river-qa
claudeDiff-aware, pluggable QA for Angular apps: maps a PR to feature manifests, finds Playwright coverage gaps, writes the missing specs against the live app, runs them and separates regressions from test drift.
3 skills · 4 agents
PR review you can read and question in a terminal: a deterministic text map of the change at several zoom levels, pluggable reviewer lenses, findings verified against the diff.
Plugin river-review from marketplace river in cduggn/river. Commands read from the repo's manifest — 1 month ago.
mapDraw a text map of a pull request or branch diff without running any reviewer lenses: logical clusters, changed functions and the flow between them, sized for a terminal and navigable by asking. The fast, cheap way to understand what a PR does before (or instead of) a full review. Use for "map this
reviewReview a pull request (or a local branch diff) as a navigable text map plus verified findings. Builds a model of the change (clusters of files, changed functions, call and data flow between them), renders it as terminal diagrams at several zoom levels, runs pluggable reviewer lenses (blast radius, s
cartographerBuilds the semantic layer of a PR map for river-review. Groups changed files into logical clusters, states what each changed function now does, and records the call and data flow between them, as JSON that a deterministic renderer draws. Read-only.
lens-reviewerReviews a PR through one lens (blast radius, security, correctness, idiom and deprecation, contradiction, tests, or a project-defined lens) for river-review, and writes evidence-backed findings as JSON. Parameterised by a lens brief; read-only.
verifierAdversarial second reader for river-review. Takes findings from lens reviewers and tries to refute each against the code, adjusting confidence and rejecting false positives, before deterministic checks and rendering. Read-only.
Diff-aware, pluggable QA for Angular apps: maps a PR to feature manifests, finds Playwright coverage gaps, writes the missing specs against the live app, runs them and separates regressions from test drift.
3 skills · 4 agents
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.