Agent skills for DeepSeek Harness

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5.

Reasoning, review, and stance discipline for Claude Opus 5 sessions — designed for Opus 5's documented failure modes and also useful when…

Hunt account takeover taxonomy — 9 distinct paths to ATO, plus chains.

Start, stop, and restart the OmniRoute server from the CLI.

Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged…

This skill guides provisioning Hetzner Cloud infrastructure with OpenTofu/Terraform.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Oracle second-model review: bundle prompts/files, debug, refactor, design.

Prepare for the oral trial: case theory, opening statement, interrogation and cross-examination scripts, challenge of…

Open Orbit briefing skill — selected by the Orbit pipeline when Gmail is the user's only connected connector, or when the user explicitly…

Open Orbit briefing skill — selected by the Orbit pipeline when Linear is the user's only connected connector, or when the user explicitly…

Skill for orbital debris risk assessment and mitigation planning

Use when working with OrbStack Linux VMs, Docker on macOS, orbctl commands, or orb machine lifecycle.

Use the public `orca` CLI to operate Orca-managed worktrees, folder contexts, terminals, repos, automations, worktree comments, and the…

Control an Android emulator / device from inside Orca using the `orca` CLI.

Use Orca's Linear CLI through `orca linear ...` commands to read linked ticket context with `orca linear issue --current --full --json`…

Orchestrate fixing a bug — reproduce it as a failing regression test, fix to green, review, and gated commit — by delegating each phase to…

Iterate fresh-context passes against an external done-check within a bound.

Orchestrate a behavior-preserving refactor — confirm tests are green, restructure without changing behavior, keep tests green, review, and…

Coordinate long-running, multi-milestone projects across multiple turns, from conversational discovery through evidence-based completion.

This skill should be used when coordinating multiple subagents, implementing orchestrator patterns, or managing parallel agent workflows.