Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Execute architectural refactoring from an assessment document with deterministic, chunked operations and aggressive verification at every step. Use when you have an architectural assessment, clean architecture review, refactoring recommendations, or seam-ripper output and need to actually perform the refactoring safely. Also use when asked to "refactor based on this assessment", "execute these architectural recommendations", "fix architectural drift", "refactor in chunks", or any request to systematically restructure a codebase according to a plan. Designed specifically to prevent the kind of agent drift that causes architectural problems in the first place.
Audit websites for SEO, technical, content, and security issues using squirrelscan CLI. Returns LLM-optimized reports with health scores, broken links, meta tag analysis, and actionable recommendations. Use when analyzing websites, debugging SEO issues, or checking site health.
Author or upgrade Model Advisor checks for Simulink and System Composer models. Covers the full lifecycle: guideline authoring, check specification, Model Advisor check implementation, and qualification testing. Use when creating new checks (edit-time, standard batch, config-parameter, auto-fix), converting legacy StyleOne/StyleTwo/StyleThree checks to modern DetailStyle, creating a guideline for modeling, enforcing a modeling rule, or testing/qualifying a check. Triggers on any modeling constraint (e.g., "blocks shall...", "signals must match...", "parameters shall be set to...").
Research-grounded, read-only audit that validates a repository's codebase, architecture, and business logic against real-world knowledge from authoritative sources (arxiv, PubMed, Google Scholar, JSTOR, OpenAlex, Crossref, Semantic Scholar) plus standards bodies (NIST, IETF/RFC, OWASP, ISO, sector regulators). Use when you want an audit that flags algorithms, architectural choices, or business rules violating established norms, standards, or best practices — e.g. 'is our APR calculation correct per lending norms?', 'does our crypto follow NIST?', 'is this consensus approach sound?' — each finding tied to a real, fetched citation. Extracts falsifiable claims across algo/arch/biz layers, routes each to the right source class, verifies against fetched evidence, and adversarially refutes before reporting; emits a severity-graded cited report with UNCONFIRMED for anything ungrounded. Not a linter, SAST, or CVE scanner — it reasons about norms, not syntax.
Write a corrective action report, CAPA, respond to an NCR or audit finding, or document an 8D D5 root cause action. Covers the full CAR structure: root cause analysis, corrective actions, implementation evidence, and verification of effectiveness (VOE) per ISO 9001 §10.2. Use for any quality escape requiring documented systemic corrective action.
A reference for Chinese-language review communication: phrasing templates, severity labels (must fix / suggested change / for reference only), and responses to common anti-patterns in domestic teams. Invoke only when the user explicitly enters /chinese-code-review; do not trigger automatically based on context.
Use this skill when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually works end-to-end. Use the repository bootstrap scripts to standardize the local `clawteam` command and to wire project-local `.agents` and `.claude` skills back to this repository. This skill is repository-development oriented, not a general end-user usage guide.
Writing maintainable code - readability principles, SOLID patterns applied pragmatically, and the judgment to know when rules should bendUse when "code quality, clean code, readability, naming, SOLID, refactor, code review, best practices, maintainable, how should I structure, clean-code, solid, readability, maintainability, code-review, naming, functions, principles" mentioned.
Review code through BurntSushi's "honest machinery" lens — asking whether APIs, invariants, error contracts, performance boundaries, and defaults accurately represent reality. Use when reviewing library APIs, patches that change complexity or cost, dependency additions, or when the user asks "is this API honest?", "will this panic?", "is the cost visible?", "does this scale?", or "are the defaults right?". Works across languages; see REFERENCE.md for Rust-specific elaborations. Do NOT use for deletion/anti-bloat review (use code-review-russ-cox) or product-vs-library tradeoffs (use code-review-mitsuhiko).
Use when the user asks for a styled HTML code review report, a browser-readable review, or both markdown + HTML output. Trigger on phrases like "/code-review-html", "HTML 리뷰 보고서", "styled review report", "review with badges/sidebar". For markdown-only output use `code-review-md`; for in-conversation review use `code-review`.
Control Plan — build, review, or audit a Prototype, Pre-launch, or Production Control Plan linked to PFMEA failure modes and controls. Use when creating a new control plan, updating after a process change or corrective action, or auditing an existing CP for completeness and PFMEA alignment. Covers AIAG Control Plan reference manual and IATF 16949 §8.5.1.
Automated cookie consent validation using Selenium and Playwright. Covers banner interaction testing, consent state verification, tag firing audit after consent choices, regression testing for cookie compliance, and CI/CD pipeline integration.
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
QA an analysis before sharing with stakeholders — methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility
Apply systematic debugging, profiling, and root cause analysis across codebases and technology stacks. Use when investigating bugs, flaky behavior, crashes, stack traces, production issues, memory leaks, performance regressions, or any unexpected behavior where guessing would waste time.
This skill should be used when the user asks to "write tests", "django tests", "pytest", "test factories", "create test", "add tests", "test coverage", or mentions testing Django applications, fixtures, or factory_boy. Provides pytest-django patterns with factory_boy for test data generation.
Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to "dogfood", "QA", "exploratory test", "find issues", "bug hunt", "test this app/site/platform", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.
.NET code quality with Roslyn analyzers, StyleCop, and dotnet format. Covers linting, formatting, and best practices for C#/.NET. USE WHEN: user works with "C#", ".NET", "ASP.NET Core", asks about "Roslyn analyzers", "StyleCop", "dotnet format", ".NET linting", "C# best practices" DO NOT USE FOR: SonarQube - use `sonarqube` skill, testing - use .NET test skills, security - use `dotnet-security` skill
A specialized skill for creating test doubles (mocks, stubs, spies) with NSubstitute. Use when isolating external dependencies, simulating interface behavior, or verifying method calls. Covers complete guidance on Substitute.For, Returns, Received, Throws, and more. Make sure to use this skill whenever the user mentions mock, stub, spy, NSubstitute, test double, 測試替身, Substitute.For, Returns, Received, or dependency isolation, even if they don't explicitly ask for mocking guidance. Keywords: mock, stub, spy, nsubstitute, 模擬, test double, 測試替身, IRepository, IService, Substitute.For, Returns, Received, Throws, Arg.Any, Arg.Is, 隔離依賴, 模擬外部服務, dependency injection testing
Design, review, and diagnose DeepSeek Harness tests and fixtures that can fail nondeterministically under CI concurrency, shared host resources, clocks, process-global state, subprocesses, network listeners, or asynchronous teardown. Use when adding or changing tests with those risks, investigating flaky CI, or reviewing test isolation; use dsh-pre-push-checks separately to select outgoing commands
Multi-agent code review system that spawns three independent Claude sub-agents to review PR diffs. Each agent receives files in different randomized order to reduce ordering bias. One agent focuses specifically on code health and maintainability. Issues are validated using reasoned analysis rather than simple vote counting. Reports merge verdict (YES / NOT SURE / NO). Automatically deduplicates against existing PR comments. Always posts a summary (even if no new issues), with low priority issues in a collapsible section.
Write and review Playwright E2E tests for Langflow. Trigger when the user asks to write, fix, or review E2E tests, spec files, Playwright tests, or integration tests that exercise the full UI. Also trigger when modifying data-testid attributes, test helpers in tests/utils/, or fixture configuration.
(NS) Execute a GitLab issue end-to-end — first-act status, branch-reuse and source-branch gates, single-worktree isolation, atomic delivery, MR lifecycle, mandatory code review gate with bounded fix loop. Use when the user provides a GitLab ISSUE_URL or asks to implement a GitLab issue directly — not for local-only ad-hoc coding (use code-coder) or non-GitLab autonomous runs (use code-autonomous standalone). Delegates actual coding to the code-autonomous engine. Requires mcp-gitlab-usage for MCP and code-reviewer for the review gate.
WHEN: User is writing Go code, asking about Go patterns, reviewing Go code, asking "what's the best way to...", "how should I structure...", "is this idiomatic?", or any general Go development question. Trigger this skill liberally for ANY Go-related development work as a routing hub to specialized skills. WHEN NOT: Non-Go languages, questions entirely unrelated to programming
Use when scanning an AAB or APK for Google Play policy compliance before submission, or checking signing key consistency across releases. Trigger when the user mentions preflight, compliance check, policy scan, pre-submission check, signing key consistency, certificate mismatch, or wants to verify their AAB/APK meets Google Play requirements. Also trigger for questions about restricted permissions, target SDK requirements, 64-bit compliance, hardcoded secrets detection, Data Safety form reminders, foreground service declarations, or App content declarations
Build an ordered, locally-served HTML reading order for a large commit, PR (by number, branch or github url - the repo need not be checked out here), working tree or conflict resolution, grouped by theme, with each file's diff inline in an editable Monaco editor (2-way, or 3-way current | resolution | incoming for a conflict), per-line review notes, and a pan/zoom compare viewer for changed images. Use when a commit/PR is too large to read file-by-file in git-log order and the user wants a guided path through it; to review changed Playwright screenshot baselines / any image diffs visually (the scripted snapshots-only mode needs no authoring at all); and offer it, unasked, straight after you (or another agent) resolve non-trivial merge, rebase, cherry-pick or revert conflicts - before the operation is continued or committed - so the user can check the resolution against both sides.
Diagnose and fix failing GitHub Checks on PR work by default: fetch evidence, write ephemeral ci-fails report, apply fixes, verify locally. Run automatically — do not wait for user to ask. Never merge without authorize merge. Companion to /heyeddi fails.
Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board type, and sensors. Supports timed execution, failure analysis, code-edit suggestions, and iterative re-runs.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.