Loading...
Loading...
Found 163 Skills
Review Chinese-to-English translations for accuracy, grammar, terminology, and consistency. Produces a structured review report with prioritized issues. Trigger when: user provides a Chinese document and its English translation for review/checking/proofreading, or mentions "翻译检查", "翻译审校", "translation review", "translation check", "proofread translation".
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.
Audit an AEM Edge Delivery Services page for content quality, SEO, accessibility, performance, and EDS best practices. Produces a prioritized fix list with specific remediation steps. Use when reviewing page quality, preparing for launch, or optimizing existing content.
Review the ECC (everything-claude-code) distribution list, which includes two modes: (A) Existing List Pruning: Analyze the overlap and quality between distribution.yaml.enabled and first-party ai-dev-skills, and output enabled_remove recommendations; (B) New Item Import Evaluation: Based on ecc-catalog.yaml and the scope of the last update, introduce newly added skills from ECC upstream, analyze applicable scenarios, and recommend whether to add them to enabled. Use when: (1) Evaluating whether the ECC distribution list needs pruning, (2) Deciding whether to import after ECC upstream adds new skills, (3) Wanting to generate an ecc-profile.yaml starter for end users, (4) Conducting regular reviews quarterly/semi-annually. Triggers: "Analyze ECC skill", "ECC overlap", "ECC list pruning", "ECC new items", "ECC upstream additions", "Should I import", "ecc analyze", "ecc new items review", "ecc profile starter", "ECC quality review".
Analyzes bounded code for absurd or questionable parts, steelmans why each should stay, and produces an evidence-adjudicated read-only report. Use when asked to challenge, investigate, or review absurd, dubious, suspicious, overcomplicated, or questionable code in a project, repository, directory, file, snippet, diff, commit, branch, or PR.
Comprehensive multi-perspective review using specialized judges with debate and consensus building
Detects entropy signals in a codebase: stale TODOs, disabled tests, lint suppressions, commented-out code, dead imports, empty catch blocks, and deprecated API usage. Designed for daily runs to catch quality erosion early. Do NOT use for feature work, refactoring planning, or security audits.