How to Force Load a Specific PM Skills Skill: Syntax and Examples

Prefix the skill name with a forward slash to force load a specific PM skills skill using /plugin-name:skill-name or /skill-name syntax.

The phuryn/pm-skills repository provides a collection of product management skills for Claude that typically load automatically based on conversation context. When you need immediate access to a specific skill's knowledge without waiting for trigger phrases, you can force load a specific PM skills skill using simple slash commands.

Understanding PM Skills Auto-Loading vs Force Loading

PM Skills are built as individual markdown files containing specialized knowledge, trigger phrases, and instructions. According to the repository's README.md, Claude automatically loads these skills when the conversation topic matches predefined trigger phrases in the skill's frontmatter.

However, in scenarios where you need to prioritize specialized skill knowledge over general model knowledge, force loading bypasses the automatic trigger system. This ensures the skill's context is immediately available for your next prompt.

Force Load Syntax and Examples

The force-load syntax requires prefixing the skill identifier with a forward slash. You can use either the full qualified name or the short form.

Full Syntax with Plugin Prefix

Use /plugin-name:skill-name when you need to specify exactly which plugin owns the skill:

User: /pm-toolkit:review-resume
Claude: (skill `review-resume` is now loaded)
User: Here is my resume PDF…

Short Form (Skill Name Only)

Use /skill-name and Claude will automatically resolve the plugin prefix:

User: /review-resume
Claude: (skill `review-resume` loads automatically)
User: Please tailor this resume for a senior PM role.

CLI and Interactive Sessions

When using Claude Code or Codex CLI, first install the plugin containing the skill, then invoke the force-load command:

# Install the plugin that contains the skill

claude plugin install pm-toolkit@pm-skills

# Force-load the skill in an interactive session

claude> /pm-toolkit:review-resume

Complex Strategy Skills

For advanced skills like strategy red-teaming, force loading ensures the analytical framework is active before you present your content:

User: /pm-execution:strategy-red-team
Claude: (skill `strategy-red-team` is now active)
User: Analyze the assumptions in this product roadmap.

How Force Loading Works Internally

The force-load mechanism operates through three stages as implemented in the phuryn/pm-skills architecture:

1. Skill Registration – Each skill resides under plugin-name/skills/ as a markdown file with YAML frontmatter containing a description and trigger phrases. For example, pm-toolkit/skills/review-resume/SKILL.md defines the resume review capability.

2. Auto-Loading – Claude monitors user utterances for trigger phrase matches, fetching the skill's knowledge only when relevant to the conversation context.

3. Force-Loading – The slash prefix (/) signals Claude to load the skill immediately without waiting for trigger matches, injecting the skill's knowledge into the model's context window for the subsequent interaction.

This behavior is documented in both README.md (section Force-loading skills) and CLAUDE.md, which states: "Skills can be force-loaded with /plugin-name:skill-name or /skill-name."

Summary

• Force load a specific PM skills skill by prefixing the skill name with a forward slash: /plugin-name:skill-name or /skill-name.
• Use the full syntax when multiple plugins might contain skills with similar names; use the short form for convenience when the skill name is unique.
• Force loading is essential when you need specialized PM knowledge immediately without relying on automatic trigger phrase detection.
• Key files defining this behavior include README.md and CLAUDE.md in the repository root, with individual skill definitions stored in paths like pm-toolkit/skills/review-resume/SKILL.md.

Frequently Asked Questions

What is the difference between auto-loading and force-loading PM skills?

Auto-loading occurs when Claude detects trigger phrases in your conversation that match a skill's defined keywords, automatically fetching the skill's knowledge. Force-loading uses the /skill-name syntax to immediately inject the skill's context without waiting for trigger detection, ensuring the specialized knowledge is available for your next prompt.

Can I force load multiple PM skills at once?

The source documentation in README.md and CLAUDE.md describes force-loading syntax for individual skills. To load multiple skills, you would issue separate force-load commands for each skill (e.g., /pm-toolkit:review-resume followed by /pm-execution:strategy-red-team), allowing Claude to accumulate the relevant context from each.

Where are PM skills stored in the repository?

Individual skills are stored as markdown files within plugin-specific directories under the repository root. For example, the review-resume skill is located at pm-toolkit/skills/review-resume/SKILL.md, while the strategy-red-team skill resides at pm-execution/skills/strategy-red-team/SKILL.md. Each file contains the skill's instructions, trigger phrases, and knowledge base.

Do I need to install the plugin before force loading a skill?

Yes, the plugin containing the skill must be installed in your Claude environment before force loading. As shown in the CLI examples, you must first run claude plugin install pm-toolkit@pm-skills (or the appropriate plugin identifier) before you can successfully invoke /pm-toolkit:review-resume or /review-resume.

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}