benchflow-ai

SkillsBench contribution workflow. Use when: (1) Creating benchmark tasks, (2) Understanding repo structure, (3) Preparing PRs for task submission.

SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook,…

SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for…

Methodology for clause-by-clause review of a contract against a structured deviation policy ("playbook"). Covers how to walk a playbook, locate the matching provision in the contract, apply rule types (max-value, must-be-present, must-be-absent,…

Reference for the standard clauses found in commercial non-disclosure agreements (mutual and one-way) — what each clause does, the surface forms it appears in, and how to recognise it in unfamiliar drafting. Use when reviewing, comparing, or extracting…

Read Microsoft Excel (.xlsx) files robustly with `openpyxl` (or `pandas`). Covers multi-sheet workbooks, header rows, empty cells, merged cells, comma-separated list cells, and converting a sheet to a list-of-dicts the rest of your code can consume. Use when…

Build unified multi-level category taxonomy from hierarchical product category paths from any e-commerce companies using embedding-based recursive clustering with intelligent category naming via weighted word frequency analysis.

Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or…

Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. Use this skill whenever the user asks to audit traj health, failed or timed-out runs, healthy pass/fail/timeout status, no-skill leakage, skill loading, reward…

Operate, test, troubleshoot, and explain `bench traj upload` for public or trusted-direct trajectory contributions, including interactive and fully specified commands, dry runs, input validation, local secret masking, trajectory reports and previews, manifest…

Find a local Claude Code or Codex session, open the BenchFlow trajectory viewer, and submit it after the user reviews it. Use this skill whenever someone pastes a BenchFlow eval prize line, wants to submit / share / contribute / upload a trajectory, set up…

SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. Use when the user wants to create a new SkillsBench task, scaffold a task from an existing workflow (notebook,…

SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude and Codex (with and without skills), audits trajectories for…

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.

Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. Use when asked to benchmark an AI coding agent, run a benchmark suite, create tasks, view trajectories, or compare agent performance.

Delegate complex coding tasks to a specialist model. Use when facing algorithmic challenges, performance optimization, or tricky debugging that benefits from focused code expertise.

Generate a metrics report and a shareable deliverable for a git repository: lines of code, language mix, merged PRs and their complexity tiers, test-to-code ratio, untested files, functions/classes, commits, contributors, issue references, CI and…

Scan a git repository for leaked secrets and env keys, a missing LICENSE, and unclear authorship (bot or non-employee committers), then optionally fix the safe parts. Reports secret matches with values redacted, .env files tracked or untracked, secrets found…

Execute a base→gold fail→pass check on a fix pull request to confirm it contains a genuine regression test. Checks out the pre-PR commit in a throwaway git worktree, installs dependencies, applies only the PR's test changes (expects FAIL), then applies the…

Adapt an agent to run on BenchFlow (ACP) and verify it behaves identically inside the eval harness vs standalone — closing the eval↔prod gap. Use when adding a new agent to this repo or checking an existing one for eval/prod behavior parity.