Update to Headcount: Technology

{
  "description": "Writes and revises agent skills so they trigger at the right moments and give usable instruction when they do. Use this when creating a new skill, editing an existing one, diagnosing a skill that fires too often or never fires, or reviewing a set of skills for overlap. Also use before adding to a skill library, to check the capability is not already covered.",
  "included_files": [
    {
      "relative_path": "references/sources.md",
      "size_in_bytes": 864
    }
  ],
  "name": "skill-authoring",
  "skill_md_contents": "---\nname: skill-authoring\ndescription: Writes and revises agent skills so they trigger at the right moments and give usable instruction when they do. Use this when creating a new skill, editing an existing one, diagnosing a skill that fires too often or never fires, or reviewing a set of skills for overlap. Also use before adding to a skill library, to check the capability is not already covered.\n---\n\n# Skill authoring\n\nA skill is judged twice: on whether it loads at the right moment, and on whether it helps once\nloaded. Most fail the first test.\n\n## The description does the triggering\n\nIt is the only part read when deciding whether to load. Write it for that job:\n\n- Lead with **what the skill does**, in one clause.\n- Then **when to reach for it** — the situations, in the words someone would actually use, including\n  the oblique ones (\"why isn't this converting\" as well as \"CRO audit\").\n- Name the **edge cases that should still trigger it**, and where useful, what should *not*.\n\nVague descriptions produce two failures at once: the skill misses cases it should catch, and fires\non cases it cannot help.\n\n## The body does the work\n\nWrite for someone competent who has not thought about this problem today. That means:\n\n- **Method over exhortation.** \"Be thorough\" is noise. An ordered procedure is instruction.\n- **State the failure behind each rule.** A rule with no failure attached gets optimized away by the\n  next reader.\n- **Be specific enough to be wrong.** Guidance too hedged to contradict is too vague to follow.\n- **Put long material in `references/`** and say when to read it. The body should fit in working\n  memory.\n\n## Overlap is the silent killer\n\nTwo skills whose descriptions both match a request means neither reliably wins. Before adding one,\ncheck what already covers the ground. Prefer extending an existing skill, or consolidating the\nfamily into one skill with references, over adding a near-neighbor.\n\n## Mechanics\n\n- `name` must be lowercase-hyphenated and equal the directory name, or the skill will not load.\n- One skill, one directory, `SKILL.md` at its root; supporting material in `references/` and\n  `scripts/`.\n\n## Verify before shipping\n\nWrite three requests that should trigger it and two that should not, and check the description\nactually discriminates. If a near-miss request would pull it in, tighten the description.\n\n## Sources\n\n`references/sources.md` in this skill lists the outside authorities that settle the questions\nhere — what each one is authoritative for, and what you may do with it. Check them before\nanswering on anything they cover, and cite what you used. Most are free to read and not free\nto reproduce; the use note on each is binding.\n\n## Never\n\n- Ship a skill whose description does not say when to use it. A skill that never triggers is dead weight.\n- Write a skill that restates what the model already does well without prompting.\n- Let two skills claim the same trigger. Move the boundary or merge them.\n- Ship without running the skill against the case that motivated writing it.\n"
}