clawfu-skills
clawfu-skills is an MIT-licensed collection of structured “marketing skills” (159 described in the README) meant to be used by AI agents, primarily via an MCP server entrypoint (npx @clawfu/mcp-skills). Each skill is stored as a SKILL.md file with YAML frontmatter, and includes guidance such as when to use, expected AI vs human actions (“What Claude Does vs What You Decide”), and “Skill Boundaries”/limitations.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
The provided material does not document authentication/authorization, secret handling practices, or TLS requirements for the MCP runtime. As a prompt/skill library, it is mainly a guidance artifact, but using it via an agent still implies prompt-injection risk and data-handling risk in the surrounding agent environment. Because details about dependencies and server implementation are not provided, dependency hygiene can’t be verified from the supplied content.
⚡ Reliability
Best When
You want an MCP-enabled agent to draw from a curated library of marketing methodologies with consistent formatting and human/AI separation.
Avoid When
You need strict operational guarantees (SLA, idempotency semantics, pagination conventions, or clear error codes/rate-limit headers) based on the information available here.
Use Cases
- • Generating marketing deliverables (positioning, copywriting, offers, negotiation, sales frameworks, etc.) using standardized, reusable prompts
- • Agent-assisted marketing workflow design and multi-skill orchestration (as implied by the “skill orchestrator” / multi-skill workflows category)
- • Providing structured guidance to ensure a human-in-the-loop (centaur mode) for creative/strategic decisions
- • Onboarding and internal enablement for marketing best practices (as skills/methods templates)
Not For
- • Production systems requiring guaranteed factual accuracy of marketing claims without human review
- • Use cases needing a stable, documented REST/GraphQL/SDK contract for programmatic consumption (documentation for such APIs is not provided in the README)
- • Security- or compliance-critical automation without additional controls and review
- • Workloads that require explicit rate-limit or retry behavior guarantees (not documented in the provided content)
Interface
Authentication
No authentication mechanism is described in the provided README content for the MCP entrypoint.
Pricing
No usage-based pricing information is provided in the supplied content.
Agent Metadata
Known Gotchas
- ⚠ The README shows installation/config patterns for MCP but does not describe MCP tool schemas, parameters, or output formats; agent integration may require inspecting the MCP implementation directly.
- ⚠ No documented error codes, retry behavior, or rate-limit headers are included in the provided content.
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for clawfu-skills.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.