メニュー
Triggers the L5 Red Team Sub-Agent to rigorously audit a plugin against the 39-point L4 pattern matrix.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use this skill when a BC Small Claims Notice of Claim draft is already captured in canonical JSON and the next step is deterministic PDF-generation readiness review, renderer handoff, or artifact verification. This skill is for JSON-to-PDF generation only. It must not take over guided intake or canonical JSON authoring.
Use this skill when a BC Small Claims Notice of Claim draft already exists in canonical JSON and the next step is to produce a deterministic mock filing payload, simulate downstream submission, or inspect adapter artifacts. This skill is for JSON-to-adapter handoff only. It must not take over guided intake or PDF rendering.
This skill should be used when the user wants to start a BC Small Claims Notice of Claim, answer the Form 1 questions interactively, turn freeform facts into a structured intake packet, align the answers to the observed Filing Assistant question flow and canonical case JSON, or identify what information is still missing before validation or rendering.
Use this skill when a BC Small Claims Notice of Claim draft is already captured in canonical JSON and the next step is deterministic PDF-generation readiness review, renderer handoff, or artifact verification. This skill is for JSON-to-PDF generation only. It must not take over guided intake or canonical JSON authoring.
Use this skill when a BC Small Claims Notice of Claim draft already exists in canonical JSON and the next step is to produce a deterministic mock filing payload, simulate downstream submission, or inspect adapter artifacts. This skill is for JSON-to-adapter handoff only. It must not take over guided intake or PDF rendering.
This skill should be used when the user wants to start a BC Small Claims Notice of Claim, answer the Form 1 questions interactively, turn freeform facts into a structured intake packet, align the answers to the observed Filing Assistant question flow and canonical case JSON, or identify what information is still missing before validation or rendering.
| name | audit-plugin-l5 |
| plugin | agent-scaffolders |
| description | Triggers the L5 Red Team Sub-Agent to rigorously audit a plugin against the 39-point L4 pattern matrix. |
| allowed-tools | Bash, Read, Write |
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ../../requirements.txt for the dependency lockfile (currently empty — standard library only).
This skill abstracts the execution of the L5 Enterprise Red Team Auditor. By using this skill, you trigger an uncompromising architecture and security review against the 39-point pattern matrix.
Before executing this skill, ensure you know the exact path or name of the plugin you wish to audit (e.g., plugins/oracle-legacy-system-analysis/xml-to-markdown).
This skill delegates immediately to the l5-red-team-auditor sub-agent.
Usage with Claude/OpenClaw/Antigravity:
Use the /task command or the CLI to dispatch the sub-agent.
# If using the CLI directly:
claude -p l5-red-team-auditor "Please deeply assess the plugin located at: plugins/[INSERT_PLUGIN_NAME_HERE]"
The sub-agent is instructed to output a structured markdown artifact titled [Plugin_Name]_Red_Team_Audit.md containing:
Always conclude execution with a Source Transparency Declaration explicitly listing what was queried to guarantee user trust: Sources Checked: [list] Sources Unavailable: [list]
references/*.md. The L5 Red Team Auditor MUST use these ADRs (especially ADR 001-006) as primary evidence when evaluating architectural maturity and loose coupling. Any deviation from these standards must be flagged as an L4/L5 maturity gap.