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 insight-synthesisgit 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/insight-synthesis)<a href="https://agentmods.dev/skills/stanislavnianko/product-discovery-claude-skills/insight-synthesis"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/insight-synthesis/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/insight-synthesis"><img src="https://agentmods.dev/badge/skills/stanislavnianko/product-discovery-claude-skills/insight-synthesis.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 | $0.00067 | $0.01348 |
| Opus 5 | $0.00034 | $0.00674 |
| Sonnet 5 | $0.00013 | $0.00270 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
insight-synthesis 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Insight Synthesis
Part of the discovery-phase skill pack ·
synthesisgroup · readsdiscovery-context.md(runprofile-builderfirst if missing).
Turns whatever evidence the BA managed to gather into structured insights — weighted by source quality so the team doesn't treat one SME's hunch as equal to five user interviews.
Step 1 — Read discovery context
Read discovery-context.md (section 4. Access & Data) to know what evidence to expect. If missing, ask the BA inline: "which evidence types should I expect — interviews / SMEs / tickets / secondary / competitive / mix?" — or weight all sources equally and tag the output [NO-WEIGHTING-CONTEXT]. Never block; recommend profile-builder for high-stakes work.
Then scan ./discovery/ for actually-present artifacts:
interview-notes/*.md(direct evidence — highest weight)sme-notes/*.md(proxy evidence — medium weight)support-data-analysis.md(unsolicited signal — high weight)secondary-research.md(published data — variable weight by source)competitive-scan.md(market signal — context, not direct evidence)
If fewer than 2 sources are present, tell the BA: "Synthesis with single-source evidence is fragile. Consider running another evidence skill before this. Proceed anyway?"
Step 2 — Affinity mapping (sticky-notes phase)
For every distinct observation across all sources, create a one-line entry in ./discovery/_observations.md:
- [P03 | direct] "I keep a spreadsheet because the tool doesn't filter by region"
- [P01 | direct] 15 min/day lost to manual status updates
- [SME-Maria | inferred] "Users get stuck at the third step" (no specific user cited)
- [tickets | n=23] complaints about CSV export breaking
- [secondary | Gartner 2025] 60% of similar tools lack X
Tag each with [source | confidence]. Aim for 30-80 observations across all sources.
Step 3 — Cluster into themes
Group by underlying job, not surface vocabulary. Target 5-8 themes. More than 10 = clusters too narrow; fewer than 4 = too broad.
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 · 103 lines · 67 tokens per session scan A 589d69d649ef
insight-synthesis is a skill published in the GitHub repository stanislavnianko/product-discovery-claude-skills (1 stars, last pushed 4mo ago), licensed MIT. It adds 67 tokens to every session and 1,348 once invoked, about $0.0003 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…