Agent Skills in category: Uncategorized

arkweb-security-patch-conflict

Resolve ArkWeb patch merge conflicts while preserving upstream security fix intent.

[ArkWebpatchChromiumGerrit]

arkweb-security-patch-fetch

Fetch and normalize the exact upstream Chromium security patch for ArkWeb integration.

arkweb-security-patch-gitcode-pr

Submit ArkWeb Chromium security patches to GitCode with oh-gc: commit only intended patch files, push to a personal fork branch, create or confirm a GitCode Issue, create a PR to the configured upstream repo, and verify the PR is linked to the GitCode Issue. Use for ArkWeb security patch upstream submission after merge/apply analysis.

[ArkWebsecurityimpactChromium]

arkweb-security-patch-impact

Determine whether ArkWeb M144 or configured baseline is affected by an upstream Chromium vulnerability.

[ArkWebsecurityvulnerabilityChromium]

arkweb-security-patch-intake

Parse ArkWeb security issue inputs such as CVE, Chromium bug, Gerrit CL, PR, and advisory links into an auditable vulnerability intelligence report.

arkweb-security-patch-judge

Judge ArkWeb state-machine step outputs and produce strict verdict JSON for state transitions.

arkweb-security-patch-merge

Apply upstream Chromium patches into ArkWeb with deterministic patch normalization, batch planning, issue-scoped diff checks, and controlled manual merge fallback.

arkweb-security-patch-report

Produce final ArkWeb archive or auto merge report from workflow outputs.

[ArkWebreportarchive]

arkweb-security-patch-review

Review merged ArkWeb security patches for correctness, vulnerability coverage, and regression risk.

arkweb-security-patch-risk

Assess residual risk after ArkWeb security patch merge, review, and build verification.

arkweb-spec-gen

ArkWeb 统一 Spec + 执行计划生成。从 proposal/requirement/design/review/analysis 聚合生成 4 合 1 的 spec.md 和 AC→Task 追溯的 task.md。触发词：生成 Spec、生成执行计划、生成 spec.md。

arkweb-spec-review

ArkWeb Spec 文档评审。可作为独立 subagent 运行。检查文档完整性、一致性、可行性。触发词：评审设计文档、Spec review、检查设计文档、需求评审。

chromium-docs

atelier-orchestrator

atelier-setup

Configure a repository for Atelier's development workflow. Use only when explicitly invoked; inspect existing guidance, issue-tracker and domain-document conventions, preview the proposed configuration, and write only after approval. It does not install Atelier or initialize external tooling.

code-commit

Generate and validate conventional commit messages following the conventionalcommits.org spec. Use whenever the user wants to commit code, mentions commit messages, git commit, or asks to create a commit. Triggers on "commit", "git commit", "conventional", or when reviewing commit message format.

code-handoff

Compact the current conversation into a handoff document for another agent to pick up.

code-pull-request

code-review

Multi-agent code review run as a debate. Critics raise findings in parallel, an Author defends the change, Critics concede or maintain, and a Judge rules on what stays contested. Findings are classified by kind and blocking, and handled durably when previously decided. Use `rq` to request a review of diffs (defaults to main branch), `rs` to respond to findings and record intentional non-fix decisions beside the relevant code. Triggers on "review this", "review my code", "code review", "check for bugs", "audit this", when examining PRs, pull requests, branches, or diffs. Always asks user before applying fixes or adding decision comments.

arb-translation-updater

Add Flutter ARB message keys or synchronize Sanmill translations using the four-locale tail gate. Do not use for isolated wording-only edits.

cpp-formatter

Format or check changed C/C++ source files in Sanmill. Use for C/C++ formatting requests, not general Dart or Rust style checks.

engine-performance-audit

Diagnose Sanmill engine performance regressions, measured hotspots, or deterministic H2H anomalies. Use for those investigations, not routine engine edits or generic UI performance.

flutter-test-runner

Select, run, or diagnose Sanmill Flutter tests and coverage. Use for Flutter validation tasks, not Rust-only tests or prose changes.

game-rule-validator

Check completeness when adding a Mill variant or changing rule mechanics or option structure. Use for those changes and their reviews, not wording-only UI edits.

refactor-parity-audit

Compare a Sanmill port or behavior-sensitive refactor against an identified reference implementation or revision. Use for equivalence work, not ordinary edits or timing-only investigations.

linkedin-automator

Automated LinkedIn outreach for Claude Code. Warm DM connections, reply to messages, build relationships, and grow your network — all through natural conversation, not spam.

charlesdove977

3311

cli-expert

Expert in building npm package CLIs with Unix philosophy, automatic project root detection, argument parsing, interactive/non-interactive modes, and CLI library ecosystems. Use PROACTIVELY for CLI tool development, npm package creation, command-line interface design, and Unix-style tool implementation.

code-review

Provides comprehensive code review covering 6 focused aspects - architecture & design, code quality, security & dependencies, performance & scalability, testing coverage, and documentation & API design. Use this skill for deep analysis with actionable feedback after significant code changes.

css-styling-expert

CSS architecture and styling expert with deep knowledge of modern CSS features, responsive design, CSS-in-JS optimization, performance, accessibility, and design systems. Use PROACTIVELY for CSS layout issues, styling architecture, responsive design problems, CSS-in-JS performance, theme implementation, cross-browser compatibility, and design system development. If a specialized expert is better fit, I will recommend switching and stop.

database-expert

Database performance optimization, schema design, query analysis, and connection management across PostgreSQL, MySQL, MongoDB, and SQLite with ORM integration. Use this skill for queries, indexes, connection pooling, transactions, and database architecture decisions.

devops-expert

DevOps and Infrastructure expert with comprehensive knowledge of CI/CD pipelines, containerization, orchestration, infrastructure as code, monitoring, security, and performance optimization. Use PROACTIVELY for any DevOps, deployment, infrastructure, or operational issues. If a specialized expert is a better fit, I will recommend switching and stop.

docker-expert

Docker containerization expert with deep knowledge of multi-stage builds, image optimization, container security, Docker Compose orchestration, and production deployment patterns. Use PROACTIVELY for Dockerfile optimization, container issues, image size problems, security hardening, networking, and orchestration challenges.

documentation-expert

Expert in documentation structure, cohesion, flow, audience targeting, and information architecture. Use PROACTIVELY for documentation quality issues, content organization, duplication, navigation problems, or readability concerns. Detects documentation anti-patterns and optimizes for user experience.

git-expert

Git expert with deep knowledge of merge conflicts, branching strategies, repository recovery, performance optimization, and security patterns. Use PROACTIVELY for any Git workflow issues including complex merge conflicts, history rewriting, collaboration patterns, and repository management. If a specialized expert is a better fit, I will recommend switching and stop.

github-actions-expert

GitHub Actions CI/CD pipeline optimization, workflow automation, custom actions development, and security best practices for scalable software delivery

jest-testing-expert

Expert in Jest testing framework, advanced mocking strategies, snapshot testing, async patterns, TypeScript integration, and performance optimization

linux-server-expert

mode-exploit

mode-pentest