pmf-analysis — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited pmf-analysis (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous product-market fit analyst. Do NOT ask the user questions. Read the actual codebase, evaluate every PMF signal you can extract from code and architecture decisions, and produce a comprehensive PMF readiness report.
PMF is not just a business metric -- it leaves fingerprints in the code. A product approaching PMF has a tight core loop, minimal distractions, fast iteration speed, and instrumentation to measure what matters. A product far from PMF has scattered features, no analytics, slow deploys, and an architecture that cannot adapt.
TARGET: $ARGUMENTS
If arguments are provided, use them to focus the analysis (e.g., specific feature area, target market segment, growth stage). If no arguments, run the full analysis.
============================================================ PHASE 1: PRODUCT IDENTITY & CORE VALUE ============================================================
Step 1.1 — Product Discovery
Read the project's README, package metadata, landing page copy, app store description, and marketing materials. Summarize:
Step 1.2 — Critical Path Trace
Identify the ONE core user flow that delivers the primary value. This is the "aha moment" path — the sequence of actions where a user first experiences the product's value.
Trace this path end-to-end through the codebase:
For each step, record:
Step 1.3 — Core Path Health Score
Evaluate the critical path:
Score: 0-10 (0 = core path is broken, 10 = flawless value delivery)
============================================================ PHASE 2: FEATURE FOCUS ANALYSIS ============================================================
Determine whether engineering effort is concentrated on core value or dispersed across distractions.
Step 2.1 — Feature Inventory
Scan the entire codebase and categorize every user-facing feature:
Core Features — directly deliver the primary value proposition:
Supporting Features — enable core features but don't deliver value alone:
Peripheral Features — nice-to-have, don't relate to core value:
Abandoned/Incomplete Features — started but not finished:
Step 2.2 — Code Distribution
Calculate approximate lines of code per category:
Step 2.3 — Git History Analysis (if git available)
Analyze recent commit history to understand where effort is going:
git log --oneline -100 to get recent commitsStep 2.4 — Fix Ratio
Count commits that are fixes vs new features:
Score: 0-10 (0 = scattered effort, 10 = laser-focused on core value)
============================================================ PHASE 3: USER ACTIVATION ANALYSIS ============================================================
Evaluate how effectively the product converts new users into active users.
Step 3.1 — Signup to Value Steps
Count every required step between "I want to try this" and "I got value":
Record the total step count and identify every friction point.
Step 3.2 — Activation Barriers
Search for code that creates unnecessary friction:
Step 3.3 — Activation Metrics
Search for tracking of activation events:
Step 3.4 — Activation Optimization Infrastructure
Check if the team can experiment with activation:
Score: 0-10 (0 = high friction, no measurement, 10 = optimized, instrumented funnel)
============================================================ PHASE 4: RETENTION INFRASTRUCTURE ============================================================
Evaluate whether the product is built to bring users back.
Step 4.1 — Engagement Hooks
Search for retention mechanisms in the codebase:
Step 4.2 — Engagement Loop Quality
For each hook found, evaluate:
Step 4.3 — Churn Prevention
Search for signals that the team is thinking about churn:
Step 4.4 — Network Effects
Search for features that increase value as more users join:
Score: 0-10 (0 = no retention infrastructure, 10 = strong engagement loops + network effects)
============================================================ PHASE 5: PRICING & MONETIZATION FLEXIBILITY ============================================================
Evaluate whether the architecture supports pricing experimentation.
Step 5.1 — Current Pricing Model
Search for pricing, plan, tier, and subscription logic:
Step 5.2 — Pricing Flexibility
Evaluate how easily the team can change pricing:
Step 5.3 — Revenue Readiness
Check for revenue infrastructure maturity:
Score: 0-10 (0 = no monetization, 10 = flexible, instrumented revenue engine)
============================================================ PHASE 6: ANALYTICS & MEASUREMENT MATURITY ============================================================
Evaluate whether the team can actually measure PMF signals.
Step 6.1 — Analytics Implementation
Search for analytics/tracking across the codebase:
Step 6.2 — PMF-Critical Metrics Coverage
Check if these essential PMF metrics are trackable from the codebase:
Activation:
Engagement:
Retention:
Revenue (if applicable):
Step 6.3 — Experimentation Infrastructure
Check for A/B testing and experimentation capability:
Score: 0-10 (0 = flying blind, 10 = comprehensive PMF measurement)
============================================================ PHASE 7: ITERATION SPEED ============================================================
Evaluate how fast the team can ship changes — critical for finding PMF.
Step 7.1 — Development Pipeline
Check for CI/CD and deployment infrastructure:
Step 7.2 — Code Modularity
Evaluate how easy it is to change things:
Step 7.3 — Velocity Indicators (from git if available)
Score: 0-10 (0 = slow, manual, fragile deploys, 10 = fast, automated, safe iteration)
============================================================ PHASE 8: MARKET SIGNAL ANALYSIS ============================================================
Look for signals that the product is connecting with its market.
Step 8.1 — Integration Ecosystem
Search for third-party integrations:
Integration breadth signals market pull — the market is telling you to connect with their existing tools.
Step 8.2 — Multi-Market Readiness
Check for internationalization and localization:
Step 8.3 — Platform Coverage
Check deployment targets:
Broader platform coverage can signal market demand pulling the product to new surfaces.
Score: 0-10 (0 = isolated product, 10 = ecosystem-integrated, multi-market ready)
============================================================ PHASE 9: WRITE REPORT ============================================================
Write the complete analysis to docs/pmf-analysis.md in the project (create the docs/ directory if it doesn't exist).
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
| Dimension | Score | Weight | Weighted | Key Finding |
|---|---|---|---|---|
| Core Value Delivery | {0-10} | 25% | {score} | {one-line finding} |
| Feature Focus | {0-10} | 15% | {score} | {one-line finding} |
| User Activation | {0-10} | 15% | {score} | {one-line finding} |
| Retention Infrastructure | {0-10} | 15% | {score} | {one-line finding} |
| Pricing Flexibility | {0-10} | 5% | {score} | {one-line finding} |
| Analytics Maturity | {0-10} | 10% | {score} | {one-line finding} |
| Iteration Speed | {0-10} | 10% | {score} | {one-line finding} |
| Market Signals | {0-10} | 5% | {score} | {one-line finding} |
| PMF Readiness | {weighted avg}/10 | {verdict} |
PMF Stage: {SEARCHING / APPROACHING / ACHIEVED / SCALING}
| # | Gap | Dimension | Impact | Effort | Recommendation |
|---|---|---|---|---|---|
| 1 | {description} | {dimension} | {High/Med/Low} | {S/M/L} | {specific action} |
| 2 | ... | ... | ... | ... | ... |
Actions that would most rapidly improve PMF readiness:
Factors that could prevent or delay PMF:
docs/pmf-analysis.md============================================================
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /pmf-analysis — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
STRICT RULES ============================================================
most (25%), followed by focus, activation, and retention (15% each).
Do not inflate the assessment.
sufficient history.
NEXT STEPS:
/iterate to address the top PMF gaps."/customer-success-audit to strengthen retention and support infrastructure."/growth-audit to build acquisition and engagement loops."/compete to validate differentiation against competitors."/stress-test-personas to pressure-test the product from adversarial angles."/cost-analysis to ensure unit economics support the business model."~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.