--- title: Top Skills for Product slug: product type: vertical-category canonical: https://top-agent-skills.com/top-skills-for-product skills: 16 rubric: 1.0 updated: 2026-08-18 --- # Top Skills for Product **block-kit** is the top-ranked product Skill at 51/100: Slack's own Block Kit skill — and the rare vendor skill that needs no token, because it validates against Slack's public API. PRDs, specs, user research synthesis, roadmap planning, feature exploration. This page lists the Skills useful in this domain, including general-purpose tooling commonly used here — not only Skills built for it. Where a general-purpose Skill outranks the domain-native ones, the introduction below says so. 16 Skills indexed, ranked by a published composite score (https://top-agent-skills.com/about/methodology). Content last changed 2026-08-18. ## The ranking ### 1. 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. - Best for: Composing Slack messages, modals and Home tabs where hand-written Block Kit JSON is the thing that keeps breaking — it validates output against Slack rather than guessing. - Not ideal for: Actually sending the message. It generates and validates layouts; delivery is the sibling slack-api skill, which does need a token. - Publisher: Slack Technologies · MIT - Verified on: claude-code ```bash /plugin marketplace add slackapi/slack-skills-plugin ``` Full entry: https://top-agent-skills.com/skill/slack-block-kit (https://top-agent-skills.com/skill/slack-block-kit.md) ### 2. visualize-data — score 51/100 (verified-org) OpenAI's chart-design skill: the judgement layer that decides which chart the question actually needs before any plotting code is written. - Best for: Getting a chart that answers the question rather than one that displays the data — chart-type choice, encoding, and a QA pass on a figure you already have. - Not ideal for: Library-specific implementation help. It carries visual judgement, not D3 or Vega syntax, so pair it with a plotting library skill when the code is the hard part. - Publisher: OpenAI · MIT - Verified on: codex ```bash npx skills add openai/role-specific-plugins --skill openai-visualize-data ``` Full entry: https://top-agent-skills.com/skill/openai-visualize-data (https://top-agent-skills.com/skill/openai-visualize-data.md) ### 3. build-dashboard — score 51/100 (verified-org) Dashboards with source definitions and a QA step — the parts that separate a monitoring view from a wall of charts nobody trusts. - Best for: A dashboard people will make decisions from, where every metric needs a stated definition and source rather than an unexplained number. - Not ideal for: One-off exploratory charts. The structure it imposes — metric definitions, filters, QA — is overhead when you are just looking at data once. - Publisher: OpenAI · MIT - Verified on: codex ```bash npx skills add openai/role-specific-plugins --skill openai-build-dashboard ``` Full entry: https://top-agent-skills.com/skill/openai-build-dashboard (https://top-agent-skills.com/skill/openai-build-dashboard.md) ### 4. start — score 50/100 (official-anthropic) One-command productivity bootstrap. Memory, tasks, dashboard. - Best for: Setting up the productivity plugin for the first time. - Publisher: Anthropic · MIT - Verified on: claude-code, antigravity ```bash claude plugin install productivity ``` Full entry: https://top-agent-skills.com/skill/productivity-start (https://top-agent-skills.com/skill/productivity-start.md) ### 5. deep-research — score 50/100 (official-anthropic) Cited research reports from fanned-out web search with adversarial verification. - Best for: Any deep, multi-source, fact-checked research request — competitive analysis, technical surveys, market sizing. - Publisher: Anthropic · MIT - Verified on: claude-code, antigravity Install: Built into Claude Code. Invoke with /deep-research. Full entry: https://top-agent-skills.com/skill/deep-research (https://top-agent-skills.com/skill/deep-research.md) ### 6. consolidate-memory — score 50/100 (official-anthropic) Memory hygiene. Merge, fix, prune. Full entry: https://top-agent-skills.com/skill/consolidate-memory (https://top-agent-skills.com/skill/consolidate-memory.md) ### 7. notion-api-skill — score 49/100 (verified-org) Notion API: page/database CRUD, block hierarchies, rich text, schema sync. Full entry: https://top-agent-skills.com/skill/notion-api-skill (https://top-agent-skills.com/skill/notion-api-skill.md) ### 8. 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) ### 9. internal-comms — score 48/100 (official-anthropic) Internal comms that read consistent. Newsletters, status reports, FAQs, updates. Full entry: https://top-agent-skills.com/skill/internal-comms (https://top-agent-skills.com/skill/internal-comms.md) ### 10. research-synthesis — score 47/100 (official-anthropic) Turn raw research into themes, segments, and a prioritized next-steps list. Full entry: https://top-agent-skills.com/skill/research-synthesis (https://top-agent-skills.com/skill/research-synthesis.md) ### 11. user-research — score 47/100 (official-anthropic) Research-ops in a skill. Plan the study, run it, synthesize the findings. Full entry: https://top-agent-skills.com/skill/user-research (https://top-agent-skills.com/skill/user-research.md) ### 12. memory-management — score 47/100 (official-anthropic) Workplace memory that actually understands your team's shorthand. Full entry: https://top-agent-skills.com/skill/memory-management (https://top-agent-skills.com/skill/memory-management.md) ### 13. task-management — score 47/100 (official-anthropic) Lightweight task tracking in a single markdown file. Full entry: https://top-agent-skills.com/skill/task-management (https://top-agent-skills.com/skill/task-management.md) ### 14. update — score 47/100 (official-anthropic) Periodic memory + task refresh from real activity. Full entry: https://top-agent-skills.com/skill/productivity-update (https://top-agent-skills.com/skill/productivity-update.md) ### 15. system-architecture-diagrams — score 42/100 (community) C4, deployment, sequence-of-events architecture diagrams generated from natural-language descriptions. Full entry: https://top-agent-skills.com/skill/system-architecture-diagrams (https://top-agent-skills.com/skill/system-architecture-diagrams.md) ### 16. excalidraw-generator — score 40/100 (community) Excalidraw JSON diagrams from prose, with rendering self-checks. Full entry: https://top-agent-skills.com/skill/excalidraw-generator (https://top-agent-skills.com/skill/excalidraw-generator.md) ## About this category The best agent Skills for product management in 2026 are Anthropic's user-research and research-synthesis — the pair that turns raw interviews into themes, segments and a prioritised list — plus deep-research for cited market work and notion-api-skill or slack-block-kit for getting the output where the team already reads. OpenAI's openai-visualize-data and openai-build-dashboard top the ranking on install volume; they are the reporting half of the job, not the discovery half. Product vertical Skills cover the PM workflow — PRDs, specs, roadmap planning, user research synthesis, feature exploration, A/B test design, prioritization frameworks. The category sits at the intersection of engineering, design and growth, and the strongest Skills here understand all three. The common workflows include drafting a PRD from a problem statement, writing technical specs that engineers can implement directly, synthesizing customer research into prioritized themes, designing experiments with proper sample size and success metrics, building a roadmap that respects engineering capacity, and authoring product launch communications. Several pair with Linear, Monday, ClickUp, Notion, and analytics MCPs for live ticket and metric state. Product managers, founders, growth PMs, and product analysts use these Skills. Composite scoring weights install count, the structure of the artifacts (PRDs that ship vs. PRDs that drift), and how well the Skill handles tradeoffs — Skills that produce confident roadmaps without surfacing constraints rank below those that show their work. ## Common questions **What does a PRD Skill produce?** A structured PRD — problem, goal, non-goals, user stories, success metrics, open questions, rollout plan. The top Skills follow a recognizable template that engineers can read and implement directly. **Do these Skills handle A/B test design?** Yes — they specify the hypothesis, success metric, sample size for a given MDE, and audience definition. They do not run the test; that requires your experimentation platform. **Can these Skills synthesize user interviews?** Yes — research-synthesis Skills cluster raw transcripts into themes, identify recurring patterns, and surface representative quotes. They work best on full transcripts. **Are roadmap Skills aware of engineering capacity?** When paired with Linear or Jira MCPs they read team capacity; otherwise they ask. They are explicit about assumptions rather than guessing. **Do these Skills work for B2B and B2C?** Both — the artifacts (PRDs, specs, research synthesis) are format-stable across product types. Audience-specific Skills (consumer onboarding, enterprise pilot design) are separately tagged. --- _Top Agent Skills. Machine-readable twin of https://top-agent-skills.com/top-skills-for-product._ _JSON: https://top-agent-skills.com/top-skills-for-product.json · whole catalog: https://top-agent-skills.com/skills.json (CC BY 4.0)_