--- title: "cometweb-agent-skills" description: "CometWeb Labs specialist skills for research, quality workflows, adversarial review, product operations, QA, release readiness, and evidence-based decisions." canonical: https://agentpluginsdirectory.com/plugins/cometweb-agent-skills last-updated: 2026-10-21 --- # cometweb-agent-skills CometWeb Labs specialist skills for research, quality workflows, adversarial review, product operations, QA, release readiness, and evidence-based decisions. - Slug: cometweb-agent-skills - Publisher: CometWeb Labs - Repository: https://github.com/CometWeb-io/agent-skills - Manifest: plugin.json - Version: 2.8.3 - License: MIT - Category (editorial): other - Skills: 34 (ai-council, ai-humanize, artifact-acceptance, benchmark-curator, brief-architect, cometweb-context, competitive-intelligence, competitor-profiling, content-reviewer, content-roaster, content-writer, customer-ops, design-partner-finder, ebook-publisher, evidence-researcher, feedback-integrator, longform-publisher, portfolio-operator, product-operator, product-teardown, quality-loop-operator, release-readiness, repair-operator, repo-roaster, repo-to-roadmap, research-program-operator, rubric-designer, science-roaster, seo-geo-aeo-maxxing, skill-auditor, skill-evaluator, skill-orchestrator-multiagent, skill-orchestrator, web-app-auditor) - MCP servers: 0 - Stars: 1 - Repository created: 2026-08-25 - Repository last pushed: 2026-10-16 - Publisher type: Organization - Listing: https://agentpluginsdirectory.com/plugins/cometweb-agent-skills - Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json ## What cometweb-agent-skills does, in the publisher's words Agent Skills with executable package and contract tests for research, product decisions, QA and release gates, installable in Cursor, Claude Code, Codex and other hosts that read SKILL.md packages. Experimental distribution: task qualification is unestablished for the published packages. Each installed folder and ZIP carries its declared stage and experimental status; see skill maturity for the four stages and the boundary between package checks and task evidence. This repository contains 34 reusable skill packages. Each one is a SKILL.md entry point plus the references, scripts and eval cases it needs, and every package is covered by the test suite. Skills supply instructions and output contracts. They do not supply a model, connector accounts or permission to act: browser access, connectors and external side effects stay with your host and your authorization. From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/CometWeb-io/agent-skills/HEAD/README.md ## Skills - ai-council: Run an always-current, evidence-governed AI decision council for material, high-stakes, multi-domain decisions where options, risk gates, forecasts, and living memory matter. Do not use for routine weekly product prioritization, whole-repo roadmapping, release-candidate gates, customer support tria… - ai-humanize: Naturalize, edit, or substantially rewrite English and Polish prose while preserving meaning, factual constraints, and the author's intentional voice. Do not use merely for generic proofreading, unrelated copywriting, or AI-authorship detection. Use specifically when the user asks to humanize text,… - artifact-acceptance: Run a final evidence-backed acceptance gate on a content, research, documentation, sales, or other knowledge artifact against an explicit brief, required evidence, unresolved findings, and format/QA criteria. Do not use as the final production-release gate for software, to choose among consequentia… - benchmark-curator: Curate and version eval corpora for Agent Skills: case taxonomies, discovery/forced/negative controls, adversarial and regression cases, difficulty strata, holdout isolation, provenance, duplication, contamination, coverage balance, and benchmark hashes. Do not use to run the experiment or claim li… - brief-architect: Turn an ambiguous request for a content, product requirements (PRD), research, sales, documentation, or knowledge artifact into an explicit execution contract with audience, objective, evidence policy, constraints, acceptance criteria, risks, and handoff fields. Do not use to write the final artifa… - cometweb-context: Builds a fresh, provenance-aware context snapshot for CometWeb and its active projects before product, portfolio, strategy, GTM, pricing, outreach, meeting, content, or advisory work. Do not use for simple conceptual questions or when one direct authoritative source is sufficient. Use when the requ… - competitive-intelligence: Continuous competitive intelligence and competitor change detection. Do not use for a one-time initial deep profile with no monitoring intent (prefer a dedicated competitor-profiling skill when one is installed), for extracting a competitor's mechanisms to adapt into your own product (use product-t… - competitor-profiling: Build an evidence-backed initial competitor profile from public and supplied sources, covering company, ICP, positioning, product surface, pricing, proof, discovery channels, uncertainties, contradictions, and a normalized handoff to Competitive Intelligence. Use for a first deep baseline or dossie… - content-reviewer: Review an existing piece of content constructively against its brief, intended reader, factual/evidence requirements, structure, clarity, specificity, usefulness, and internal consistency. Do not use for adversarial roasting, full rewrites, evidence collection, humanization-only editing, or final r… - content-roaster: Run evidence-anchored adversarial reviews of marketing, sales, product, editorial, and long-form content: landing and pricing pages, offers, emails, articles, case studies, ebooks, docs, and sales decks. Do not use for scientific peer review (science-roaster), code critique (repo-roaster), rewrite-… - content-writer: Write evidence-aware informational or editorial prose (articles, guides, reports, documentation, research-backed explainers) from a brief or clear request. Do not use for persuasion-first landing copy, ads, or cold email, copy-editing or humanization-only rewrites (ai-humanize), long-form publicati… - customer-ops: Run the operational customer-to-resolution loop across support conversations, customer cases, incidents, account risk, commitments, internal handoffs, feedback clusters, and GitHub engineering work. Do not use for broad VOC/persona research, retention-program design, general CRM architecture, analy… - design-partner-finder - ebook-publisher - evidence-researcher - feedback-integrator - longform-publisher - portfolio-operator - product-operator - product-teardown - quality-loop-operator - release-readiness - repair-operator - repo-roaster - repo-to-roadmap - research-program-operator - rubric-designer - science-roaster - seo-geo-aeo-maxxing - skill-auditor - skill-evaluator - skill-orchestrator-multiagent - skill-orchestrator - web-app-auditor Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.