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 skills add stanislavnianko/product-discovery-claude-skills --skill personasgit clone --depth 1 https://github.com/stanislavnianko/product-discovery-claude-skillsWrote 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/stanislavnianko/product-discovery-claude-skills/personas)<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/personas"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/personas/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/personas"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/personas.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00072 | $0.01351 |
| Opus 5 | $0.00036 | $0.00675 |
| Sonnet 5 | $0.00014 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
personas 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 12d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Personas
Part of the discovery-phase skill pack ·
synthesisgroup · readsdiscovery-context.md(runprofile-builderfirst if missing) and the evidence artifacts produced by theevidencegroup.
Turns evidence into 2-4 distinguishable user archetypes that downstream skills (journey-mapping, opportunity-mapping, feature-scoping) can target. Refuses to invent traits — every claim must cite a source. If evidence is thin, says so explicitly and tags fields [ASSUMED] rather than fabricating.
Step 1 — Read context + evidence
Read discovery-context.md (sections 2. Product / Initiative, 3. Users / Stakeholders, 4. Discovery Access Level). Then enumerate available evidence in ./discovery/:
themes.md(frominsight-synthesis) — primary inputinterview-notes/— quote sourcesme-notes/— proxy when end users unreachablesupport-data-analysis.md— behavioral evidencesecondary-research.md— segment-level signals
If themes.md is missing, recommend running insight-synthesis first. Don't block — but warn the BA that personas built directly from raw interview notes (without synthesis) often duplicate themes incorrectly.
If discovery-context.md is missing, ask inline: "(a) what's the buyer vs end-user split? (b) B2B / B2C / B2B2C? (c) any segments the client already named?" — tag unverified personas as [ASSUMED].
Step 2 — Decide how many
Default: 2-4 personas. Hard cap at 4. Rationale:
- 1 persona → not a synthesis, you don't need this skill
- 2-3 → typical for focused B2B and B2C
- 4 → multi-sided marketplace or B2B2C with distinct buyer/user/admin
- 5+ → diminishing returns; collapse near-duplicates
If the BA insists on 5+, push back: "Which two could collapse without losing strategic distinction?"
Step 3 — Pick the right archetype model
Match the engagement context:
| Context | Persona model |
|---|---|
| B2C product | Behavioral (jobs-to-be-done + context) |
| B2B SMB | Role-based, single buyer = end user |
| B2B Enterprise | Buyer + Champion + End-user + Admin (often 3-4) |
| Marketplace | Supply + Demand + Operator |
| Internal tool | Role + Permission tier |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 99 lines · 72 tokens per session scan A 50965cdbd599
personas is a skill published in the GitHub repository stanislavnianko/product-discovery-claude-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 1,351 once invoked, about $0.0004 per session on Opus 5. 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 2026-08-31.
Other skills, from other repositories
jtbd-extractor
Turn raw research into Jobs-to-be-Done statements showing what users are really trying to accomplish. Use when: extract jobs, jtbd analysis, jobs to be done, what job is the user hiring, underlying user needs.
assumption-mapper
Surfaces the assumptions a product or strategy depends on, classifies them by criticality and evidence quality, and produces a prioritized test plan. Use when: assumption mapping, identify assumptions, what could go wrong, leap-of-faith assumptions, riskiest assumption test, RAT, assumption inventory, validate before…
competitive-analyzer
Structured competitive teardown for product discovery - surface the 4-6 dimensions buyers actually weigh, score every competitor on each, and identify exploitable gaps. Use when: competitive analysis, competitor teardown, market positioning, where do we win, where do we lose, competitive gap analysis, competitor audit.
feedback-prioritizer
Triages a backlog of raw customer feedback into a ranked list of opportunities scored on reach, severity, strategic fit, and confidence. Outputs a prioritized list with explicit "do not act" callouts for vocal-minority signals. Use when: triage feedback, prioritize feature requests, customer feedback backlog, what…
north-star-metric-finder
Identifies a candidate North Star Metric (NSM) for a product - the single metric that captures the value the product delivers to its customers and predicts long-term business growth. Tests candidates against five criteria and surfaces input metrics that move it. Use when: north star metric, NSM, single metric that…
prd-taskmaster
Zero-config goal-to-tasks engine (the Atlas engine). Takes any goal (software, pentest, business, learning), runs adaptive discovery via brainstorming, generates a validated spec, parses into TaskMaster tasks, and hands off to execution. Use when user says "PRD", "product requirements", "I want to build", invokes…