← all publishers

benchflow-ai

@benchflow-ai source repo

34 published skills

  1. Benchflow 2 · benchflow-ai bundle
    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.
    6
    repo stars
  2. Adaptation Parity · benchflow-ai bundle
    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.
    6
    repo stars
  3. Repo Scrub · benchflow-ai bundle
    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 in git history, license presence, and committer domains. With --fix it untracks .env, adds it to .gitignore, writes a values-blanked .env.example, and scaffolds a LICENSE; --redact-code also replaces secrets found in tracked source. Never rewrites git history automatically — it prints the command instead. Use before publishing, open-sourcing, transferring, or sharing a repository, or when asked to find leaked keys, add a license, or check IP hygiene. Trigger phrases: 'scan for secrets', 'is there an API key in this repo', 'check before open-sourcing', 'add a license', 'clean this repo before sharing'.
    6
    repo stars
  4. Repo Report · benchflow-ai bundle
    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 reproducibility signals, and license class — plus charts over time (commits, merged PRs and active contributors per month), representative code excerpts, up to 3 sample PRs with diffs, and flags for secrets or PII. Runs offline on a local checkout and packages a PDF, an Excel workbook, JSON, CSV and SVG charts into a single zip. Use when asked to profile, summarise, or document a codebase, produce repo statistics, assess test coverage signals, or pull representative code and PR samples. Trigger phrases: 'generate a repo report', 'analyse this codebase', 'repo stats', 'summarise this repository', 'what does this codebase look like', 'pull sample code and PRs'.
    6
    repo stars
  5. Repo Verify · benchflow-ai bundle
    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 source fix (expects PASS). A real FAIL→PASS transition returns verified:true; a build failure, an already-passing test, or a suite needing a live server/database returns verified:false with the reason. Use to confirm a PR's tests actually reproduce the bug it fixes, check whether a fix is covered by a regression test, or validate that a repository's fixes are reproducible. Trigger phrases: 'does this PR have a real regression test', 'verify this fix', 'run the fail to pass', 'check if this PR's tests reproduce the bug'.
    6
    repo stars
  6. Benchflow · benchflow-ai bundle
    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.
    6
    repo stars
  7. Independent Review · benchflow-ai bundle
    Incorporate feedback from an independent code reviewer to improve your solution. The reviewer is a different agent that analyzed your work.
    6
    repo stars
  8. Task Review · benchflow-ai bundle
    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 cheating and skill invocation, and produces a `pr-N-task-timestamp-run.txt` review report alongside a `prN.zip` bundle of trajectories. Use when reviewing a SkillsBench task PR (by number, branch, or local task path), when the user asks to review a task, run benchmarks on a PR, audit a submission, classify a task as research or multimodal track, or prepare a comment to post on a SkillsBench PR.
    6
    repo stars
  9. Task Creator · benchflow-ai bundle
    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, Excel workbook, document, dataset), convert a prompt or a benchmark item into a SkillsBench task, write skills for a task, or prepare a SkillsBench PR. Pairs with `task-review` (run that as a self-check before submitting).
    6
    repo stars
  10. Code Specialist · benchflow-ai bundle
    Delegate complex coding tasks to a specialist model. Use when facing algorithmic challenges, performance optimization, or tricky debugging that benefits from focused code expertise.
    6
    repo stars
  11. Benchflow Traj Upload · benchflow-ai bundle
    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 traj upload, view a session, or pick a session to send. Also use it when they mention the eval prize, benchflow-traj-upload, or "copy this to your agent".
    6
    repo stars
  12. Benchflow Traj Upload Ops · benchflow-ai bundle
    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 metadata, upload progress, idempotency, and production promotion checks. Use this skill when a maintainer or operator wants to test, inspect, or debug a trajectory upload; validate a trajectory, report, or manifest; or verify the public upload path end to end. For helping a contributor submit their own session, use `benchflow-traj-upload` instead.
    6
    repo stars
  13. Benchflow Experiment Review · benchflow-ai bundle
    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 hacking, verifier isolation, metadata completeness, token usage, timing, Daytona-vs-Docker parity, path/root handling, coverage gaps, Docker/Daytona failures, or release-readiness of benchmark data.
    6
    repo stars
  14. Skill Creator · benchflow-ai
    Create a tiny task-specific skill pack for BenchFlow self-gen smoke tests.
    6
    repo stars
  15. Conformance Writer · benchflow-ai
    Write the conformance smoke output file when the task asks for conformance.txt.
    6
    repo stars
  16. Mesh Analysis · benchflow-ai bundle
    Analyzes 3D mesh files (STL) to calculate geometric properties (volume, components) and extract attribute data. Use this skill to process noisy 3D scan data and filter debris.
    6
    repo stars
  17. Finite Horizon Lqr · benchflow-ai
    Solving finite-horizon LQR via dynamic programming for MPC.
    6
    repo stars
  18. Mpc Horizon Tuning · benchflow-ai
    Selecting MPC prediction horizon and cost matrices for web handling.
    6
    repo stars
  19. Flood Detection · benchflow-ai
    Detect flood events by comparing water levels to thresholds. Use when determining if flooding occurred, counting flood days, aggregating instantaneous data to daily values, or classifying flood severity.
    6
    repo stars
  20. Usgs Data Download · benchflow-ai
    Download water level data from USGS using the dataretrieval package. Use when accessing real-time or historical streamflow data, downloading gage height or discharge measurements, or working with USGS station IDs.
    6
    repo stars
  21. Integral Action Design · benchflow-ai
    Adding integral action to MPC for offset-free tension tracking.
    6
    repo stars
  22. Trend Analysis · benchflow-ai
    Detect long-term trends in time series data using parametric and non-parametric methods. Use when determining if a variable shows statistically significant increase or decrease over time.
    6
    repo stars
  23. Citation Management · benchflow-ai bundle
    Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
    6
    repo stars
  24. Nws Flood Thresholds · benchflow-ai
    Download flood stage thresholds from NWS (National Weather Service). Use when determining flood levels for USGS stations, accessing action/minor/moderate/major flood stages, or matching stations to their flood thresholds.
    6
    repo stars
  25. Pcap Triage Tshark · benchflow-ai bundle
    Fast workflow to inspect PCAPs and extract protocol-level details using tshark
    6
    repo stars
  26. State Space Linearization · benchflow-ai
    Linearizing nonlinear dynamics around operating points for control design.
    6
    repo stars
  27. Pca Decomposition · benchflow-ai
    Reduce dimensionality of multivariate data using PCA with varimax rotation. Use when you have many correlated variables and need to identify underlying factors or reduce collinearity.
    6
    repo stars
  28. Suricata Rules Basics · benchflow-ai
    Core building blocks of Suricata signatures and multi-condition DPI logic
    6
    repo stars
  29. Syzkaller Build Loop · benchflow-ai
    Full build workflow for adding new syscall descriptions to syzkaller
    6
    repo stars
  30. Syzlang Ioctl Basics · benchflow-ai
    Syzkaller syzlang syntax basics for describing ioctl syscalls
    6
    repo stars
  31. Syz Extract Constants · benchflow-ai
    Defining and extracting kernel constants for syzkaller syzlang descriptions
    6
    repo stars
  32. Contribution Analysis · benchflow-ai
    Calculate the relative contribution of different factors to a response variable using R² decomposition. Use when you need to quantify how much each factor explains the variance of an outcome.
    6
    repo stars
  33. Suricata Offline Evejson · benchflow-ai bundle
    Running Suricata against PCAPs offline and validating results via eve.json
    6
    repo stars
  34. Meteorology Driver Classification · benchflow-ai
    Classify environmental and meteorological variables into driver categories for attribution analysis. Use when you need to group multiple variables into meaningful factor categories.
    6
    repo stars