dsh-record-replay: Recording macOS Desktop Operation Demos as Agent Skills
dsh-record-replay is a DSH workflow plugin maintained by humblebanana, integrating the Open Record/Replay macOS recorder into Harness. It provides the open-record-replay skill and orr_* tools. Agents can record user demonstrations, validate events.jsonl, package skill-input, and pass it to the host Skill Creator or the built-in orr_skill_create to generate a Skill. It exclusively supports macOS and requires Node.js >= 22.19 along with a local open-record-replay checkout.
Read MoreTurn macOS Desktop Demonstrations into DeepSeek Harness Skills with dsh-record-replay
dsh-record-replay is a DeepSeek Harness plugin maintained by humblebanana that integrates Open Record/Replay into the runtime: it uses the `orr_*` tools to record macOS desktop demonstrations, verify `events.jsonl`, and then packages the files for the host Skill Creator. This article verifies the installation commands, `repoRoot` configuration, the rollback of `orr_skill_create` in version 0.2.0, as well as the privacy boundary between Accessibility permissions and local recording by cross-referencing with the directory page and GitHub repository.
Read MoreAdd macOS Computer Control to DeepSeek Harness with dsh-computer-use
DSH-Computer-Use is a DeepSeek Harness tool plugin maintained by Anionex, which provides native macOS computer control for intelligent agents. It conducts real-time observations based on the accessibility tree, rejects expired states, divides read and write permissions by application, and tries its best not to move the system cursor or inject pointer events into the global desktop. This article checks the installation commands, Skill loading methods and capability boundaries against the community directory page and GitHub README. Currently, it only supports macOS 14 and above, with the early version 0.1.0.
Read More