Autoresearch goal

Skill mrzhangguoguo/oh-my-workbuddy/skills/autoresearch-goal

Durable professor-critic research workflow bound to a tracked goal, with validation-gated completion. Use when a research mission needs ongoing goal-focused management plus professor/critic-style validation.From its SKILL.md

Install

npx -y skills add mrzhangguoguo/oh-my-workbuddy --skill autoresearch-goal

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 633 tokens by cl100k_base, as published. Nobody here has run it

Ported from oh-my-codex autoresearch-goal. OMX runtime conventions ($macro invocation, omx CLI, .omx/ state directory) are replaced with WorkBuddy idioms (Skill tool, Agent tool, task list, .workbuddy/memory).

Autoresearch Goal

Use this workflow when a research mission should be bound to a tracked goal while WorkBuddy remains the durable state owner. This is for research projects that need goal-focused management plus professor/critic-style validation; it is not the default answer for ordinary pre-planning best-practice lookup.

Boundary

Do not claim shell commands mutate hidden external goal state — WorkBuddy tracks the goal locally.
Do not edit upstream tooling or add dependencies to satisfy a goal lifecycle.
Track goal status with the task list (TaskCreate/TaskUpdate) and persist durable artifacts under .omw/autoresearch-goal/<slug>/.
Treat the goal as "complete" only via the local completion gate below, not via an external tool's hidden state.

Artifacts

autoresearch-goal writes:

.omw/autoresearch-goal/<slug>/mission.json
.omw/autoresearch-goal/<slug>/rubric.md
.omw/autoresearch-goal/<slug>/ledger.jsonl
.omw/autoresearch-goal/<slug>/completion.json

Flow

Create the mission and professor-critic rubric. Capture in .omw/autoresearch-goal/<slug>/mission.json and rubric.md (topic, rubric, and the critic command/prompt).
Emit the model-facing handoff: summarize the mission + rubric so the active session has a clear objective.
Track the goal with the task list; mark it active as the intended objective.
Research iteratively against the rubric. Record every critic outcome in .omw/autoresearch-goal/<slug>/ledger.jsonl via the verdict command (verdict pass|fail|blocked + evidence).
Completion is blocked until professor-critic validation records verdict=pass. After the mission audit passes, mark the task-list goal complete and record .omw/autoresearch-goal/<slug>/completion.json with the matching goal snapshot.
Treat the completion step as durable local state reconciliation; do not mutate external goal state through shell commands or hooks.
After completion, clear the active goal in the task list before starting another same-session goal.

Completion gate

A passing professor-critic artifact and a matching completed goal snapshot (task-list status complete) are required. Assistant prose, partial tests, or a failed/blocked verdict are not sufficient.

Lifecycle: the task-list goal starts active when the mission is created, and is marked complete after the professor-critic and audit pass. Local artifacts reconcile snapshots and record the cleanup step; they must not mutate hidden external goal state.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.