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 assimovt/productskills --skill research-synthesisgit clone --depth 1 https://github.com/assimovt/productskillsWrote 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/assimovt/productskills/research-synthesis)<a href="https://agentmods.dev/skills/assimovt/productskills/research-synthesis"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/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/assimovt/productskills/research-synthesis"><img src="https://agentmods.dev/badge/skills/assimovt/productskills/research-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 | $0.00046 | $0.00736 |
| Opus 5 | $0.00023 | $0.00368 |
| Sonnet 5 | $0.00009 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
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 13d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Turn raw research into atomic insights that drive decisions. Good synthesis surfaces patterns, bad synthesis creates narrative fiction. The goal is structured evidence, not a compelling story that cherry-picks quotes.
Atomic Research Method
Break research into four levels, bottom-up:
1. Nuggets (Raw Evidence)
Individual observations from a single source. Each nugget is:
- One observation per nugget (not a paragraph)
- Tagged with source (participant ID, date, method)
- Direct quotes preferred over your interpretation
Example: "[P3, Jan 12] 'I spend 30 minutes after every customer call just trying to remember what they said.'"
2. Patterns (Recurring Themes)
Group nuggets that point to the same phenomenon. A pattern requires evidence from 3+ independent sources.
Example: "5 of 7 PMs report spending 20-45 minutes on post-call documentation. All describe it as tedious and low-value."
3. Insights (Implications)
What the pattern means for the product. An insight connects a pattern to a product opportunity or risk.
Example: "Post-call documentation is a high-frequency pain point (daily for active PMs) with no satisfying solution. Current workarounds (voice memos, bullet lists) lose context and emotional nuance."
4. Recommendations (Actions)
Specific product actions justified by insights. Each recommendation traces back through the chain: recommendation ← insight ← pattern ← nuggets.
Evidence Strength
Rate every pattern and insight:
| Strength | Criteria |
|---|---|
| Strong | 5+ sources, consistent behavior observed, corroborated by data |
| Moderate | 3-4 sources, mostly consistent, some data support |
| Emerging | 2 sources, needs more evidence before acting |
| Weak | Single source or contradictory evidence |
NEVER make product recommendations based on Weak or Emerging evidence. Flag them for further research.
Synthesis Process
- Extract all nuggets from raw notes — one per line, tagged with source
- Affinity map: group nuggets by theme (not by interview)
- Name each group as a pattern with a count ("5/7 participants...")
- Derive insights from strong and moderate patterns only
- Write recommendations that trace back to specific insights
- Flag contradictions explicitly — don't smooth them over
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.
- 13d ago First seen · 71 lines · 46 tokens per session scan A b1c125f3bbbb
research-synthesis is a skill published in the GitHub repository assimovt/productskills (68 stars, last pushed 6mo ago), licensed MIT. It adds 46 tokens to every session and 736 once invoked, about $0.0002 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
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…
handoff
Phase 3 of the prd-taskmaster pipeline: smart mode selection and user handoff. Detects installed capabilities (superpowers, ralph-loop, task-master-ai, playwright, research providers), recommends ONE execution mode (A/B/C) with reasoned justification, appends the task-execution workflow to CLAUDE.md, surfaces a…
generate
Phase 2 of the prd-taskmaster pipeline: spec generation and task parsing. Loads a template (comprehensive|minimal), fills it with DISCOVER-phase constraints and answers, validates the spec (placeholdersfound, grade thresholds), parses the PRD into tasks via task-master, runs TaskMaster's native complexity analysis…
discover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the…
execute-fleet
Phase execution skill for licensed Atlas Fleet runs. Use when HANDOFF has selected Atlas Fleet and the project should be executed across isolated launcher worktrees with inbox-based result collection, verified CDD cards, sequential integration merges, and one final PR.
customise-workflow
Customise the prd-taskmaster plugin workflow via curated brainstorm questions. The AI asks, the user answers in plain English, and the skill writes their preferences to .atlas-ai/config/atlas.json. Future runs of prd-taskmaster read that file and apply user preferences to phase gates, validation strictness, default…