agentleFS
Sign inStart free
ElasticKnown publisherelastic/oblt-actions/.agents/skills/copilot-review/SKILL.md

copilot-review

Skill6 starsChanged 31 days agoApache-2.0View on GitHub

Review pull requests in elastic/oblt-actions for concrete, high-impact defects using repository-specific checks.

7 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions7 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 7

    1. github/gh-aw★ 5.6ksame name
    2. elastic/oblt-aw★ 4same name
    3. hccnm/pocket-skills★ 4same name
    4. DanaResearchGroup/agent-skills★ 1same name
    5. elastic/oblt-updatecli-policies★ 0same name
    6. gaurav/llming★ 0same name
    7. ultimatile/development-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repositoryOne other file it gives its agents.

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use this skill only when reviewing a pull request in elastic/oblt-actions.

    line 8
  2. Distinctive:

    Read the complete pull request diff.

    line 12
  3. Distinctive:

    Prefer silence when impact or evidence is uncertain.

    line 14
  4. Very specific:

    Check meaningful existing coverage before requesting tests.

    line 15
  5. Distinctive:

    When action metadata changes, check the declared inputs and outputs against callers and the action README.

    line 24
  6. Very specific:

    Use the tool coverage listed in .github/instructions/repository-review.instructions.md.

    line 28

“Common” is measured: kept by at least 6 in 10 of the 6 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

Copilot pull request review

Use this skill only when reviewing a pull request in elastic/oblt-actions. Follow the global review policies in .github/instructions/review-policy-core.instructions.md, .github/instructions/review-policy-security.instructions.md, and .github/instructions/review-policy-tests.instructions.md. Apply .github/instructions/repository-review.instructions.md and, for action or workflow changes, .github/instructions/github-actions.instructions.md.

Review process

  1. Read the complete pull request diff. For each possible finding, inspect only the relevant callers, configuration, tests, and documentation needed to verify it.
  2. Report a finding only when the changed lines introduce or materially worsen a concrete failure. Confirm the repository supports the claim and describe a realistic trigger, mechanism, and user, security, reliability, or operational impact.
  3. Prefer silence when impact or evidence is uncertain. Do not report wording, style, praise, speculative risks, unrelated existing defects, or diagnostics already enforced by CI and pre-commit.
  4. Check meaningful existing coverage before requesting tests. When action behavior changes, look for the action's dedicated .github/workflows/test-<action>.yml or colocated tests; prefer end-to-end tests that invoke the composite action with uses: ./<action-path>.
  5. Report concise, actionable findings tied to changed lines. Identify the failure and impact, then give the smallest corrective action or the specific evidence needed to verify safety.

Repository-specific checks

  • For .github/workflows/trigger-obs-aw-*, compare forwarded secret and environment names with the called elastic/oblt-aw reusable-workflow contract. Keep the trigger inventory in README.md aligned when mappings change; a name mismatch can make a downstream workflow run without the credential it requires.
  • For edot-release/** or .github/edot-release.json, trace tag selection, full-history inputs, release-range output, version changes, and branch handoffs through preparation and finalization. A wrong boundary or handoff can publish an incorrect version or omit contributing pull requests.
  • For oblt-cli/deploy-my-kibana, oblt-cli/undeploy-my-kibana, and their workflows, verify deploy and teardown issue labels remain aligned with the downstream handlers. Mismatched labels can lose a deployment request or leave an environment running after teardown.
  • For aws/auth, azure/auth, and google/auth, check that account, project, tenant, and derived identity values refer to the intended cloud target. Incorrect mapping can authenticate to the wrong account or prevent cloud operations.
  • When action metadata changes, check the declared inputs and outputs against callers and the action README. If the action's runtime behavior changes, verify the end-to-end test exercises the local action rather than only reimplementing its logic.

Deterministic checks

Use the tool coverage listed in .github/instructions/repository-review.instructions.md. Do not repeat pre-commit, actionlint, action README generation, Jest, or Dependabot diagnostics in review comments. Focus on material behavior that those checks cannot establish.

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.

Check your setup, free