Interactive companion that guides you through manually reviewing someone else's pull request instead of reviewing it for you. Explains the PR's scope, breaks the change into logical components, and walks through them one at a time while you form your own judgment.
Plugin pr-review-companion from marketplace humantouch in gvillenave/humantouch. Commands read from the repo's manifest — 1 month ago.
pr-review-companionWalks you through reading an unfamiliar codebase instead of summarizing it for you. Presents a map, then guides you component by component while you read the code, predict what it does, and build your own working model.
1 skill
Guides you through diagnosing and fixing a bug yourself instead of patching it for you. Gathers the evidence, poses ranked hypotheses, and walks the investigation one step at a time while you form the diagnosis and write the fix.
1 skill
Stress-tests your system design decisions instead of producing an architecture for you. Interviews you about constraints, poses one trade-off at a time, and challenges each decision you make with concrete failure scenarios.
1 skill
Guides you through writing your own technical document instead of generating one for you. Covers design docs, RFCs, ADRs, runbooks, postmortems, specs, PRDs, proposals (change proposals included), one-pagers, project plans and briefs, READMEs, and more.
1 skill
Guides you through estimating your own work instead of producing estimates for you. Maps what each ticket actually touches — hidden work, unknowns, and how AI-assisted coding reshapes the effort — then you name every estimate and defend it against concrete stress tests. Ends with an estimate sheet verified against your words and sources.
1 skill
Guides you through decomposing a coding project into an execution plan you own instead of generating a plan for you. Mines your docs, tickets, and codebase for the real work and dependencies while you make every scoping, sequencing, and milestone decision — ending with an outline of steps, milestones, and tickets, verified claim by claim against your sources, plus a handoff to doc-coach for the shareable writeup.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Harness-native ECC operator layer - 71 agents, 314 skills, 98 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
200 skills · 98 commands · 71 agents · 1 MCP server · hooks
Security review for Claude-generated code. Pattern-based warnings on edits, LLM-powered diff review on Stop, and an agentic commit reviewer that catches injection, XSS, SSRF, hardcoded secrets, and 25+ other vulnerability classes.
hooks
Advanced git workflows with diff analysis, risk scoring, and reviewer recommendations
2 skills · 1 command · 1 agent
Use Alibaba Open Code Review from local Codex.
2 skills
Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.
13 skills · 9 commands · 1 MCP server
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.