Architecting cross-tool conversion flows that match audience and stage. Landing page to lead magnet to nurture sequence to offer to advanced funnels. Honest about silo-funnels (every tool standalone), kitchen-sink-funnels (every audience squeezed through one path), and matched-funnels (architecture matched to audience-and-stage) patterns. Triggers on funnel design, conversion architecture, marketing funnel, growth funnel, lifecycle architecture, nurture sequence design, multi-tool funnel orchestration. Also triggers when the team's growth tools are working individually but not together, when audience segments share one nurture path, or when a funnel is being architected from scratch.
47
49%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/funnel-flow-architecture/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong description that clearly articulates specific capabilities around funnel architecture with well-defined patterns and comprehensive trigger terms. The explicit 'Triggers on...' clause and situational triggers ('when growth tools are working individually but not together') are particularly effective. Minor weakness is potential overlap with adjacent marketing skills, though the architectural framing helps differentiate it.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and patterns: landing page to lead magnet to nurture sequence to offer, identifies three distinct funnel patterns (silo-funnels, kitchen-sink-funnels, matched-funnels), and describes cross-tool conversion flow architecture. | 3 / 3 |
Completeness | Clearly answers both 'what' (architecting cross-tool conversion flows, matching audience and stage, identifying funnel patterns) and 'when' (explicit trigger terms listed, plus situational triggers like when tools aren't working together or when a funnel is being built from scratch). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including 'funnel design', 'conversion architecture', 'marketing funnel', 'growth funnel', 'nurture sequence design', 'multi-tool funnel orchestration', plus situational triggers like 'growth tools working individually but not together' that match real user language. | 3 / 3 |
Distinctiveness Conflict Risk | While the funnel architecture focus is fairly specific, terms like 'marketing funnel', 'nurture sequence', and 'conversion architecture' could overlap with skills focused on email marketing, copywriting for landing pages, or general marketing strategy. The three named patterns (silo/kitchen-sink/matched) add some distinctiveness but the domain is broad enough to risk conflicts. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads as a marketing philosophy essay rather than an actionable skill for Claude. It is extremely verbose, restating its core thesis (matched-funnels > silo/kitchen-sink) multiple times across sections and two closing sections. It lacks any concrete deliverables, templates, executable examples, or step-by-step workflows that would enable Claude to actually architect a funnel. The progressive disclosure structure is reasonable in concept but undermined by the bloated overview layer.
Suggestions
Replace the philosophical narrative with a concrete step-by-step workflow: e.g., Step 1: Define audience segments (provide a template matrix), Step 2: Map entry points to segments (provide a mapping table template), Step 3: Assign tools to segments (provide example mapping), Step 4: Design nurture sequences per segment, Step 5: Define cross-tool data flow, Step 6: Validate architecture against the 12-point checklist.
Add concrete output artifacts: a sample audience-stage matrix table, a sample entry-point routing diagram (even in ASCII), a sample tool-to-funnel mapping document, and a sample architecture audit checklist with pass/fail criteria.
Cut the content by at least 60%: remove the two closing sections (merge into one sentence), eliminate repeated explanations of silo/kitchen-sink/matched patterns (define once, reference thereafter), and remove all explanatory prose that describes concepts rather than instructs actions.
Add validation checkpoints to the workflow: e.g., 'Before proceeding to nurture sequence design, verify that every entry point maps to at least one segment-stage cell in the matrix. If any entry point is unmapped, the architecture has a gap.'
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose. The skill repeatedly explains concepts Claude already understands (what a funnel is, what segmentation means, what nurture sequences are). The three-pattern framing (silo/kitchen-sink/matched) is restated at least 4 times across different sections. Two closing sections say essentially the same thing. Much of the content reads like a thought-leadership blog post rather than actionable instructions. The entire document could be reduced to roughly 30% of its length without losing any instructional value. | 1 / 3 |
Actionability | The skill provides no concrete, executable guidance. There are no code examples, no templates, no specific commands, no sample outputs, no diagrams, no actual funnel architecture artifacts. The 'worked example' in the entry-point section is a brief narrative description rather than a concrete deliverable. The 12-consideration framework is a checklist of abstract principles, not actionable steps with specific outputs. A practitioner reading this would know the philosophy but not what to actually produce. | 1 / 3 |
Workflow Clarity | There is no clear workflow sequence for designing or auditing a funnel architecture. The 12-consideration framework is a flat checklist without sequencing, dependencies, or validation checkpoints. There are no feedback loops, no 'if X then Y' decision points, and no verification steps. For a skill that covers architecting complex cross-tool systems, the absence of a step-by-step process with validation is a significant gap. | 1 / 3 |
Progressive Disclosure | The skill does reference 9 external files with clear one-level-deep links and descriptive labels, which is good structure. However, since no bundle files are provided, we cannot verify these references exist. The main document itself is far too long and contains substantial content that should have been pushed into the reference files rather than repeated in the overview. The inline content is not concise enough to serve as an overview layer. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
8e70d03
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.