om-implement-feature-optimized — Claude Code skill: install
The om-implement-feature-optimized Claude Code skill delegates feature implementation to configured model workers. It activates for requests to build a feature with workers and leaves verified changes staged, not published.
MIT 501 installs ★ 282 updated 2026-10-22
npx skills add open-mercato/skills --skill om-implement-feature-optimized -a claude-codeWhat om-implement-feature-optimized does
The skill selects the optimized profile for the om-implement-feature workflow. It passes through the required {brief} and optional --slug argument. Choose either --interactive or --autonomous; the two modes cannot be combined.
Execution starts by loading approved configuration, local extensions, and shared rules. The base workflow then handles bounded implementation packets and validates the result. If the configured worker or profile fails its probe, the run stops instead of falling back to implementation by the host alone. The optimized profile requires configured model bindings and an audited implementation worker. Setup runs interactively through om-setup-agent-harness, after which the workflow retries with the originally requested profile.
The verified feature is left staged for handoff, with publication disabled. The skill never commits, pushes, or publishes; a person must authorize publication separately.
What it helps with
- delegate feature implementation to configured model workers
- split a feature brief into bounded implementation packets
- leave a verified feature staged without publishing it
Example prompts for the agent
- Implement this feature brief with the configured model workers: {brief}
- Build the feature in autonomous mode with the optimized profile: {brief}
- Implement {brief} using --slug {slug} and leave the changes staged, not published
How to install om-implement-feature-optimized
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-optimized -a claude-code2Manually: put the files in place
~/.claude/skills/om-implement-feature-optimized/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/om-implement-feature-optimized/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-optimized -a codex2Manually: put the files in place
.agents/skills/om-implement-feature-optimized/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-optimized -a cursor2Manually: put the files in place
.cursor/skills/om-implement-feature-optimized/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install open-mercato/skills skills/om-implement-feature-optimized2Manually: put the files in place
.github/skills/om-implement-feature-optimized/SKILL.md1Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-optimized -a gemini-cli2Platform CLI
gemini skills install https://github.com/open-mercato/skills --path skills/om-implement-feature-optimizedManually: put the files in place
.devin/skills/om-implement-feature-optimized/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add open-mercato/skills --skill om-implement-feature-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-optimized
How do I install om-implement-feature-optimized in Claude Code?
Run npx skills add open-mercato/skills --skill om-implement-feature-optimized -a claude-code.
What does om-implement-feature-optimized do?
It runs om-implement-feature with the optimized profile, delegates bounded implementation work to configured model workers, then leaves the verified feature staged and unpublished.
What does om-implement-feature-optimized need to run?
It needs a feature brief and configured model bindings, including an audited implementation worker. If the worker or profile fails its probe, the run stops; configure the bindings interactively with om-setup-agent-harness.
Source text
SKILL.md · MIT
---
name: om-implement-feature-optimized
description: Thin worker-optimized alias for om-implement-feature that delegates bounded implementation packets to configured models, then leaves the verified feature staged and unpublished. Use when the user says "optimized feature build", "use model workers", "cheap staged feature", or "zaimplementuj przez workerów".
---
# Implement Feature — Optimized
Select the `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-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 optimized`.
2. Preserve its packet boundaries, host integration, validation, stage-only boundary, and handoff report.
## Rules
- Shared communication, marker, label, and safety rules: `references/rules.md`. They always apply.
- Do not restate or replace any base workflow phase.
- If no selected worker is ready, the runtime `probe` exits non-zero and the run is blocked: stop, report the failed probe, and never silently downgrade to host-only implementation.
- 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