map-growth-loops
Identify, map, and measure the self-reinforcing growth loops in your product — viral, content, paid, and usage loops. Understand cycle time, throughput, and where loops are broken. Use when a PM needs to move beyond linear funnel thinking and understand the compounding systems that drive sustainable growth.
69
62%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./growth-skills/skills/map-growth-loops/SKILL.mdQuality
Discovery
85%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 skill description that clearly articulates specific capabilities (identifying, mapping, and measuring growth loops), names concrete loop types and metrics, and includes an explicit 'Use when' clause. The main weakness is that trigger term coverage could be broader to capture more natural user phrasings like 'flywheel', 'network effects', or 'growth model'. The description uses proper third-person voice and avoids vague language.
Suggestions
Expand trigger terms to include common synonyms and variations users might say, such as 'flywheel', 'network effects', 'growth model', 'retention loops', or 'compounding growth'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'identify, map, and measure self-reinforcing growth loops', names specific loop types (viral, content, paid, usage), and specifies metrics like 'cycle time, throughput, and where loops are broken'. | 3 / 3 |
Completeness | Clearly answers both 'what' (identify, map, and measure growth loops with specific types and metrics) and 'when' (explicit 'Use when a PM needs to move beyond linear funnel thinking and understand compounding systems that drive sustainable growth'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'growth loops', 'viral', 'content', 'paid', 'usage loops', 'cycle time', and 'funnel thinking', but misses common user variations like 'flywheel', 'network effects', 'retention loops', 'growth model', or 'growth engine' that users might naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on growth loop analysis and mapping, with clear domain-specific triggers like 'self-reinforcing growth loops', 'cycle time', 'throughput', and 'compounding systems' that are unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a thorough and well-structured framework for mapping growth loops, with a clear 5-step workflow and useful diagnostic tables. However, it is severely over-long, explaining many concepts Claude already knows (growth loop definitions, K-factor, viral mechanics) and packing everything into a single monolithic file. The content would benefit greatly from aggressive trimming and splitting into reference files.
Suggestions
Cut the opening philosophy paragraph and loop type definitions by 60-70% — Claude knows what viral loops, SEO loops, and marketplace effects are. Focus only on the specific diagnostic steps and measurement framework.
Extract the detailed loop taxonomy (Step 1) into a separate LOOP_TYPES.md reference file, keeping only a brief checklist in the main skill.
Move the anti-plays section and loop interaction mapping guidance into separate reference files, linking to them from the main workflow.
Remove explanatory asides like 'This is equivalent to the K-factor for viral loops but applies to all loop types' — Claude knows this.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This is extremely verbose at ~300+ lines. It explains concepts Claude already knows well (what growth loops are, what funnels are, definitions of viral/SEO/UGC loops, what K-factor means). The opening paragraph philosophizing about funnels vs. loops is unnecessary context. Much of the loop taxonomy is general business knowledge that doesn't need to be spelled out at this length. | 1 / 3 |
Actionability | The skill provides a structured framework with specific steps, a concrete table format for measuring conversion, and example loop diagrams. However, it's fundamentally a prompt template rather than executable code/commands — the guidance is detailed but remains conceptual (e.g., 'estimate the impact of fixing it') rather than providing concrete tools, scripts, or copy-paste-ready artifacts. | 2 / 3 |
Workflow Clarity | The 5-step workflow is clearly sequenced and logically ordered: identify → measure → diagnose breaks → assess interactions → recommend. Each step has explicit sub-steps and the output format section serves as a validation checklist. The anti-plays section provides guardrails against common mistakes, functioning as error-prevention checkpoints. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no references to supporting files. The detailed loop taxonomy, measurement frameworks, and anti-plays could all be split into separate reference files. Everything is inline, making this a very long single document with no navigation structure beyond the step headers. | 1 / 3 |
Total | 7 / 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 | |
- Repository
- amplitude/builder-skills
- Commit
221ffaa
- Reviewed
Table of Contents
Is this your skill?
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.