Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/aakashg/pm-claude-code-setup/user-researchnpx skills add aakashg/pm-claude-code-setup --skill user-researchgit clone --depth 1 https://github.com/aakashg/pm-claude-code-setupWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/aakashg/pm-claude-code-setup/user-research)<a href="https://agentmods.dev/skills/aakashg/pm-claude-code-setup/user-research"><img src="https://agentmods.dev/badge/skills/aakashg/pm-claude-code-setup/user-research.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00551 |
| Opus 5 | $0.00000 | $0.00275 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
user-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Research Synthesizer
Trigger
Activate on "synthesize research", "analyze interviews", "research findings", "interview synthesis".
Behavior
Step 1: Get Input
Ask:
- Paste the research notes or interview transcripts
- What was the research question?
- How many participants?
Step 2: Synthesize
Key Findings (ranked by evidence strength) For each:
- Finding (1 sentence)
- Evidence (how many participants, quotes)
- Confidence (High/Medium/Low)
- Product implication
Themes | Theme | Frequency | Representative Quote | Implication |
Surprises
- What contradicted our assumptions
Gaps
- Questions not answered, segments not covered
Recommended Actions
- Prioritized list with supporting evidence
Example
Bad synthesis (no evidence, no confidence levels):
Key Findings:
- Users like the product
- Onboarding could be better
- Some people want more features
Good synthesis:
Key Findings (ranked by evidence strength):
1. Users abandon onboarding at the "connect integrations" step
Evidence: 7 of 10 participants hesitated or failed here. 4 said
variants of "I don't want to give access to my data yet."
Confidence: HIGH
Implication: Move integrations to post-activation. Let users see
value before asking for trust.
2. Power users create personal workarounds for batch editing
Evidence: 3 of 10 participants (all daily users) showed custom
keyboard shortcuts or browser extensions they built themselves.
Confidence: MEDIUM (small sample of power users)
Implication: Batch editing is a retention lever for heaviest users.
Worth exploring, but validate with usage data first.
Surprises:
- 6 of 10 participants didn't know the search feature existed. It's
behind a keyboard shortcut (Cmd+K) with no visible UI entry point.
This contradicts our assumption that search is well-adopted.
Gaps:
- No participants from enterprise segment (>500 employees). Findings
may not generalize to that tier.
- Research question about pricing sensitivity was not explored — all
participants were on free plans.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 80 lines · 0 tokens per session scan A 70649a56d91c
user-research is a skill published in the GitHub repository aakashg/pm-claude-code-setup (152 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 551 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
kimchi
Turn a raw product idea into build-ready docs — one doc per EPIC with locked decisions, exact API contracts, a story-by-story priority plan, and an execute.md handoff Claude can build from across sessions. Gets the clarity by interrogating the user through a roster of expert personas that grill, counter, and refuse to…
create-slide-deck
Create beautiful HTML slide decks for product presentations. Reads product context, extracts brand colors from websites, and generates self-contained HTML files with keyboard navigation and print-friendly layouts.
pm-setup
Interactive onboarding wizard that creates the PM-OS knowledge base for your product. Asks questions, fetches company info, and populates all knowledge files.
opportunity-assessment
Validate ideas with market sizing (TAM/SAM/SOM), competitive landscape, strategic alignment, technical feasibility, and a go/no-go recommendation.
pm-os
Product Manager's Operating System: gateway skill that routes requests to 27 PM workflow skills and manages the knowledge system.
sprint-scope
Sprint planning with capacity awareness. Pulls from backlog (via MCP or manual input), calculates what fits based on team velocity, and outputs recommended scope with stretch goals and deferred items.