Tools & Automation

CLI tools, utilities, converters, workflow automation, and productivity helpers

skills in category: 47,515
pages available: 1,980

Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.

Open in full browser

Browse tools & automation skills

Showing 14,449–14,472 of 47,515 skills

Audit UatACross-phase audit of all outstanding UAT and verification itemstoolsbashdocumentationVotes: 0GitHub stars: 102
Analyze DependenciesAAnalyze phase dependencies and suggest Depends on entries for ROADMAP.mdtoolsbashapiVotes: 0GitHub stars: 102
Add TodoACapture idea or task as todo from current conversation contexttoolsbashgitVotes: 0GitHub stars: 102
Add PhaseAAdd phase to end of current milestone in roadmaptoolsbashVotes: 0GitHub stars: 102
Payment IntegrationAImplement payment integration with SePay (Vietnamese payment gateway with VietQR, NAPAS, bank transfers, and cards). Use when integrating Vietnamese payment processing, implementing checkout flows, handling webhooks, processing bank transfers, generating QR codes, or building billing systems for the Vietnamese market. Supports API Key/OAuth2 authentication, virtual accounts, bank account monitoring, and SDK integrations (Node.js, PHP, Laravel).toolsphpnodeVotes: 0GitHub stars: 3
Group Member ApprovalAĐọc và xử lý hàng chờ "Yêu cầu tham gia" của Facebook Group TUYỂN DỤNG F&B [CareerFNB] (631265717502650) bằng agent-browser (Vercel Labs) qua profile Chrome riêng đã xác thực — áp logic SOP, luôn xác nhận với người trước khi bấm Phê duyệt/Từ chối. Dùng khi user nói "duyệt member group", "xử lý hàng chờ tham gia", "chạy phiên duyệt thứ 3/thứ 6", "mở participant_requests". KHÔNG BAO GIỜ tự bấm mà không hỏi xác nhận trước — đây là rào cứng của skill, không phải gợi ý.toolsgobashVotes: 0GitHub stars: 3
Skills DirectorySkills Directory 3 slots · $399/mo · one ad per page · sponsors can never buy grades.See placements
Browser Profile LoginATạo profile Chrome riêng cho agent-browser và duy trì phiên đăng nhập cho bất kỳ site nào cần login (Facebook, Shopify admin, CMS...) khi KHÔNG lái được profile Chrome thật của user (Chrome >=136 chặn cả copy profile lẫn gắn CDP vào profile mặc định). Dùng khi cần agent-browser giữ phiên đăng nhập bền vững, hoặc khi debug lỗi "vẫn ra trang đăng nhập dù URL đúng". Không tự động hoá bước gõ mật khẩu — luôn cần người đăng nhập thủ công một lần.toolsbashdebuggingVotes: 0GitHub stars: 3
Mcp WordpressAWordPress MCP wrapper. Activate for WordPress content ops via an MCP server when available; else falls back to the wordpress-rest curl path. Manages posts, pages, media, taxonomies, SEO meta.toolsgobashVotes: 0GitHub stars: 3
Mcp SendgridASendGrid MCP wrapper. Activate for transactional email, marketing campaigns, deliverability checks, or list management. Routes to MCP tools if available, else generates email templates for manual send.toolsbashapiVotes: 0GitHub stars: 3
Mcp ReviewwebAReviewWeb MCP wrapper. Activate for reputation audits, review monitoring, sentiment analysis. Routes to MCP tools if available, else asks user to paste reviews for analysis.toolsrustgoVotes: 0GitHub stars: 3
Mcp Ga4AGoogle Analytics 4 MCP wrapper. Activate when user needs traffic reports, real-time data, attribution, or any GA4 metrics. Routes to MCP tools if available, else falls back to manual CSV export.toolsgobashVotes: 0GitHub stars: 3
Fixture Linked SkillANEUTRAL SYNTHETIC TEST-FIXTURE SOURCE for `scripts/tests/test_validator.py`, not a shipped skill. It is stored under a neutral `dot-claude/` directory on purpose: `test_docs_paths_links` copies this `paths-tree` fixture into a throwaway temporary repository and materializes `dot-claude` -> `.claude` ONLY there, so the link-resolution cases run against a real `.claude/skills/...` target without this file ever living under a literal `.claude/skills/` path in the tracked tree. WHY the neutral la...toolsVotes: 0GitHub stars: 5
Readonly Scratch WriterARead-only review of build configs; changes nothing in the repository.toolsVotes: 0GitHub stars: 5
Generic ApprovalARecords approval decisions for scope changes. Use when an approval must be recorded.toolsVotes: 0GitHub stars: 5
Clean SkillAFormats diagrams for readability. Use when a diagram needs consistent layout.toolsVotes: 0GitHub stars: 5
Approved Doc WriterARecords a decision note after content-specific approval. Use when a decision needs recording.toolsVotes: 0GitHub stars: 5
Skill Quality ReviewerAReview ONE library skill''s quality — the judgment layer above scripts/validate-skills.py. Runs the mechanical validator first (structure/lengths/registration/name collisions are its job — never re-checked), judges what it cannot: description trigger-oriented ("use when <situation>") vs merely descriptive; trigger collision with shipped skills, colliders NAMED (the main failure mode across the full shipped skill corpus); duplication better shipped as an EXTENSION (the LLM04/ASI04 pattern); ev...toolspythongoVotes: 0GitHub stars: 5
Schema Evolution PlannerAPlan how a live store's schema changes without breaking deployed readers and writers — the expand → migrate → contract sequence (additive first, dual-read/dual-write windows, backfill, contraction only after verified cutover), per-stage compatibility guarantees (old code × new schema, new code × old schema), consumer impact across ORM models, event payloads, and analytics extracts, a deprecation register for columns still physically present, and verification gates per stage. Produces the stag...toolsgoshellVotes: 0GitHub stars: 5
Risk Tiered Validation SelectorAMachine-classify a change''s touched files into impact classes that select validation DEPTH — docs-only fast path, fast tier, or full tier — with a classifier that FAILS CLOSED: unmatched, ambiguous, or error cases escalate to full, never down. Ships tier check bundles, an explicit docs-only definition PLUS a "never docs-only" list (workflows, scripts, schema/migrations, auth/RLS, lockfiles, agent-instruction files), forced-full lists for high-risk surfaces, and diffable rules; aggregation is...toolsrustgoVotes: 0GitHub stars: 5
Local Ci Mirror PreflightAMANUAL-ONLY; never auto-invoke. Explicitly invoke to mirror the repository's CI locally before commit or push. Read PR-triggered workflow checks, derive and run their local equivalents, and verify clean mainline in a separate Git worktree. Classify failures as PR-caused, pre-existing on main, CI infrastructure, or locally indeterminate; report inherited failures without absorbing them. Includes a declared docs-only path and evidence for closeout. Runs only repository-declared checks. Not the ...toolsgogitVotes: 0GitHub stars: 5
Llm Output Safety ReviewerAReview how an application consumes LLM output for improper output handling (OWASP LLM10) — treat model output as untrusted and trace it to each sink: HTML/markdown rendering (XSS), SQL/shell/eval execution (injection, RCE), file paths and URLs (traversal, SSRF), tool arguments, stored-then-reused output (second-order), and AI-generated code before it is saved, committed or run (no auto-run, sandbox, checks, human review gate, provenance). Verify context-correct encoding, sandboxing incl. auto...toolsjavascriptpythonVotes: 0GitHub stars: 5
Human Agent Trust ReviewerAAdversarially review the human-approval layer of an agent system for trust exploitation (OWASP Agentic ASI09) — consent fatigue (approval floods that train rubber-stamping; rate/latency as the signals), deceptive, over-polished justifications making a dangerous action look routine, self-reported summaries diverging from the actual action, dangerous steps bundled in innocuous batches, urgency manipulation, and automation bias as trust accumulates. Where human-approval-boundary places the gates...toolsrustgoVotes: 0GitHub stars: 5
Contribution Guide AuthorADesign a CONTRIBUTING guide that takes a contributor from zero to a merged change — environment setup, the contribution workflow (fork/branch/PR or the project's flow), coding standards and commit/PR conventions, how to run tests and checks locally, the review and merge process, honest expectation-setting (response times, what gets accepted), code-of-conduct and licensing/DCO-CLA pointers, and lowering the first-contribution barrier (good-first-issues, where to ask). Designs contribution guid...toolsrustgoVotes: 0GitHub stars: 5
Ai Misinformation GuardADesign controls against misinformation and overreliance in a large language model (LLM) feature, the Open Worldwide Application Security Project (OWASP) LLM07 category. Require authoritative grounding, checked citations, calibrated uncertainty and refusal, validation before consequential action, and a user experience that shows limits. Cover invented software packages or application programming interfaces (APIs) and human oversight for high-impact outputs. Compose rag-security-architect for r...toolsjavascriptrustVotes: 0GitHub stars: 5