agentleFS
py-econometricspy-econometrics/pyfixest/.agents/skills/pr-review/SKILL.md

pr-review

Skill363 starsChanged 14 days agoMITView on GitHub

Review a pyfixest diff for defects and scope, self-review a change, or guide a requested walkthrough. Explanations use the walkthrough mode rather than launching a full audit.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use oss-pr, pr-automation and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • CES-LtdSkill

    oss-pr

    Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.

    Also in 3 projects that use this

  • CES-LtdSkill

    pr-automation

    PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".

    Also in 3 projects that use this

  • jtenniswoodSkill

    expert-reset

    Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.

    Also in 3 projects that use this

  • jtenniswoodSkill

    updates

    Summarize user-facing project updates from the last 7 days, ordered by importance and written as one-sentence "Feature: description" entries. Use when the user says "/updates", asks what changed recently, or wants a concise list of recent features, device support, fixes that users will notice, or other product value.

    Also in 3 projects that use this

  • openchamberSkill

    clack-cli-patterns

    Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.

    Also in 3 projects that use this

  • openchamberSkill

    drag-to-reorder

    Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.

    Also in 3 projects that use this

  • +6 more from openchamber

The file

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 178 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user wants to review together, follow their pace.

    line 15
  2. Distinctive:

    Use a small, consistent example: show the formula or input, the relevant intermediate values, and how the result changes.

    line 19
  3. Distinctive:

    Check the supported paths, independent numerical evidence, and documented compatibility decisions.

    line 42
  4. Distinctive:

    Use existing verification evidence before rerunning checks.

    line 49

“Common” is measured: kept by at least 6 in 10 of the 178 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review or explain a pyfixest diff

Resolve the intended base and include the relevant working changes. For a stack, distinguish the current layer from its ancestors and the cumulative result. If the displayed diff contains unrelated files, fix the comparison before explaining them.

Guided walkthrough

When the user wants to review together, follow their pace. Start with the concrete problem and the before/after behavior, then suggest the first changed function to inspect. Explain one function or hunk at a time when requested.

Use a small, consistent example: show the formula or input, the relevant intermediate values, and how the result changes. Define names before using them. Connect numerical code to its equation, including shapes, scales, ordering, and weights where they matter. Distinguish outputs you ran from illustrations. Answer the current question directly; a syntax question does not require a fresh review or a test run. Explain tests by the behavior and failure they distinguish, unless the user asks for their mechanics.

Questions about alternatives call for an assessment, not an unsolicited rewrite. Apply requested edits and use the checks appropriate to those edits.

Defect review and self-review

For guidance or documentation, check accuracy, links, consistency, and scope. Numerical tracing applies only to code that can affect results or state.

Prioritize silently wrong results. Trace the changed values through their callers: construction, fitting, inference, post-estimation, and cleanup as applicable. Check mathematical meaning, row/column alignment, weight factors already applied, ownership, and lifetime. Frozen fields do not make contained arrays immutable. Before deleting a wrapper or accessor, inspect subclass overrides and callers; fewer functions alone do not prove a better design.

Check the supported paths, independent numerical evidence, and documented compatibility decisions. Audit tests for distinct failures they catch, not just their count or agreement with the implementation. Apply the scope policy to independent improvements discovered in review.

Use existing verification evidence before rerunning checks. A green suite does not rebut a demonstrated defect. For a cumulative stack review, a later layer's fix resolves the final-stack finding; it does not make the earlier layer independently acceptable.

Report actionable findings first, with file/line references and a concrete failure mode. Separate introduced defects, pre-existing issues, compatibility decisions, questions, and optional cleanup. Say when no findings remain; do not manufacture blockers from naming preferences or unfamiliar syntax. Summarize verification and remaining uncertainty without a second checklist.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.