mthines

mthines/agent-skills

Plugin Claude Code

Plugin marketplace listing 3 plugins: agent-tasks-hooks, pr-relevance-memory, pr-reviewer-shape-guard.

mthines/agent-skills

Plugin Claude Code

Agent skills for code review, DX/UX analysis, TDD, holistic analysis, and developer productivity.

mthines/agent-skills

Instructions file

Instructions for mthines/agent-skills, covering agent skills, audience, repository structure, workflow/ — end-to-end orchestrators and quality/ — code, tests, plans, ai apps.

mthines/agent-skills

Agent

Independent fresh-context verifier for bug-fix PRs produced by /fix-bug. Receives only the Evidence Record, the reproduction path/command, the bug-notes ledger (read-only), and the PR diff — explicitly NOT the planner's reasoning, the plan.md, or the executor's reasoning. Runs FAILTOPASS (repro now passes), PASSTOPASS…

mthines/agent-skills

Agent

Independent fresh-context verifier for feature PRs produced by /autonomous-workflow. Receives only the plan.md (Acceptance Criteria, Requirements, File Changes), walkthrough.md, the PR diff, and the project test command — explicitly NOT the planner's reasoning, the executor's reasoning, or any chat history. Runs…

mthines/agent-skills

Agent

Extract evidence from a single Linear ticket — read the ticket, locate affected code, and return an Evidence Record matching the /fix-bug Phase 2 schema. Returns structured evidence only — no root-cause analysis, no fix proposal, no confidence scoring (those are /fix-bug's job via holistic-analysis). Used by…

mthines/agent-skills

Agent

Code reviewer for GitHub PRs — your own (self relation) and other people's (cross relation). Runs a pre-merge gate check (description vs. code, CI, unresolved review feedback, self-review signals, docs) then a multi-lens review — correctness, quality, description accuracy, external integrations, holistic…

mthines/agent-skills

Agent

Context-isolated root-cause analysis. Runs the holistic-analysis skill in fix mode plus confidence in analysis mode inside a fresh sub-agent context, then returns ONLY a compact Root-Cause Record (root cause, causal chain, evidence, ruled-out alternatives, confidence score, proposed fix direction). The verbose 8-phase…

mthines/agent-skills

Plugin Claude Code

Emits lifecycle hook events for the Agent Tasks VS Code extension Sessions panel.

mthines/agent-skills

Hook

Runs when a session starts, executing emit-event.js via node. From mthines/agent-skills.

mthines/agent-skills

Hook

Runs when a session ends, executing emit-event.js via node. From mthines/agent-skills.

mthines/agent-skills

Hook

Runs when you submit a prompt, before the agent sees it, executing emit-event.js via node. From mthines/agent-skills.

mthines/agent-skills

Hook

Runs when the agent finishes a response, executing emit-event.js via node. From mthines/agent-skills.

mthines/agent-skills

Hook

Runs when the agent sends a notification, executing emit-event.js via node. From mthines/agent-skills.

mthines/agent-skills

Plugin Claude Code

GitHub Actions reusable workflow that records PR comment resolution signals into LoreKit, making the reviewer and pr-reviewer agents continuously more accurate per repository.

mthines/agent-skills

Plugin Claude Code

GitHub Actions reusable workflow that validates a POSTED pr-reviewer report body against the report shape contract, from outside the agent.

mthines/agent-skills

Skill Claude CodeCodex

Forces a full holistic re-analysis when a fix or refactor isn't working. Instead of continuing to patch in isolation, this skill triggers a structured step-back analysis that traces the entire execution path end-to-end — from entry point to exit — analyzing each block, every contract boundary, and the full data flow.…

mthines/agent-skills

Skill Claude CodeCodex

Generates, stress-tests, and iteratively evolves ideas for a stated problem — product concepts, features, solution options, strategies — using research-grounded divergent/convergent agent loops: parallel persona generators (nominal-group simulation), independent judges scoring novelty, feasibility, impact, and fit on…

mthines/agent-skills

Skill Claude CodeCodex

Aligns on the scope of a request before any plan or implementation begins — the requirements-elicitation interview a senior engineer runs before touching code. Restates the request and diffs it against the user's words, researches the codebase so questions are specific, surfaces unknowns, non-goals, edge cases, and…

mthines/agent-skills

Skill Claude CodeCodex

Analyzes Playwright E2E trace.zip archives (and bare trace JSONL when unpacked). Extracts the action timeline, network waterfall, console errors, and DOM-snapshot anchors, then identifies the highest-impact problems (flaky waits, slow selectors, network bottlenecks, hung actions, unhandled console errors, navigation…

mthines/agent-skills

Skill Claude CodeCodex

Analyzes React DevTools Profiler exports, Chrome DevTools Performance traces, and Chrome heap snapshots / heap-timelines / heap-profiles. Identifies the highest-impact bottlenecks (long tasks, expensive renders, layout thrash, wasted memoisation, blocking scripts, retained memory, leaks) and proposes concrete code…

mthines/agent-skills

Skill Claude CodeCodex

Guides product analytics and RUM (Real User Monitoring) event tracking in web (React/Next.js) and mobile (React Native/Expo) apps. Decides what user interactions are valuable to capture, what's noise, what's PII to avoid, and how to implement, audit, update, and remove tracking code cleanly. Covers event naming…

mthines/agent-skills

Skill Claude CodeCodex

Records short videos of specific page sections using Playwright's recordVideo API, plays scripted interactions (hover, click, focus, scroll, keypress), crops the output to a target element via ffmpeg, and saves a .webm (or .mp4 / .gif) artifact to .agent/recordings/. Use when a still screenshot cannot prove the change…

mthines/agent-skills

Skill Claude CodeCodex

Analyse a video file — primarily a screen recording of a bug — to extract errors, UI state, and reproduction steps. Resolves input from a Linear ticket URL, a local file path, or a direct video URL. Extracts keyframes with ffmpeg, runs optional Tesseract OCR and Whisper audio transcription, then delivers structured…