panjose
UserScientific agent skills for Claude Code and Codex that turn research goals into auditable hypothesis generation, review, ranking, evolution, and synthesis.
Categories
Indexed Skills (42)
co-scientist-pipeline
Run the full Co-Scientist pipeline for one research run.
convergence-check
Evaluate whether a hypothesis newly entered the current top-k set and update the convergence counter deterministically.
evolution-strategy-supervisor
Choose exactly one concrete evolution strategy for the active evolution round.
hypothesis-deep-verification
Run the assumption decomposition and deep verification review for a hypothesis.
hypothesis-evolution-loop
Run the iterative evolution loop from the current persisted run state until convergence.
hypothesis-evolve-coherence
Generate exactly one child hypothesis that improves logical coherence, causal consistency, and assumption hygiene.
hypothesis-evolve-combination
Generate exactly one child hypothesis by combining complementary strengths from multiple parent hypotheses.
hypothesis-evolve-feasibility
Generate exactly one child hypothesis that is more experimentally and operationally feasible than its parent.
hypothesis-evolve-grounding
Generate exactly one grounded child hypothesis by strengthening evidence, specificity, and literature support.
hypothesis-evolve-inspiration
Generate exactly one cross-parent child hypothesis by transferring a useful principle from one parent context into another.
hypothesis-evolve-out-of-box
Generate exactly one divergent but still testable child hypothesis that challenges the shared assumptions of the parent set.
hypothesis-evolve-simplification
Generate exactly one child hypothesis that preserves the core idea while reducing unnecessary complexity.
hypothesis-full-review
Run the full literature-grounded review for a hypothesis.
hypothesis-generate-assumptions
Generate exactly one hypothesis candidate by enumerating and combining testable assumptions.
hypothesis-generate-debate
Generate exactly one hypothesis candidate through a structured scientific debate.
hypothesis-generate-literature
Generate exactly one literature-grounded hypothesis candidate for the active round.
hypothesis-generation-pipeline
Dispatch one enabled generation strategy for a given `ResearchPlan`.
hypothesis-proximity-update
Update hypothesis proximity state by invoking the canonical embedding bridge for one hypothesis.
hypothesis-ranking-pipeline
Update ranking artifacts for one reviewed hypothesis using canonical placement-opponent selection, ranked-frontier selection, tournament judgments, and Elo updates.
hypothesis-review-pipeline
Run the decomposed review pipeline for a single hypothesis and persist each review stage as a structured artifact.
hypothesis-simulation-review
Simulate the hypothesis mechanism and identify failure scenarios.
insights-from-reviews
Extract recurring critique patterns from the completed review of a hypothesis.
island-select
Select the next island strategy and parent hypothesis set for one evolution round.
literature-search
Run the canonical literature search bridge for one evidence query and persist traceable evidence artifacts.
ranking-elo-update
Apply deterministic Elo updates for one completed tournament batch, persist touched hypotheses, and write the ranking update receipt.
research-config
Generate a `ResearchPlan` from `input.md` or equivalent raw research input.
research-overview-pipeline
Generate the final research overview from the top-ranked hypotheses.
co-scientist-run
Bootstrap an existing Co-Scientist run directory from Codex.
co-scientist-start
Start one Co-Scientist run from Codex using a research goal or imported brief.
strategy-router
Produce the current `state/STRATEGY_PLAN.json` bundle for configuration, generation, review, evolution, or overview routing.
hypothesis-initial-review
Run the initial review gate for a hypothesis.
hypothesis-observation-review
Evaluate a hypothesis against prior observations.
hypothesis-review-summary
Summarize the completed reviews for a hypothesis.
co-scientist-resume
Resume an interrupted Co-Scientist run from Codex.
dashboard-snapshot
Assemble a dashboard-ready snapshot from the canonical state.
hypothesis-placement-tournament
Judge one placement-tournament matchup between a candidate hypothesis and one opponent.
hypothesis-ranked-tournament
Judge one ranked-tournament matchup between two top frontier hypotheses.
run-policy-router
Interpret the user's high-level research intent into `RUN_POLICY.yaml` and `state/POLICY_DECISION.json`.
co-scientist-dashboard
Resolve dashboard links for one Co-Scientist run from Codex.
co-scientist-doctor
Diagnose the local Co-Scientist host-agent environment from Codex.
co-scientist-params
Show the supported Co-Scientist start parameters for Codex users.
co-scientist-validate
Validate one Co-Scientist run directory from Codex.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.