القائمة
Reference for the promptherder CLI — syncs AI agent rules, skills, and workflows from herd repos to agent targets. Use when installing, updating, or troubleshooting prompt distribution.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Semver release workflow — bump version, tag, push, verify CI. Use when releasing, bumping version, updating version, or when the user says 'release', 'bump', 'major', 'minor', 'patch', 'update version', 'new version', 'cut a release', 'tag', or 'goreleaser'.
Mise dev tool manager — installing tools, running mise-managed commands, and configuring .mise.toml. Use when installing tools, running CLI commands that aren't found, or setting up project environments.
Docker best practices for multi-stage Alpine builds — security patches, image pinning, and layer optimization. Use when creating, reviewing, or updating Dockerfiles.
Tekmetric REST API — authentication, paginated endpoints, sync patterns, and undocumented behaviors. Use when integrating with Tekmetric shop management data (customers, vehicles, repair orders, employees, appointments).
DaisyUI v5 component library for Tailwind CSS — semantic UI classes, themes, layout patterns, drawer/sidebar gotchas, and component quick reference. Use when building, styling, or debugging UI with DaisyUI, Tailwind components, or DaisyUI themes.
Groq API syntax — Whisper transcription, audio processing, and prompt-based jargon guidance. Use when calling Groq endpoints or transcribing audio.
| name | promptherder |
| description | Reference for the promptherder CLI — syncs AI agent rules, skills, and workflows from herd repos to agent targets. Use when installing, updating, or troubleshooting prompt distribution. |
Go CLI that manages AI agent configuration per repo. .promptherder/ is the source of truth for each repository's agent rules, skills, and workflows.
Sources Agent targets (local)
┌──────────────┐
│ herds (GitHub)│──┐
└──────────────┘ │
├──→ .agents/ (Antigravity)
┌──────────────┐ ├──→ .github/ (Copilot)
│ repo-local │──┘
│ (.promptherder/agent/)
└──────────────┘
.promptherder/agent/ add per-project skills, rules, or overrideshard-rules.md in .promptherder/ contains always-on rules specific to this repopromptherder merges everything and fans out to each agent target.promptherder/manifest.json tracks what files promptherder owns# Install a herd
promptherder pull https://github.com/shermanhuman/compound-v
promptherder pull https://github.com/shermanhuman/oh
# Sync to all targets (run after every pull)
promptherder
# Preview without writing
promptherder -dry-run
# Sync one target only
promptherder copilot
promptherder antigravity
A herd is a GitHub repo with herd.json and content in rules/, skills/, workflows/:
my-herd/
├── herd.json # {"name": "my-herd", "version": "0.1.0"}
├── rules/
│ └── my-rule.md
├── skills/
│ └── my-skill/
│ └── SKILL.md
└── workflows/
└── plan.md
Only rules/, skills/, and workflows/ are synced. Everything else is metadata.
pull downloads but does not sync — always run bare promptherder aftergenerated array (e.g., stack.md) are never overwrittenCOPILOT.md or ANTIGRAVITY.md override SKILL.md