om-implement-feature-multi-optimized — Claude Code skill
om-implement-feature-multi-optimized is a Claude Code skill that routes feature work to configured implementation workers and independent review advisors. It stages the result without publishing.
MIT 501 installs ★ 282 updated 2026-10-22
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a claude-codeWhat om-implement-feature-multi-optimized does
The skill invokes om-implement-feature with the multi-optimized profile, passing through a required brief and an optional --slug. Interactive mode is the default; --autonomous can be used instead. The base workflow handles the implementation, its worker packets and spec, then the review councils.
Configured model bindings and a passing profile probe are required. If either is missing or fails, the skill stops and runs om-setup-agent-harness interactively before retrying the originally requested profile. The feature remains staged for handoff. The skill never commits, pushes, or publishes; publication requires a separate human-authorized step.
What it helps with
- implement a feature brief with the
multi-optimizedprofile - route implementation work to configured workers and review to independent advisors
- leave a verified feature staged without committing or publishing it
Example prompts for the agent
- Implement this feature from the brief with the
multi-optimizedprofile: … - Run this feature task autonomously with the
multi-optimizedprofile: … - Implement the issue with
multi-optimizedand leave the result staged for handoff.
How to install om-implement-feature-multi-optimized
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a claude-code2Manually: put the files in place
~/.claude/skills/om-implement-feature-multi-optimized/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/om-implement-feature-multi-optimized/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a codex2Manually: put the files in place
.agents/skills/om-implement-feature-multi-optimized/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a cursor2Manually: put the files in place
.cursor/skills/om-implement-feature-multi-optimized/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install open-mercato/skills skills/om-implement-feature-multi-optimized2Manually: put the files in place
.github/skills/om-implement-feature-multi-optimized/SKILL.md1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a gemini-cli2Platform CLI
gemini skills install https://github.com/open-mercato/skills --path skills/om-implement-feature-multi-optimizedManually: put the files in place
.devin/skills/om-implement-feature-multi-optimized/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about om-implement-feature-multi-optimized
How do I install om-implement-feature-multi-optimized in Claude Code?
Run npx skills add open-mercato/skills --skill om-implement-feature-multi-optimized -a claude-code. The skill file is installed at ~/.claude/skills/om-implement-feature-multi-optimized/SKILL.md.
What does om-implement-feature-multi-optimized do?
It invokes om-implement-feature using the multi-optimized profile, sending implementation work to configured workers and review to independent advisors. The result is staged, with commits, pushes, and publication off limits.
What does om-implement-feature-multi-optimized need to run?
It needs configured model bindings for agentHarness and the requested profile, plus a successful profile probe. If setup is missing or the probe fails, it runs om-setup-agent-harness interactively and retries the same profile.
Source text
SKILL.md · MIT
---
name: om-implement-feature-multi-optimized
description: Thin combined alias for om-implement-feature that uses configured implementation workers and independent review advisors, then leaves the verified feature staged and unpublished. Use when the user says "multi optimized feature", "workers plus model council", "cheap cross-model staged feature", or "zaimplementuj feature multi optimized".
---
# Implement Feature — Multi Optimized
Select the `multi-optimized` profile without duplicating the base workflow.
## Arguments
- `--interactive` (default) or `--autonomous` — pass the execution mode to the base workflow; never enable publication. Reject both together.
- `{brief}` (required) — pass through to `om-implement-feature`.
- `--slug` (optional) — pass through unchanged.
## Chaining
Consume the issue or brief and requested profile. Invoke the base workflow and its lower-level companions by name; stop with the missing name if one is unavailable. Emit the staged handoff, optional `Issue:`/`Spec:` references, and final `WORKTREE=` line. Publication is a separate human-authorized step.
## Workflow
**Claims:** `references/claim-pr.md` governs atomic/fallback ownership and release.
**ALWAYS check first:** Apply `.ai/skills/om-implement-feature-multi-optimized/SKILL.md` when present; safety rules still win.
0. **Agentic setup** — follow `references/agentic-setup.md` before any action: load approved configuration, apply local extensions and shared rules, and preserve the untrusted-content boundary.
1. Read and execute `om-implement-feature` in full with `--profile multi-optimized`.
2. Preserve its worker packets, spec and final councils, same-family independence rule, stage-only boundary, and report.
## Rules
- Shared communication, marker, label, and safety rules: `references/rules.md`. They always apply.
- Do not restate or replace any base workflow phase.
- Treat review from the implementation worker's family as a self-check, not an independent vote.
- When `agentHarness` or the requested profile is missing or fails its probe, stop, tell the user this variant needs configured model bindings, and run `om-setup-agent-harness` interactively — an optimized profile needs an audited implementation worker; adding a reviewer alone cannot unblock it — then re-run with the originally requested profile. Continue under another profile only on the user's explicit, informed request; never substitute one silently.
- Never commit, push, or publish.
© open-mercato · MIT · open-mercato/skills