Install
$ agentstack add skill-bglglzd-agent-workflows-product-growth-audit ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Product Growth Audit
Find the strongest next improvements for an existing product. Produce a roadmap based on evidence, not a generic feature list.
Workflow
- Inspect the repository, docs, current UI, tests, issues, release notes, feedback, and data that are actually available. Record verified facts, assumptions, and unknowns.
- Map users, jobs to be done, product promise, key workflows, platform, maturity, constraints, and the journey from first touch through repeat use and support.
- Evaluate the relevant lenses: positioning; UX/UI; core value and features; activation, retention, distribution, and business model; trust and reliability; technical leverage; and AI quality when AI is part of the product.
- Evaluate niche, internal, B2B, open-source, and mass-market paths from the available evidence. Do not assume broad distribution is the goal.
- Create a non-duplicative opportunity map. For every item, provide evidence, user problem, improvement hypothesis, expected outcome, success signal, impact/confidence/effort rationale, dependencies, risks, and a smallest safe validation step.
- Separate quick quality wins, strategic bets, growth or business options, and technical enablers.
- Write or update product documentation. When no convention exists, use
docs/product/PRODUCT_GROWTH_AUDIT.md. - Deliver a 30/60/90-day roadmap split into Now, Next, and Later. Include scope, acceptance criteria, measurement plan, dependencies, and an owner type for every recommended item.
Guardrails
- Do not invent metrics, users, competitor claims, market demand, revenue, or evidence. Mark missing data clearly.
- Do not recommend trendy features, AI, gamification, paywalls, or growth hacks without a product-specific rationale.
- Use external research only with authorization and cite it.
- Do not implement, redesign, alter production, publish marketing, or contact users before approval.
- Preserve real differentiators and prioritize feasible work for the actual team, codebase, budget, and privacy posture.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bglglzd
- Source: bglglzd/agent-workflows
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.