Connected Chrome
claudeRoute browser work to the agent's user-facing Chrome integration.
18 skills
Run an independent Claude Code review of local code changes, verify its findings, and fix confirmed issues.
Plugin claude-code-review from marketplace imankulov-skills in imankulov/skills. Commands read from the repo's manifest — 28 days ago.
claude-code-reviewRun an independent Claude Code review of local code changes, verify its findings, and fix confirmed issues. Use after implementing a feature or bug fix, before a commit or PR, or whenever the user asks for a Claude, Claude Code, Opus, second-pass, or independent code review. Also use when the user a
connected-chromeRoute browser work to the agent's user-facing Chrome integration. Use when the task requires an existing Chrome profile, its signed-in state, installed extensions, open tabs, or user observation/control. Also use for requests such as "use my Chrome," "open this in my profile," or "test the installed
deep-research-reportRun a multi-question investigation and produce a durable, multi-page research report that lives next to the project: clarify scope, gather evidence with parallel sub-agents and real data, build a zensical site with charts and raw data, then adversarially review and polish it. Use when the user asks
dependabot-configAudit, design, or update GitHub Dependabot configuration in `.github/dependabot.yml`. Use when reviewing whether Dependabot is configured correctly, reducing dependency PR noise, grouping updates, setting schedules or cooldowns, covering monorepos and package ecosystems, or documenting blocked upgra
dependabot-prsTriage, review, test, fix, and merge Dependabot pull requests safely, including a backlog handled in batches by language, package ecosystem, workspace, or subsystem. Use when asked to address, clear, process, review, or merge Dependabot PRs; investigate failed dependency-update CI; assess upgrade re
dependency-cooldownConfigure a minimum release age (cooldown) on package managers so freshly published versions are not installed for N days — a cheap, high-leverage defense against supply chain attacks (npm shai-hulud, axios typosquats, malicious post-install hooks). Use when the user asks to harden a project or thei
django-ninjaDjango Ninja API endpoint patterns including routers, authentication tiers, typed requests, and Pydantic input/output models. Use when writing or reviewing Django Ninja API endpoints, routers, or auth configuration. Also use when creating new API modules or adding endpoints. Do NOT use for: Django v
djangoOpinionated Django development patterns for well-structured, maintainable projects. Use when writing Django models, migrations, views, admin configuration, Celery tasks, or external service integrations. Also use when reviewing or refactoring Django code or creating new Django apps. Do NOT use for:
docstoreDocument-collection data organization for semi-structured repositories. MUST be consulted whenever creating, moving, or organizing files in a repository that declares docstore conventions in its agent instructions file (CLAUDE.md, AGENTS.md, or similar). Also use when the user asks where to put a fi
draftDraft text intended for humans: Slack messages, emails, proposals, summaries, architecture docs, product briefs, or any prose the user wants to review and edit before sharing. Use when the user asks to draft, compose, or write something — even if they don't say "draft" explicitly. Also use when they
editor-contentReview written content for engagement and clarity from a reader's perspective. Use when the user asks to review a draft, find weak spots, check whether content holds attention, or get a content edit on an article, blog post, doc, README, proposal, or any prose. Also use when they say "review this",
editor-copyCopy-edit written content: fix grammar, style, and phrasing errors directly in the file. Use when the user asks to proofread, copy-edit, or clean up an article, blog post, doc, README, email, or any prose. Also use when they say "fix the grammar", "tighten this up", or "do a copy pass". Do NOT use f
editor-pipelineRun a full editorial pass on prose: a content edit (substance, structure, engagement) applied directly, then a copy edit (grammar, style, phrasing). Use when the user wants the whole edit in one step on an article, blog post, doc, README, or any prose. Also use when they say "full edit", "edit pass"
pytestPytest testing standards emphasizing the AAA pattern, fixtures, and parametrize. Use when writing or reviewing Python tests with pytest, including Django tests. Covers fixture organization, database access patterns, API testing, and mock clients. Do NOT use for: JavaScript/TypeScript tests, unittest
pythonOpinionated Python coding standards for clean, type-safe code. Use when writing or reviewing Python functions, classes, type hints, data structures, enums, or module organization. Applies to any Python 3.12+ project. Also use when deciding on app architecture, where to place business logic, how to o
screenshot-makerCreate beautiful, documentation-ready screenshots of web pages or specific page sections. Use when the user wants to capture a screenshot for docs, READMEs, blog posts, or marketing — especially when they mention framing, shadows, rounded corners, blurring sensitive info, or targeting a specific ele
sessionsList past Claude Code sessions for the current project. Use when the user asks to see their session history, find a previous conversation, list past sessions, or look up what they worked on before. Also use when they say "show me my sessions", "what did I work on last week", or "find the session whe
writingGuidelines for clear, human-sounding prose. Use when writing any text humans will read: documentation, Slack messages, emails, commit messages, error messages, changelogs, support responses, marketing copy, landing pages, internal updates, reports, or UI text. Also use when reviewing drafts for AI t
Route browser work to the agent's user-facing Chrome integration.
18 skills
Run a multi-question investigation and produce a durable, multi-page research report that lives next to the project: clarify scope, gather evidence with parallel sub-agents and real data, build a zensical site with charts and raw data, then adversarially review and polish it.
18 skills
Audit, design, or update GitHub Dependabot configuration in `.github/dependabot.yml`.
18 skills
Triage, review, test, fix, and merge Dependabot pull requests safely, including a backlog handled in batches by language, package ecosystem, workspace, or subsystem.
18 skills
Configure a minimum release age (cooldown) on package managers so freshly published versions are not installed for N days — a cheap, high-leverage defense against supply chain attacks (npm shai-hulud, axios typosquats, malicious post-install hooks).
18 skills
Opinionated Django development patterns for well-structured, maintainable projects.
18 skills
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
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
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Action-first, ADHD-friendly output shaping for Claude Code.
1 skill · 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.