skills/base/bill-new-skill-all-agents/SKILL.md
Use when creating a new skill and syncing it to all detected local AI agents (Claude, Copilot, GLM, Codex, Opencode). Use when user mentions create skill, new skill, add skill, or sync skill to agents.
npx skillsauth add sermilion/mobile-development-plugin bill-new-skill-all-agentsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
If .agents/skill-overrides.md exists in the project root and contains a ## bill-new-skill-all-agents section, read that section and apply it as the highest-priority instruction for this skill. The matching section may refine or replace parts of the default workflow below.
If an AGENTS.md file exists in the project root, apply it as project-wide guidance.
Precedence for this skill: matching .agents/skill-overrides.md section > AGENTS.md > built-in defaults.
When asked to create a new skill, follow this workflow:
1a. Validate the proposed name against the repo naming strategy:
- Keep bill as the namespace prefix
- Base skills should use bill-<capability>
- Stack-specific skills should use bill-<stack>-<capability>
- Code-review subskills are the only approved deeper specialization shape: bill-<stack>-code-review-<area>
- Approved code-review areas are: architecture, performance, platform-correctness, security, testing, api-contracts, persistence, reliability, ui, ux-accessibility
- Platform-specific skills must reuse an existing base capability name instead of inventing a new platform-only capability
- Do not rename an existing base skill just to add taxonomy consistency; create a new stack-specific variant only when behavior actually differs
- If renaming an existing stack-bound skill, update install.sh legacy-name migration rules and README references in the same change
1b. Derive the source package from the validated name:
base for neutral skills like bill-pr-description or bill-feature-guardkotlin for Kotlin-prefixed skillskmp for KMP-prefixed skillsphp for PHP-prefixed skillsKnown agents and their paths:
$HOME/.copilot/skills$HOME/.claude/commands$HOME/.glm/commands$HOME/.codex/skills, fallback to $HOME/.agents/skills$HOME/.config/opencode/skillsNormalize the skill name to a slug:
-a-z, 0-9, -bill-... prefix structureCreate canonical skill file:
$HOME/Development/skill-bill/skills/{package}/{slug}/SKILL.mdCreate direct symlinks from each selected agent to the canonical skill directory:
ln -s $HOME/Development/skill-bill/skills/{package}/{slug} {agent_path}/{slug}Rules:
SKILL.md inside a directory named after the slug## Project Overrides section near the top that tells the skill to read .agents/skill-overrides.md for a matching ## {slug} section, with precedence skill override > AGENTS.md > built-in defaultsReturn a short summary:
development
Use when running a governed editorial assignment desk from Readian recommendations through candidate selection and source-backed story packs.
testing
Use when reviewing unit tests in a file, current changes, or a commit to flag low-value, tautological, or coverage-only tests that do not validate real behavior. Use when user mentions check test quality, review tests, tautological tests, weak tests, or coverage-padding.
data-ai
Use when removing an existing skill or platform skill set and cleaning up agent installs, manifests, and supporting links.
development
Use when you want a generic quality-check entry point that detects the dominant stack in scope and delegates to the matching stack-specific quality-check skill. Use when user mentions run checks, validate, lint, format, quality check, or run quality.