bgskillzlisted

# BGSkillz Build high-quality, portable agents and skills that trigger reliably and deliver real value. **Target ~100 lines / ~900 tokens** per skill — high signal, not high word count. ## Core Philosophy 1. **Skills are prompts** — SKILL.md is a prompt document. Everything in it shapes Claude's behavior when the skill activates. 2. **Explain the why, not just the what** — LLMs are smart. They respond better to understood rationale than rigid rules. Instead of "ALWAYS use 4-space indentation," explain *why* consistent indentation matters. If you find yourself writing MUST or NEVER in all caps, that's a yellow flag — reframe as reasoning. 3. **Progressive disclosure** — Target ~100 lines in SKILL.md (~900 tokens). Hard max 500 lines. Put depth in `references/`, judgment in `agents/`, determinism in `scripts/`. 4. **Composability** — Skills should do one thing well. Combine multiple skills for complex workflows rather than building monoliths. 5. **Portability** — Skills work across Claude.ai, Claude Code, and the API. Write for all surfaces unless you have a reason not to. 6. **Specificity wins** — Vague skills don't trigger. Specific skills with clear use cases and trigger phrases activate reliably. Make descriptions slightly "pushy" — Claude tends to undertrigger rather than overtrigger. 7. **Generalize, don't overfit** — A skill that works only for your test examples is useless. It will be invoked by diverse users with diverse needs. When iterating, resist fiddly overfitt