← all publishers

datarecce

@datarecce source repo

13 published skills

  1. Explain Hypotheses · datarecce
    Explain one ade-bench autoresearch hypothesis, or compare several, in plain words backed by structured comparison tables. Use this whenever the captain asks "what's different between h00XX and h00YY", "explain this hypothesis", "what bug does h00ZZ target", "show the remaining tasks/bugs", or any request to summarize, contrast, or lay out hypotheses, their target tasks, failure types, or results — even if they don't say the word "table". Always reach for this skill for hypothesis explanation so the format stays consistent across the whole loop.
    0
    installs
  2. Recce MCP Dev · datarecce
    Use when modifying recce/mcp_server.py, MCP tool handlers, error classification, or MCP-related tests. Also use when adding new MCP tools or changing tool response formats, or when adding a CheckDAO/RunDAO write in recce/apis/*_api.py (cloud-mode exceptions bypass `except RecceException`).
    0
    installs
  3. Recce MCP E2e · datarecce bundle
    Use when MCP server code is modified and needs smoke verification of the core diff tools against a real dbt project. Triggers after changes to recce/mcp_server.py, MCP tool handlers, single-env logic, or error classification. Also use before merging MCP PRs.
    0
    installs
  4. Linear Deep Dive · datarecce bundle
    Use when given a Linear issue ID, URL, identifier, or project name/URL to analyze and plan work. For issues, fetches the issue, classifies it, explores relevant code, proposes an approach, and orchestrates the right skills. For projects, fetches the project with milestones and issues, builds a prioritized execution plan, and systematically works through issues respecting project structure and dependencies.
    0
    installs
  5. Address Dependabot · datarecce bundle
    Use when consolidating open Dependabot PRs into a single branch. Fetches all open Dependabot PRs from the repo, applies dependency updates locally, tests for breakage, and creates a single PR that closes all Dependabot PRs.
    0
    installs
  6. Recce Review · datarecce bundle
    Review dbt model data changes using Recce. Triggers when: user asks to review data changes, check data impact, run recce review, validate model changes before committing, review a Recce Cloud PR session, connect MCP to a cloud session, pastes a GitHub PR / GitLab MR URL, or pastes a Recce Cloud session/launch URL for cloud-mode review.
    0
    installs
  7. Recce Verify · datarecce
    Lightweight pre-commit verification for dbt model changes in the single-environment dev loop — when the user has a warehouse-connected dbt project but no `target-base/` artifacts. Triggers when: user asks to verify a model change, check whether an edit is safe to commit, sanity-check a filter/aggregation/join change without setting up a base environment, or asks for a quick risk read before running /recce-review. Uses Tier-1 evidence only — column lineage, AST analysis, and targeted current-env SQL probes. Routes to /recce-review when `target-base/` is fresh.
    0
    installs
  8. Dbt CI · datarecce
    Use when generating GitHub Actions workflows for dbt, adding dbt build/test/docs steps, or configuring state-based selection with --select state:modified+. Provides templates for both full builds (CD) and incremental builds (CI).
    0
    installs
  9. Recce Pr Prep · datarecce
    Prepare the Recce part of a pull request. Prints this branch's review findings and what the developer decided about each one, as a markdown table to paste into the PR description. Triggers when: user is opening or creating a PR, is about to commit and push for a PR, asks to bring the Recce findings into the PR, asks what was decided about the findings, or asks for the findings table. Prints that table only — it does not write the PR description, does not open or edit a PR, and reviews nothing. To run a review, use /recce-dev-review.
    0
    installs
  10. Recce Guide · datarecce
    Automatically provide Recce guidance in dbt projects. Triggers when: working in dbt project directory, discussing PRs or data changes, after dbt command execution, or when user asks about data validation.
    0
    installs
  11. Python Uv CI · datarecce
    GitHub Actions workflow steps for Python projects using uv. Use this skill when generating CI workflows that need uv-based dependency installation with virtual environment.
    0
    installs
  12. Recce Dev Review · datarecce bundle
    Review the dbt changes in the current working tree against the team's base in Recce Cloud. Uploads the local `target/` artifacts to a Cloud dev session, attaches the Recce MCP server to that session, and produces an impact report. Triggers when: user asks to review their local dbt changes through Recce Cloud, run a dev review, upload their working tree and review it, or review this branch against the cloud base. Does not attach to a session that already exists — this skill prepares one from the working tree.
    0
    installs
  13. Python Pip CI · datarecce
    GitHub Actions workflow steps for Python projects using pip. Use this skill when generating CI workflows that need pip-based dependency installation with virtual environment.
    0
    installs