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 rampstackco/claude-skills --skill discovery-research-synthesisgit clone --depth 1 https://github.com/rampstackco/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/rampstackco/claude-skills/discovery-research-synthesis)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/discovery-research-synthesis"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/discovery-research-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/rampstackco/claude-skills/discovery-research-synthesis"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/discovery-research-synthesis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00150 | $0.04929 |
| Opus 5 | $0.00075 | $0.02465 |
| Sonnet 5 | $0.00030 | $0.00986 |
| Haiku 4.5 | $0.00015 | $0.00493 |
Grade A, and why
discovery-research-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 11d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- discovery-research-synthesis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 266 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery Research Synthesis
A senior PM's playbook for turning research artifacts into decisions. Customer interviews, user research notes, support ticket reviews, sales call transcripts, survey data, in-app feedback, all synthesized into the product direction they are meant to inform.
Most discovery research never produces decisions. The team conducts interviews; the transcripts pile up; a researcher hands product the raw artifacts (data-dump) or builds a polished readout deck (insight-theater); the deck gets a 30-minute review meeting and is never referenced again. Two months later the team is making the same product decisions that the research was supposed to inform, with the same gut-feel inputs the research was supposed to displace.
The discipline is in the synthesis. Synthesis is where research earns its keep: where transcripts become tagged observations, observations cluster into patterns, patterns get named, named patterns surface product implications, and implications drive specific decisions. Without that sequence, research is performance art.
This skill covers one-off discovery research projects: a 12-week customer development sprint, a sales-call review for an onboarding redesign, a support-ticket audit informing a roadmap quarter. Different from user-feedback-aggregation, which covers ongoing feedback streams; different from jtbd-framing, which is a specific framing technique often applied within synthesis but narrower in scope.
The voice is the senior PM or staff product researcher who has run synthesis well and seen plenty of teams fail at it. Honest about where polish becomes performance and where pattern-naming slides into pattern-fabrication.
When to use this skill: synthesizing a recent batch of customer interviews, auditing why prior research has not produced product decisions, designing the synthesis output for a multi-week discovery sprint, or establishing the synthesis discipline a team currently lacks.
What this skill is for
What ships with it
9 files 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.
- references/common-discovery-synthesis-failures.md 11 KB
- references/from-pattern-to-product-implication.md 9.8 KB
- references/pattern-naming-patterns.md 8.8 KB
- references/research-types-and-when-each-fits.md 10 KB
- references/synthesis-review-and-validation.md 11 KB
- references/synthesis-sequence-walkthrough.md 11 KB
- references/tagging-and-clustering-discipline.md 9.3 KB
- references/when-to-gather-more-data.md 11 KB
- references/writing-for-decisions-not-decks.md 10 KB
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.
- 11d ago First seen · 266 lines · 150 tokens per session scan A 9b8117216f51
discovery-research-synthesis is a skill published in the GitHub repository rampstackco/claude-skills (832 stars, last pushed 3d ago), licensed MIT. It adds 150 tokens to every session and 4,929 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
seo-site-health-audit
Triage technical SEO findings from Ahrefs Site Audit (and similar crawlers) by SEO impact, not just severity. Use this skill when reviewing crawl results, prioritizing technical fixes, scoping a technical SEO sprint, or after running any site-wide crawl. Triggers on site audit results, technical fix list, crawl…
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
seo-content-audit
Audit existing content across a site to decide what to keep, update, merge, redirect, or delete. Use this skill whenever the user wants to audit existing content, fix content decay, resolve keyword cannibalization, prune underperforming pages, prioritize content updates, or apply a keep/update/merge/redirect/delete…
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
content-and-copy
Write or edit website copy, blog content, and editorial pieces with attention to voice, structure, and goal. Use this skill whenever the user wants to write an article, draft website copy, edit existing content for clarity or voice, write a blog post, or produce general editorial content. Triggers on write a blog…
seo-aeo-geo
Optimize content and site structure for AI-driven search experiences including AI overviews, large language model citations, generative answer engines, and AI assistants. Use this skill whenever the user wants to optimize for AI search, get cited by language models, appear in AI overviews, build llms.txt, structure…