Loading...
Loading...
Found 208 Skills
Generate production-ready Greptile AI code review configuration for any repository. Use this skill whenever the user mentions Greptile, AI code review setup, PR review configuration, automated code review rules, or wants to set up .greptile/ config files. Also trigger when someone says "set up code review", "configure PR reviews", "add review rules", or asks about Greptile configuration — even if they don't say "Greptile" explicitly but describe wanting AI-powered PR review automation. This skill analyzes the actual repository structure and produces tailored config, not generic boilerplate.
Resolve all PR review comments (human and bot) on current PR. Fetches unanswered comments, evaluates each one, fixes real issues, dismisses false positives, and replies to every comment with the outcome.
Used for reviewing GitCode PRs, generating in-depth review conclusions or publishing line-by-line comments by combining PR metadata, diffs, and the context of the entire code repository. It is used when users want to review a GitCode PR, check a GitCode PR link, analyze change risks, or publish review comments to a GitCode PR. Typical trigger phrases include "review this PR", "inspect this PR", "check PR", or directly providing a GitCode PR link, such as https://gitcode.com/owner/repo/pull/123.
Analyzes code comments for accuracy, completeness, and long-term maintainability. Identifies misleading comments, comment rot, and documentation gaps. Triggers: After adding documentation, before finalizing a PR, when reviewing comments. Examples: - "Check if the comments are accurate" -> verifies comments match code behavior - "Review the documentation I added" -> analyzes new comments for quality - "Analyze comments for technical debt" -> finds outdated or misleading comments - "Are my docstrings correct?" -> validates documentation accuracy
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
Use when creating or revising model PR optimization history documents for SGLang, vLLM, or another serving framework that cite GitHub PRs. Requires manual, per-PR source-diff review and documentation of motivation, key implementation approach, most important code excerpts, reviewed files, and validation implications instead of generated or one-line summaries.
Use when performing a CTO-level PR review — includes staging evidence gate for infra/backend PRs.
Git commit message best practices. Use when writing commit messages, reviewing commits, or setting up commit conventions for a project. Ensures clear, consistent, and useful commit history.
Code review practices with technical rigor and verification gates. Practices: receiving feedback, requesting reviews, verification gates. Capabilities: technical evaluation, evidence-based claims, PR review, subagent-driven review, completion verification. Actions: review, evaluate, verify, validate code changes. Keywords: code review, PR review, pull request, technical feedback, review feedback, completion claim, verification, evidence-based, code quality, review request, technical rigor, subagent review, code-reviewer, review gate, merge criteria. Use when: receiving code review feedback, completing major features, making completion claims, requesting systematic reviews, validating before merge, preventing false completion claims.
Devil's Advocate stress-testing for code, architecture, PRs, and decisions. Surfaces hidden flaws through structured adversarial analysis with metacognitive depth. Use for high-stakes review, stress-testing choices, or when the user wants problems found deliberately. NOT for routine code review (use engineering:code-review). Triggers on "스트레스 테스트", "stress test", "devil's advocate", "반론", "이거 괜찮아", "문제 없을까", "깊은 리뷰", "critical review", "adversarial".
Read-only GitHub triage for issues AND PRs. 1 item = 1 background task (category: quick). Analyzes all open items and writes evidence-backed reports to /tmp/{datetime}/. Every claim requires a GitHub permalink as proof. NEVER takes any action on GitHub - no comments, no merges, no closes, no labels. Reports only. Triggers: 'triage', 'triage issues', 'triage PRs', 'github triage'.
Use when a GitHub Pull Request needs review-thread reply and resolve handling, findings ingestion, and a mandatory final gate in one PR-scoped session.