y-miyazaki
UserA repository of initial settings around the editor
Categories
Indexed Skills (26)
agent-skills-review
Review SKILL.md quality for Waza readiness and agent-skills-instructions compliance. Use when evaluating SKILL.md quality, checking compliance with skill authoring standards, preparing skills for release, reviewing skill PRs, or running waza readiness checks.
changelog
Survey and update CHANGELOG.md from unreleased commits and undocumented releases. Use in conversation when the user asks to check, review, or update the changelog. Also the loop entry skill when automation supplies commit/release detect JSON. Interactive default is survey only; edit CHANGELOG.md when the user explicitly requests a fix or automation sets may_edit in Constraints.
ci-sweeper
Triage failing CI on integration branches and/or PR heads, classify failures, apply minimal fixes when actionable. Use in conversation when the user asks to triage or fix CI failures. Also the loop entry skill when automation detects failed workflow runs or supplies detection JSON. Interactive default is survey only; edit files when the user explicitly requests a fix or automation sets may_edit in Constraints.
docs-creator
Create or improve documentation files with Diataxis-aware placement and consistent naming. Use when the user wants to create any new documentation, improve existing docs, write a README, or restructure documentation. Also use when asked to "write docs", "improve this doc", "add a tutorial", "update the readme", or any request involving markdown documentation authoring, even if they don't explicitly say "create documentation".
docs-updater
Detect documentation drift and patch affected docs (candidate survey, git hook, range cursor, or detect JSON). Use in conversation when the user asks to sync or update docs after code changes. Also the loop entry skill for documentation drift automation. Interactive default is survey only; edit docs when the user explicitly requests a fix or Constraints allow edits. Not for new document creation or markdown linting.
github-actions-review
Review GitHub Actions workflows for correctness, security, and maintainability. Use when reviewing GitHub Actions workflow PRs, checking workflow security, evaluating CI/CD pipeline design, or assessing permissions and secret handling.
github-actions-validation
Validate GitHub Actions workflows for syntax and security with ORD-01 map key order checks, actionlint, ghalint, and zizmor. Use when committing workflow changes, running CI validation, or checking workflow security issues.
github-pr-body
Update PR body content with deterministic baseline sections and optional full-body completion. Use when creating PRs or regenerating template-driven summaries.
go-review
Review Go code for security, correctness, and maintainability. Use when reviewing Go PRs requiring judgment beyond automated checks.
go-validation
Validate Go formatting, linting, tests, and vulnerabilities for maintainable and secure code delivery. Use when committing Go changes, running CI validation, or debugging failing checks in repositories.
instructions-review
Review instruction and rule files for structure, consistency, applyTo precision, and portable cross-references — package sources (`*.instructions.md`) and distributed agent rule targets (`.cursor/rules/*.mdc`, `.claude/rules/*.md`, `.kiro/steering/*.md`). Use when reviewing instruction PRs, audits, or distributed rule changes after package sync.
markdown-validation
Validate Markdown syntax, formatting, and links using markdownlint-cli2 and markdown-link-check. Use when committing docs changes, checking broken links, or validating Markdown in pull requests.
refactor
Behavior-preserving structural refactors with verification gates. Use in conversation when surveying or applying structural refactors. Also the loop entry skill when automation supplies hints (duplication_block, oversized_unit). Interactive default is survey only; apply edits when the user explicitly requests apply or automation sets may_edit in Constraints. Not for lint-only style, features, behavior-changing bugfixes, or upgrades.
report-tech-debt
Discover and classify technical debt from mechanical signals, then publish a structured report under docs/report/report-tech-debt/. Use for scheduled loop scans or explicit ad-hoc reports from detection JSON. Do not apply code fixes (use refactor) or CI repair (use ci-sweeper). Preferred via on-loop-report-tech-debt.yaml.
shell-script-review
Review shell scripts for security, correctness, maintainability, and Bats suite pairing (TEST-00) with emphasis on operational safety. Use when reviewing shell script PRs requiring judgment beyond static checks, including whether paired Bats suites were added or updated per TEST-00.
shell-script-validation
Validate shell scripts with bash -n and shellcheck for syntax safety and maintainability checks. Does not enforce Bats suite pairing (TEST-00) — companion stem `bats` covers pairing rules. Use when committing script changes, running CI validation, or debugging shellcheck findings in PRs.
terraform-review
Review Terraform quality, security, and architecture decisions. Use when reviewing Terraform PRs requiring judgment beyond automated checks across modules and environments.
terraform-validation
Validate Terraform syntax, linting, and security with terraform fmt/validate, tflint, and trivy. Use when committing Terraform changes, running CI validation, or checking IaC security issues.
tech-debt
Discover and classify technical debt from mechanical signals; apply closed-set fixes when requested. Use in conversation when the user asks to survey or fix safe documentation/dependency debt. Also the loop entry skill for scheduled scans or detect JSON. Interactive default is survey only; write report_file and apply fixes when the user explicitly requests apply or automation sets may_edit in Constraints. Do not apply structural refactors.
issue-autofix
Implement an Issue fix on a branch and open a PR (Fixes #N). Use for L2 issue-autofix automation after autofix label, repository_dispatch, or workflow_dispatch. Detect skips when an open/draft PR already closes the Issue. Do not fire repository_dispatch from the Agent.
issue-triage
Classify GitHub Issues (bug/feature/question/documentation), apply allowlisted triage labels, and post analysis or clarifying questions as Issue comments. Use for L1 issue triage automation or when asked to triage an Issue without opening a PR. Default is API side effects only (labels/comments); do not edit repository files unless Constraints set may_edit true.
pr-revise
Apply human PR review feedback when @loop (or configured mention) is present. Use for L2 pr-revise automation on PR heads. Default landing is push_head; stacked open_pr is caller-selected. Do not invent mention-less triggers.
github-issue-autofix
Implement a GitHub Issue fix on a branch and open a PR (Fixes #N). Use in conversation when the user gives an Issue number or URL and asks to implement or fix it. Also the L2 loop entry skill after autofix label, repository_dispatch, or workflow_dispatch. Interactive default is survey; apply when the user explicitly requests a fix or may_edit is true. Detect skips when an open/draft PR already closes the Issue. Agent must not fire repository_dispatch.
github-issue-triage
Classify GitHub Issues, apply allowlisted triage labels, and post analysis or clarifying questions as Issue comments. Use in conversation when asked to triage an Issue (URL or number) without opening a PR. Also the L1 loop entry skill for Issue events. Default is API side effects (labels/comments); do not edit repository files unless Constraints set may_edit true.
github-pr-revise
Apply human PR review feedback to a pull request. Use in conversation when the user gives a PR URL or number plus the feedback to apply. Also the L2 loop entry skill on PR heads when detect finds a configured mention (@loop). Interactive default is survey; apply when the user explicitly requests apply or may_edit is true. Do not invent mention-less automation triggers or act on bot comments.
loop-verifier
Independent checker for maker diffs in a maker/checker split. Default stance is REJECT until evidence is strong. Use when verifying loop-produced changes, after a minimal-fix or maker agent, or when asked to APPROVE or REJECT a branch diff against stated criteria. Do not implement fixes in this role. Caller-supplied domain rubric (when present in the prompt) is an additional input, not part of this skill.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.