--- title: Skills with Bundled Scripts slug: skills-with-bundled-scripts type: collection canonical: https://top-agent-skills.com/collections/skills-with-bundled-scripts skills: 33 rubric: 1.0 updated: 2026-08-26 --- # Skills with Bundled Scripts 33 Skills ship executable scripts rather than instructions alone — docling, hyperframes, superpowers and playwright-cli are the deepest. This matters more than it sounds: a Skill that bundles a tested script produces the same output every run, while a Skill that asks the agent to improvise the same logic in Python produces something slightly different each time. If reproducibility is the requirement, start here. 33 Skills, ranked by composite score (https://top-agent-skills.com/about/methodology). ## The picks ### 1. docling — score 66/100 (verified-org) One skill covering every document format the category exists for — including scanned PDFs and RAG chunking — from the maintainers of the parser itself. - Best for: Reading or converting documents the agent cannot open directly, at 65K stars and MIT: scanned PDFs, Office formats, tables, and chunking a corpus for retrieval. - Not ideal for: Producing polished Office files. Docling is a reader and converter — for generating a styled DOCX, XLSX or PPTX, the Anthropic document skills are the better fit. - Publisher: Docling project (LF AI & Data) · MIT - Verified on: claude-code, cursor, codex ```bash pip install docling && uvx library-skills --claude ``` Full entry: https://top-agent-skills.com/skill/docling (https://top-agent-skills.com/skill/docling.md) ### 2. hyperframes — score 64/100 (verified-org) Write HTML, render video. Agent-native, deterministic, no build step. - Best for: Programmatic video an agent can iterate on — release clips, motion graphics, captioned explainers. - Not ideal for: Generative video from a text prompt; that is a model API, not a renderer. - Publisher: HeyGen · Apache-2.0 - Verified on: claude-code ```bash npx skills add heygen-com/hyperframes --skill hyperframes ``` Full entry: https://top-agent-skills.com/skill/hyperframes (https://top-agent-skills.com/skill/hyperframes.md) ### 3. superpowers — score 61/100 (community) Structured multi-step development. Brainstorm → spec → plan → build → review → merge — TDD baked in. - Best for: Long-running engineering tasks where you want each phase to handoff cleanly. - Not ideal for: Quick one-shot tasks — the orchestration overhead is not worth it. - Publisher: obra · MIT - Verified on: claude-code, cursor, codex ```bash npx skills add obra/superpowers ``` Full entry: https://top-agent-skills.com/skill/superpowers (https://top-agent-skills.com/skill/superpowers.md) ### 4. playwright-cli — score 60/100 (verified-org) Microsoft's first-party Playwright skill, invoked through the CLI — the reference implementation for driving a real browser, with no credentials required. - Best for: Driving a real browser from the agent and working with an existing Playwright suite — navigation, assertions, tracing, video, request mocking, and test generation. - Not ideal for: Hosted scraping at scale. It drives a local browser, so rate limiting and anti-bot handling are your problem — reach for a hosted extraction skill when the target fights back. - Publisher: Microsoft · Apache-2.0 - Verified on: claude-code ```bash playwright-cli install --skills ``` Full entry: https://top-agent-skills.com/skill/playwright-cli (https://top-agent-skills.com/skill/playwright-cli.md) ### 5. azure-resource-visualizer — score 59/100 (verified-org) Diagrams generated from live infrastructure rather than from a prompt — it reads the actual resource group and draws what is really there. - Best for: Documenting an Azure estate you inherited, where the useful diagram is the one that matches reality rather than the one in the original design doc. - Not ideal for: Any cloud that is not Azure, and any diagram of a system that does not exist yet — it reads deployed resources, so there is nothing to read before you deploy. - Publisher: Microsoft · MIT - Verified on: claude-code ```bash npx skills add microsoft/skills --skill azure-resource-visualizer ``` Full entry: https://top-agent-skills.com/skill/azure-resource-visualizer (https://top-agent-skills.com/skill/azure-resource-visualizer.md) ### 6. browser — score 58/100 (verified-org) Local browser with no credentials, or a hosted Browserbase session with CAPTCHA solving and residential proxies when the target is protected. Full entry: https://top-agent-skills.com/skill/browserbase-browser (https://top-agent-skills.com/skill/browserbase-browser.md) ### 7. ui-test — score 58/100 (verified-org) Diff-aware adversarial QA: it reads the git diff and tests only what changed, across correctness, accessibility, layout and UX. Full entry: https://top-agent-skills.com/skill/browserbase-ui-test (https://top-agent-skills.com/skill/browserbase-ui-test.md) ### 8. connect-recommend — score 58/100 (verified-org) The marketplace architecture decision, made with a compatibility matrix that blocks invalid Connect configurations instead of describing them. Full entry: https://top-agent-skills.com/skill/stripe-connect-recommend (https://top-agent-skills.com/skill/stripe-connect-recommend.md) ### 9. azure-ai-contentunderstanding-py — score 56/100 (verified-org) Multimodal extraction across documents, images, audio and video through one Azure client — Microsoft-authored, with an explicit trigger list. Full entry: https://top-agent-skills.com/skill/azure-content-understanding (https://top-agent-skills.com/skill/azure-content-understanding.md) ### 10. azure-ai-translation-document-py — score 56/100 (verified-org) Batch document translation that preserves layout — the part that breaks when you translate a PDF by extracting text and re-flowing it. Full entry: https://top-agent-skills.com/skill/azure-document-translation (https://top-agent-skills.com/skill/azure-document-translation.md) ### 11. text-to-speech — score 56/100 (verified-org) Vendor-official voiceover generation across 70+ languages, from the company that defined the category. Ships with evals, which almost no skill does. Full entry: https://top-agent-skills.com/skill/elevenlabs-text-to-speech (https://top-agent-skills.com/skill/elevenlabs-text-to-speech.md) ### 12. speech-to-text — score 56/100 (verified-org) Transcription and subtitle generation as a first-class skill — the media job agents are asked for most and could not previously do well. Full entry: https://top-agent-skills.com/skill/elevenlabs-speech-to-text (https://top-agent-skills.com/skill/elevenlabs-speech-to-text.md) ### 13. dubbing — score 56/100 (verified-org) Localise video while keeping the original speaker's voice — and correct the transcript before regenerating, rather than accepting the first pass. Full entry: https://top-agent-skills.com/skill/elevenlabs-dubbing (https://top-agent-skills.com/skill/elevenlabs-dubbing.md) ### 14. postgres — score 55/100 (verified-org) The generalist Postgres skill the ecosystem was missing — schema, indexing, extensions and migrations, from a Postgres company. Full entry: https://top-agent-skills.com/skill/postgres-aiguide (https://top-agent-skills.com/skill/postgres-aiguide.md) ### 15. postgres-database-migration — score 55/100 (verified-org) Zero-downtime Postgres migrations, with the locking behaviour spelled out — which ALTER TABLE takes an AccessExclusiveLock and what to do instead. Full entry: https://top-agent-skills.com/skill/postgres-migrations (https://top-agent-skills.com/skill/postgres-migrations.md) ### 16. liteparse — score 53/100 (verified-org) Local document extraction with no API key — read the file, not the whole file. Full entry: https://top-agent-skills.com/skill/liteparse (https://top-agent-skills.com/skill/liteparse.md) ### 17. pdf — score 52/100 (official-anthropic) Extract, fill, merge. PDF manipulation with bundled scripts so Claude does not waste tokens generating them. Full entry: https://top-agent-skills.com/skill/pdf (https://top-agent-skills.com/skill/pdf.md) ### 18. block-kit — score 51/100 (verified-org) Slack's own Block Kit skill — and the rare vendor skill that needs no token, because it validates against Slack's public API. Full entry: https://top-agent-skills.com/skill/slack-block-kit (https://top-agent-skills.com/skill/slack-block-kit.md) ### 19. webapp-testing — score 50/100 (official-anthropic) Test local webapps with Playwright. Generation, run, report — end-to-end. Full entry: https://top-agent-skills.com/skill/webapp-testing (https://top-agent-skills.com/skill/webapp-testing.md) ### 20. semgrep — score 50/100 (verified-org) Semgrep's own scanning skill: run the industry-standard SAST engine across 30+ languages, and author custom rules for your codebase's patterns. Full entry: https://top-agent-skills.com/skill/semgrep-scan (https://top-agent-skills.com/skill/semgrep-scan.md) ### 21. code-security — score 50/100 (verified-org) A vendor-maintained rule corpus for secure code review — one reference file per vulnerability class, from SQL injection to Terraform misconfiguration. Full entry: https://top-agent-skills.com/skill/semgrep-code-security (https://top-agent-skills.com/skill/semgrep-code-security.md) ### 22. scan-secrets — score 50/100 (verified-org) GitGuardian's own secret-detection skill — scans history, images and packages, and ships a written remediation doctrine rather than just a list of hits. Full entry: https://top-agent-skills.com/skill/gitguardian-secret-scanning (https://top-agent-skills.com/skill/gitguardian-secret-scanning.md) ### 23. turso-db — score 50/100 (verified-org) The SQLite slot, filled by Turso — and unusually, a skill that actively steers the agent off the stale API surface web search returns. Full entry: https://top-agent-skills.com/skill/turso-db (https://top-agent-skills.com/skill/turso-db.md) ### 24. trail-of-bits — score 49/100 (verified-org) Security audits run by a real security firm. CodeQL + Semgrep + audit workflows. Full entry: https://top-agent-skills.com/skill/trail-of-bits (https://top-agent-skills.com/skill/trail-of-bits.md) ### 25. code-review-security — score 49/100 (verified-org) OWASP-published review, SCA, secrets and threat-modelling skills — the most citable provenance available for security review vocabulary. Full entry: https://top-agent-skills.com/skill/owasp-security-skills (https://top-agent-skills.com/skill/owasp-security-skills.md) ### 26. weaviate — score 49/100 (verified-org) The vector-database skill that ships executable scripts rather than prose — the agent runs the query instead of describing it. Full entry: https://top-agent-skills.com/skill/weaviate-skill (https://top-agent-skills.com/skill/weaviate-skill.md) ### 27. knock-notification-best-practices — score 49/100 (verified-org) The multi-channel notification slot nothing else covers: push, in-app and chat alongside email, with copy guidance per channel. No credentials required. Full entry: https://top-agent-skills.com/skill/knock-notifications (https://top-agent-skills.com/skill/knock-notifications.md) ### 28. docx — score 48/100 (official-anthropic) Word documents end-to-end. Create, edit, comment, track-change. Full entry: https://top-agent-skills.com/skill/docx (https://top-agent-skills.com/skill/docx.md) ### 29. xlsx — score 48/100 (official-anthropic) Excel spreadsheets with real formulas, charts, and formatting — not flat CSV exports. Full entry: https://top-agent-skills.com/skill/xlsx (https://top-agent-skills.com/skill/xlsx.md) ### 30. pptx — score 48/100 (official-anthropic) PowerPoint decks with layouts, charts, speaker notes — programmatic from prose. Full entry: https://top-agent-skills.com/skill/pptx (https://top-agent-skills.com/skill/pptx.md) ### 31. pretty-mermaid — score 48/100 (community) Actually renders Mermaid to SVG or ASCII instead of emitting text and hoping something downstream draws it. Bundles the render scripts. Full entry: https://top-agent-skills.com/skill/pretty-mermaid (https://top-agent-skills.com/skill/pretty-mermaid.md) ### 32. markdown-exporter — score 48/100 (community) The widest format matrix of any conversion skill we catalogue, and it executes the conversion rather than describing it. Full entry: https://top-agent-skills.com/skill/markdown-exporter (https://top-agent-skills.com/skill/markdown-exporter.md) ### 33. agentic-seo-skill — score 46/100 (community) The heavyweight audit machine: 88 evidence scripts so SEO findings come from data, not vibes. Full entry: https://top-agent-skills.com/skill/agentic-seo-skill (https://top-agent-skills.com/skill/agentic-seo-skill.md) --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/collections/skills-with-bundled-scripts._