PromptPartner

15 mods across 2 repositories, 216 stars between them.

release-check

01

PromptPartner/agentsmith

Skill Claude Code

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.

not rated 178 +1 4d ago A SkillSpector: pass 43 tokens original MIT

design-review

02

PromptPartner/agentsmith

Skill Claude Code

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.

not rated 178 +1 4d ago A SkillSpector: pass 61 tokens original MIT

autonomous-run

03

PromptPartner/agentsmith

Skill Claude CodeCodex needs its repo

Prepare, start, inspect, resume, or stop a finite local overnight coding run after a human has accepted a Wayfinder terminal spec; coordinates a declared Claude/Codex maker and independent checker without pushing, merging, or writing to external systems.

not rated 178 +1 changed 6d ago A SkillSpector: pass 53 tokens original MIT

example-skill

04

PromptPartner/agentsmith

Skill Claude CodeCodex

Template/example skill showing the minimal structure. Replace or delete it. Use as a starting point when you want to capture a repeatable workflow as a skill.

not rated 178 +1 4d ago A SkillSpector: pass 35 tokens original MIT

handoff

05

PromptPartner/agentsmith

Skill Claude CodeCodex

Checkpoint work for recovery — fires on "handoff", "wrap up", context pressure, a closed phase, or before a long external wait or irreversible gate. Part of the Agentsmith harness; writes durable state plus a paste-ready kickoff block so a fresh session loses nothing.

not rated 178 +1 changed 1mo ago A SkillSpector: pass 58 tokens original MIT

harness-doctor

06

PromptPartner/agentsmith

Skill Claude CodeCodex

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; checks each selected agent's managed rules, settings, skills, hooks, verification, and leanness with a one-line fix for each…

not rated 178 +1 changed 1mo ago A SkillSpector: warn 74 tokens original MIT

harness-help

07

PromptPartner/agentsmith

Skill Claude CodeCodex

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 the canonical instructions and selected agent's safety configuration, then reports the profile, rules, safety mode…

not rated 178 +1 changed 1mo ago A SkillSpector: pass 79 tokens original MIT

new-feedback

08

PromptPartner/agentsmith

Skill Claude CodeCodex

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…

not rated 178 +1 changed 1mo ago A SkillSpector: pass 82 tokens original MIT

new-research

09

PromptPartner/agentsmith

Skill Claude CodeCodex

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/ .md so findings live in the repo, never in disposable memory (R9), and are never silently deleted.

not rated 178 +1 4d ago A SkillSpector: pass 74 tokens original MIT

verify

10

PromptPartner/agentsmith

Skill Claude CodeCodex

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).

not rated 178 +1 changed 1mo ago A SkillSpector: pass 69 tokens original MIT

wayfinder

11

PromptPartner/agentsmith

Skill Claude CodeCodex

Wayfind a foggy, multi-session effort into an accepted repository spec and separate implementation-ticket drafts. Use when the destination is known but important decisions, dependencies, or scope are not yet clear enough to implement safely.

not rated 178 +1 changed 26d ago A SkillSpector: pass 46 tokens original MIT

writing-rules

12

PromptPartner/agentsmith

Skill Claude CodeCodex

Write or review anything an agent reads — a core rule, a profile gate, a SKILL.md description, an instruction-file line, a subagent prompt, a handoff note, a verify-phase label. Part of the Agentsmith harness; supplies the levers that decide whether a line changes behaviour or only costs tokens — the two loads…

not rated 178 +1 changed 1mo ago A SkillSpector: pass 107 tokens original MIT

grill-with-docs

13

PromptPartner/agentsmith

Skill Claude CodeCodex

Grill a fuzzy, single-session repository change into shared language, recorded decisions, and a handoff-ready plan. Use when the operator asks to grill or stress-test a plan or design in a repository; route multi-session uncertainty to wayfinder.

not rated 178 +1 4d ago A 55 tokens original MIT

bexio-mcp-server

14

PromptPartner/bexio-mcp-server

MCP server Claude CodeCodexCursor +2

Swiss accounting integration for Bexio. 314 tools: invoices, contacts, projects, account balances. Runs locally from the @promptpartner/bexio-mcp-server npm package.

not rated 38 +3 18d ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: