Shape agent capabilities into your workflow.

Provide a taxonomic scope, trait, seed papers, and optionally a curated dataset. The agent proposes a schema and project-specific validation hooks for approval, then searches, fetches, and processes literature in batches. A record reaches the CSV only after its quoted evidence and page are checked against the hashed source PDF, with provenance retained in an append-only ledger.

The skill gives Claude Code reference material, reusable TaxEngine patterns, and calculation checks for SST, GST, and VAT implementations. Its strongest documented coverage is Malaysia and Singapore, while the Thailand material remains a skeleton. Income, payroll, and corporate taxes are outside scope, and production rates still require official or professional verification.

Enter workload details through Claude Code commands to receive a 7R recommendation, blocker triage, readiness scoring, and focused assessments for containers, databases, networks, or VMware estates. The skill can also draft wave plans, cutover runbooks, portfolio reports, and rough cost estimates. Its methodology and guardrails are stored locally, so no MCP server is required.

Point Claude at one paper or a folder of PDFs. The skill extracts a DOI when possible, resolves metadata through CrossRef or Semantic Scholar, and renames files in an author-title-year format with collision handling. Scanned documents can use Tesseract or Claude vision, while the local processing path requires PyMuPDF and additional OCR dependencies when needed.

The skill handles formatting patterns common in ChatGPT DeepResearch DOCX exports, including headings, nested lists, code fences, Mermaid diagrams, tables, Office MathML, and bibliography-backed citation links. It verifies the generated Markdown for broken math, diagram labels, and citation formatting. The converter mainly depends on python-docx and can run in an isolated uv environment.

A PostToolUse hook records tool calls that were not covered by existing allow rules and therefore required manual confirmation. The analyzer filters those entries by project, groups repeated command patterns, and presents suggested permission rules with examples. Nothing is added automatically: the user chooses which proposals should be written to Claude’s settings.

Pass a source path to the Claude Code command and the skill uses showboat to produce a linear explanation of the codebase. The resulting walkthrough is intended to guide readers through structure and implementation in a deliberate order. It requires the showboat command to be installed and available on PATH before use.

Bazaar treats GitHub repositories tagged `claude-skill` as discoverable skills and exposes local commands for searching, viewing, installing, publishing, and following creators. It uses an authenticated GitHub CLI underneath, so there is no separate backend or marketplace account to maintain.

This Claude Code skill keeps a small `TODO.md` table for browsing and stores each task's context, guidance, notes, and work history in its own Markdown file. Commands can add, start, update, finish, reopen, or remove tasks without loading the entire backlog. The split layout scales better for long-running projects, at the cost of creating more files in the repository.

Provide a product idea or URL and the skill evaluates it through the five TELOS dimensions, then returns a go, no-go, or conditional-go recommendation. Quick, standard, and deep modes trade speed for research and estimation detail, while the report can cover team needs, costs, risks, milestones, and next steps. It is intended for early product planning and go/no-go decisions.

Roast challenges an idea, feature brief, or rough concept instead of defaulting to validation. It examines whether the problem is real, whether the value justifies the complexity, what the product would lose, and what conditions must be met to proceed. The result is a direct build, do-not-build, or major-rethink verdict for PMs, designers, and builders.

Project Navigator searches your Claude conversation history for decisions, prior deliverables, evolving ideas, and current project status. Its pattern mode can extract the structure or method used in earlier work and present it as a reusable template before applying it again. It uses Claude's built-in search rather than external storage, so results depend on what those tools can surface and cannot restore old files directly.

Seven-Lens Review makes Claude examine a target through contracts, state transitions, boundaries, security, cross-component consistency, dead interfaces, and test gaps in one pass. The checklist is language-agnostic and works best on features spanning several files, where individually reasonable components can still disagree. It is a single skill file with no added dependencies.

Describe a scenario in plain language and the skill follows it from the entry point through every real call site. It tracks how values, formats, and units change, then flags stale credentials, missing consumers, partial updates, unit mismatches, or swallowed errors. This is useful when each file looks correct alone but the full interaction fails.

Describe the systems you already run and the skill maps where AI could add value, compares integration patterns, and generates starter code for MCP servers, API connectors, RAG pipelines, middleware, or event-driven agents. It also covers deployment, monitoring, security controls, cost estimates, and phased rollout planning. The focus is early architecture and implementation scaffolding for enterprise teams.

Adversarial Audit executes the repository's claimed test and smoke commands instead of trusting source inspection or a zero exit code. It checks skipped tests, weak assertions, swallowed failures, hanging processes, and both the blocking and allowing sides of security gates. The skill is aimed at finding false-green CI and verification gaps that reading alone misses.

Verify by Execution requires reproducing the problem before changing code and rerunning the exact scenario afterward. Every conclusion includes the command, relevant output, and a pass, fail, hang, or skip result. Its rules also cover full test suites, clean-state checks, both sides of security gates, and unset, empty, valid, or invalid environment variables.

ArkTS Patterns gives Claude reference-guided workflows for state management, lifecycle, concurrency, navigation, networking, persistence, gestures, and project scaffolding on HarmonyOS NEXT. The skill routes each task to stable documentation and templates, while optional DevEco MCP tooling can add current API lookup, builds, launches, and UI verification. Basic use still works offline, but live checks remain unverified.