How do I install the Harness Gen skill?

Run npx skillmds@latest add specula-org/harness-gen in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Harness Gen safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Harness Gen?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Harness Gen free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Harness Gen?

specula-org (@specula-org) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Harness Gen by specula-org — Agent Skill

Name: Harness Gen
Author: specula-org

Harness Gen

Trace harness generation for SysMoBench. Use when bootstrapping a new task: clone the system into artifacts/<task>/, instrument it to emit NDJSON traces at the task-required granularity, write a run.sh, and produce INSTRUMENTATION.md. One-time work per task; the resulting harness is reused for every spec evaluation via the tv-eval skill.

specula-org 20f00b6 11 files · 72.5 KB Updated Sep 17, 2026

File contents

Read guide.md for the full workflow methodology.

SysMoBench conventions (overrides Specula paths in guide.md)

Cloned source lives at artifacts/<task>/ (see artifacts/README.md).
The task's prompt at tla_eval/tasks/<task>/prompts/ defines what must be modeled — the harness must emit events for each required behavior at the right granularity.
After instrumenting, update tla_eval/tasks/<task>/task.yaml's tv.repo_path to point at the cloned tree, and fill tv.harness (instrumentation_file, test_file, run_command).
Trace output goes to artifacts/<task>/traces/ by default (or a path defined by tv.harness.traces_output_env).
Downstream consumer: the tv-eval skill will re-run this harness when spec evaluation needs fresh/compliant traces.

Orchestration: bootstrap the 9 missing tasks

If you were handed this skill as part of the SysMoBench harness-bootstrap project, read BOOTSTRAP_9_SYSTEMS.md next — it lists the 9 tasks still needing harnesses, repo reuse hints, ordering, and per-task done-criteria.

Frequently asked questions