discipline tool but should be explicit.

⚠ Instruction Scope

The SKILL.md tells the agent to 'Collect message and task signals from allowed sources' but does not define or limit those sources. That vagueness grants the agent broad discretion to fetch message history or other context from whatever connectors it has access to, increasing risk of reading sensitive content. The operating rules advise not to include secrets/identifiers in outputs, but there is no enforcement or concrete filtering/redaction instruction, nor any limitation on collection scope or retention.

✓ Install Mechanism

Instruction-only skill with no install script, no code files to execute, and no network downloads — minimal install risk. Nothing in the package performs arbitrary code installation.

ℹ Credentials

The package requests no environment variables or credentials, which is consistent with its claim of being 'vendor-neutral' and publish-safe. However, practical use requires the agent/platform to have connectors to message sources; the skill does not document required permissions or connectors. Confirming which external service credentials (if any) will be used is necessary before deployment.

✓ Persistence & Privilege

Flags show default invocation (not always: true) and no claims of modifying other skills or agent-wide settings. The skill does not request persistent system presence or elevated privileges in the package.

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 drill-sergeant-skill
安装完成后，直接呼叫该 Skill 的名称或使用 /drill-sergeant-skill 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

v0.1.0

drill-sergeant-skill v0.1.0 - Initial release of the Drill Sergeant skill. - Enforces team communication discipline and execution hygiene in shared work channels. - Detects messaging violations (loops, routing errors, missing ownership, stale reviews, noise). - Generates concise corrective actions and escalation notes. - Produces manager-ready summaries and actionable updates.

元数据

Slug drill-sergeant-skill

版本 0.1.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题