Loading...
Loading...
Found 20 Skills
Validates code changes against DeepRead's mandatory patterns and standards defined in AGENTS.md. Use this after writing or modifying code to catch violations before committing.
Auto-generates conventional commit messages from git diffs with tiered format enforcement. Analyzes staged changes to produce meaningful commit messages following Conventional Commits specification.
Runs .continue/agents checks locally against the current diff, simulating the GitHub PR checks experience. Use when the user says /check to review their changes before pushing.
Post-implementation plan verification. Cross-references plans against actual changes for completeness and accuracy.
Analyse code changes since the last docs update and refresh the project's documentation files. Use when code has changed and documentation needs to be updated, after implementing new features, or before a milestone commit.
Hunts complexity in the current diff and APPLIES the simplifications directly to the working tree, then verifies the build. Five angles: reuse (duplicate logic, hand-rolled stdlib, platform features), quality (React/TypeScript hygiene, over-memoisation, exhaustive-deps, `any`, `CLAUDE.md`/`AGENTS.md` violations), efficiency (unnecessary work, missed concurrency, hot-path bloat), altitude (bandaid fixes special-cased onto shared code), and test discipline (repro test per bug fix, useless tests deleted, new tests only when they prevent a named failure). Hand it a `pr-reviewer` report and it applies those confirmed findings too. Use when the user says "tidy this up", "simplify", "clean up this diff", "polish my changes", "make this simpler", "apply the review findings", or "any reuse opportunities?". For a read-only report instead, use `pr-reviewer`; for the PR's title, description, or commits, use `pr-creator`.
You MUST use this, and not the upstream superpowers requesting-code-review skill, when completing tasks, implementing major features, or before merging to verify work meets requirements. The review itself runs the scrutinize-dispatch skill.
Review and understand freshly AI-generated code. Scans the current repo's uncommitted/branch changes and builds a Claude-style light-themed two-column webpage — the left side shows the project folder tree of changed files, the right side displays the syntax-highlighted diff of the selected file (with additions/deletions clearly distinguished from unchanged code), along with a sidebar that presents, for each code segment, the related unit requirement and plain-language code explanation. Trigger with commands like "/understand", "code review this change", "explain the newly generated code", "check this change"