Create a short, repeatable terminal GIF from real commands run against caller-selected executables. The skill helps demonstrate one observed behavior or compare a controlled before-and-after change, while keeping the tape and evidence local for review.
Use this skill to explore a CLI goal by choosing observable checks within an approved scope. It guides the agent through preparation, one exercise, and immediate validation for each case, then helps report what the evidence established and what remained unreachable.
Review GitHub CLI (`gh`) pull requests by checking their intent, related issues, repository rules, and code changes. Receive findings grouped by severity, with attention to bugs, breaking changes, missing tests, and reviewability.
Manage Agent Skills through `gh skill`: search for skills, preview their contents, install them for a chosen agent, update installed copies, and publish a repository as a discoverable skill source.
Assess open Dependabot pull requests by comparing upstream changes with repository usage and available evidence. Post one concise recommendation with a confidence level; the skill does not merge, approve, close, or label requests.
For authorized GitHub CLI maintainer work, this skill selects one small, verifiable technical debt issue, fixes it, tests the change against a recorded baseline, and opens a review-ready pull request. It follows repository rules and stops when preconditions or validation fail.
Exercise a real command-line program with specified cases or a stated goal, then capture and verify the observed behavior. It produces local media evidence such as a session video, helping reviewers see what the command did without treating the recording as proof of general correctness.
Run and record CLI exercise cases through a shared Go runtime and Tuistory adapter. The skill follows approved setup, exercise, validation, and cleanup phases, captures observed terminal behavior, and preserves execution evidence and chronology.
Use this skill to execute supplied CLI test cases without changing their commands, inputs, ordering, or assertions. It guides preparation, exercise, and validation case by case, then classifies results as passed, failed, blocked, or observed based on actual evidence.
This dispatcher helps with GitHub Agentic Workflows by identifying whether a request is about design, creation, configuration, updates, debugging, or upgrades. It selects the matching workflow prompt or skill file so the agent can follow task-specific guidance.
This reference helps agents use GitHub CLI (`gh`) to retrieve and shape issue, pull request, repository, and discussion data. It explains structured output, pagination, repository targeting, search choices, and when to fall back to `gh api` for fields the typed commands do not expose.
Use this skill to add or revise GitHub CLI acceptance tests, which exercise `gh` against live GitHub resources. It guides fixture selection, safe cleanup, API request budgeting, asynchronous waits, and focused validation.
Verify CLI exercise expectations against recorded evidence, render requested media, inspect the results, and return local artifacts with case outcomes. The workflow keeps failures visible and does not publish evidence by default.
This internal module checks whether cli-exercise can use its required build, terminal, and media tools. When a dependency is missing, it identifies a suitable setup path and requires approval before installation, then rechecks readiness. It does not authorize recordings or other actions.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)