agentsclimarketplace

Replay

Skill whenpoem/aiscientist/skills/replay

An AI-driven research workflow for generating ideas, running experiments, and writing scientific papers.

Install
npx -y skills add whenpoem/aiscientist --skill replay

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

  • 8 stars8 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.

What its author says it does

Copied from the file, not written here

Audit a past pruning or approval decision by creating a counterfactual branch from a saved snapshot without mutating the live graph. Use when the user asks what would have happened under another decision, disputes a paused branch, or wants to inspect an earlier checkpoint.

SKILL.md

2.0 KB, as published. Nobody here has run it

Replay

Replay is an inspection over frozen state. It does not execute new experiments and must not modify live graph nodes, ratings, judgments, or preregistrations.

Workflow

  1. If the user did not provide a snapshot id, call mcp__memory__list_snapshots(limit=20). Show label, timestamp, and counts; do not create a new snapshot merely to replay the past.
  2. Phrase exactly one counterfactual in a falsifiable sentence, such as Approve hyp_07 instead of pausing it.
  3. Call mcp__memory__replay_counterfactual(snapshot_id, counterfactual) and retain the returned branch_id.
  4. Inspect only the recorded snapshot and branch metadata. Do not call model scripts, seed_perturb, or the sequestered-data query tool.
  5. If the analysis suggests a live action, report it as a recommendation. The user may later call resume_branch; replay itself never flips status.

Output shape

Return:

snapshot_id: <snap_...>
branch_id: <replay_...>
counterfactual: <one sentence>
live_graph_mutated: false
evidence: <recorded facts used>
finding: <what changes under the counterfactual>
recommendation: <none or explicit user action>
limitations: <what replay cannot establish without a new experiment>

For several what-ifs, create one replay branch per counterfactual and keep each output independent. Use mcp__memory__list_replay_branches(limit=20) to audit existing branches before adding duplicates.

Completion criteria

Replay is complete when the source snapshot and new branch are identifiable, the live graph is unchanged, every finding cites recorded snapshot evidence, and any proposed live change is clearly left for separate user approval.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.