# Capability Name

> Use with named Profiles for one narrow engineering decision; do not use without the registered trigger or as the primary task owner.

- Skill: `machenjie/capability-name` (Agent Skill, multi-file: 3 files)
- Install (CLI): `npx skillmds@latest add machenjie/capability-name`
- Raw SKILL.md: https://api.skillmd.com/api/skills/machenjie/capability-name/raw
- Safety review: PASS (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: machenjie (https://skillmd.com/u/machenjie)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/machenjie/capability-name

---


# capability-name

## Registry Trigger

**Use when**

- Name the concrete source, contract, or risk signal that requires this decision.

**Do not use when**

- Name the adjacent or absent condition that makes this capability irrelevant.

## Skill Role

Define the named professional decision and exclude adjacent concerns already owned by other Skills.

## High-Value Rules

- State three to eight rules that change a design, implementation, review, or proof decision.
- Bind each rule to current-system evidence instead of prescribing a context-free technology or threshold.
- Preserve the named invariant, consumer, failure behavior, and selection tradeoff.

## Anti-Patterns

- Name concrete failure patterns that a competent agent may otherwise miss, including the condition and consequence.

## Targeted References

- Link only registry-indexed References whose subject can change this decision; do not load them by default.