# SKILL_NAME

> Verb-first one-line summary of what the skill does, ending with a period.

- Skill: `thijsvos/skill-name` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add thijsvos/skill-name`
- Raw SKILL.md: https://api.skillmd.com/api/skills/thijsvos/skill-name/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: thijsvos (https://skillmd.com/u/thijsvos)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/thijsvos/skill-name

---


<!-- Skill prompt body. Replace this comment with content. -->
<!--                                                       -->
<!-- Canonical structure:                                  -->
<!-- 1. First line: `Call \`EnterPlanMode\` immediately   -->
<!--    before doing anything else.`                       -->
<!-- 2. 1-3 sentence mission statement                     -->
<!-- 3. If argument-hint declared: ARGUMENTS line +       -->
<!--    quoting note (use $ARGUMENTS / $0 / $name as       -->
<!--    needed)                                            -->
<!-- 4. `---` separator                                    -->
<!-- 5. Numbered steps (`## Step N: <Title>`) separated   -->
<!--    by `---` rules                                     -->
<!-- 6. The LAST step ends with: present report → call    -->
<!--    `ExitPlanMode` → action offer question →         -->
<!--    execute changes (Edit/Write happen here, AFTER    -->
<!--    plan mode exit)                                    -->
<!--                                                       -->
<!-- Subagents: default NO. Only add `Agent, Workflow` to  -->
<!-- allowed-tools and run a Workflow of exactly 3 read-   -->
<!-- only Explore agents (Agent tool as fallback) if the   -->
<!-- skill has THREE genuinely orthogonal analysis lenses. -->
<!-- See `skills/create-skill/SKILL.md` R4 decision gate.  -->
<!--                                                       -->
<!-- Body substitutions: $ARGUMENTS, $0/$1/$N (or          -->
<!-- $ARGUMENTS[N]), $<name>, \$ to escape a literal $,   -->
<!-- ${CLAUDE_SESSION_ID}, ${CLAUDE_EFFORT},               -->
<!-- ${CLAUDE_SKILL_DIR}, ${CLAUDE_PROJECT_DIR}. Use        -->
<!-- `` !`<command>` `` to run a shell command BEFORE      -->
<!-- Claude reads the skill (dynamic context injection).   -->

Call `EnterPlanMode` immediately before doing anything else.

Your mission statement goes here. Describe what Claude should do when this skill is invoked.