Mirror an existing external repo privately under the user's account and overlay the firmware: clone upstream, strip template-only files, privacy-sweep, run init-project. Use on $adopt-repo <url> or 'pull this repo into our firmware'.
Use on $apply-firmware or to bring the current folder (a plain folder, an existing repo, or an older or partial firmware copy) up to full Harness Firmware in place. To mirror an external repo instead, use adopt-repo.
Use on explicit $external-review invocation or when a launcher prompt names this file. Single-context leaf review of an exact diff scope: no agents, nested reviews, or edits.
Use when work spans context windows or sessions, progress is lost after compaction or retries, or the user invokes $long-horizon or asks to work in verified rounds.
Use when the user asks to reduce per-turn context or token load, trim kernels, skills, or connectors, or propagate a generic context optimization to the starter.
Full multi-reviewer Claude review from Codex: Claude CLI runs impartial-review as Manager with fresh Opus sub-reviewers, then Codex verifies each finding. Use for $opus-fullreview or a full Claude/Opus review with sub-reviewers.
Run measured optimization rounds with independent review for FPS, loading, latency, throughput, and resource use; with no named target, triage every dimension first. Use for $perf-loop or broad performance requests; skip isolated fixes.
Use for an explicit workflow-improvement review, turning the user's preferences into rules or a skill, recurring task friction that may justify a narrow change to skills or project references, or the unattended weekly review (/refine weekly).
Use on $servers, after starting a dev server, or when the user asks what is running, which port is which, why browsers are open, or to close old servers and browsers.
Push an artifact past what people expect from its kind, in any medium. Use for $showpiece, ambitious creative direction, portfolio-quality work, or replacing generic AI styling. Not for quiet or faithful work such as forms, dashboards, exact recreations or brand matching; use the project's UI skill. Skip routine edits unless explicitly invoked.
Use for $wow-loop, wow factor, a target score (\"get it to 8/10\"), or visual work needing reference fidelity or repeated correction, on one deliverable or a set of like items. Skip routine cosmetic edits and discussion of the skill.
Use on $wrapup or when the user asks if a session is done, good to archive, or what is left: one verdict from git, the PR, scratch files and running servers or browsers.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.