PromptPartner
UserUniversal, model-agnostic operating harness for AI agents (Claude, Codex, Gemini, …) — a lean core + work-type profiles assembled by one setup script.
Categories
Indexed Skills (8)
design-review
Use when adding or restyling a Facet UI component, or before merging a UI PR — walks the component against DESIGN.md (tokens, states, a11y, contrast, responsive) so the design system is matched, not just remembered. The judgment check verify.sh can't grep.
release-check
Use when cutting an Orchard release (tagging a new version of the FastAPI inventory service) — walks the pre-tag checklist so migrations, verify, changelog, and the tag stay in sync.
handoff
Wrap up a work session for a clean restart — fires on "handoff", "wrap up", "let's stop here", when context is filling, or when a phase closed. Part of the Agentsmith harness; writes a durable handoff note plus a paste-ready kickoff block so a fresh session loses nothing.
harness-doctor
Check whether this project's Agentsmith harness is installed correctly and healthy — fires on "is my harness set up right?", "harness doctor", "check my harness". Part of the Agentsmith harness; runs self-contained health checks (CLAUDE.md managed block, settings, verify.conf, scripts, leanness) with a one-line fix for each finding.
harness-help
Orient a non-coder to this project's Agentsmith harness — fires on "what is this harness?", "what are my rules?", "which profile am I on?", "what do I type next?". Part of the Agentsmith harness; reads CLAUDE.md and reports the active profile, a short rules summary, the safety mode, and the next thing to type — in plain language.
new-feedback
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-*.md with the five-stage template (R9 — numbers are never reused).
new-research
Start a durable research / source note that captures what you read and found — fires on "start a research note", "capture these sources", "log my research". Part of the Agentsmith harness; scaffolds docs/research/<slug>.md so findings live in the repo, never in disposable memory (R9), and are never silently deleted.
verify
Answer "is this shippable / done?" with evidence before a commit or PR — fires on "verify", "is this done", "ready to ship?", pre-commit or pre-PR. Part of the Agentsmith harness; runs the project's verify phases and never claims "passing" without showing the output (R5).
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.