Synthesize
Turn noisy multi-channel research agent results into one ranked, themed markdown report after a Tome research session.
Overview
synthesize is an agent skill most often used in Idea (also Validate, Launch) that merges, dedupes, ranks, and formats multi-channel research into a themed report.
Install
npx skills add https://github.com/athola/claude-night-market --skill synthesizeWhat is this skill?
- Four-step workflow: merge_findings → rank_findings → group_by_theme → format_report
- Output formats: full report, brief (1–2 pages), and transcript
- Explicit When NOT To Use: no active research session or single-channel refinement (use dig instead)
- Designed to run after multiple research channels return results
- Category synthesis with ~150 estimated tokens and standard model hint
- 4-step synthesis workflow (merge, rank, group, format)
- 3 output formats: report, brief, transcript
Adoption & trust: 1 installs on skills.sh; 304 GitHub stars; 3/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
What problem does it solve?
You finished multi-channel research but only have piles of overlapping agent output with no ranked narrative to decide what matters.
Who is it for?
Builders running Tome-style research stacks who need one authoritative ranked report from several channels.
Skip if: Empty sessions with no prior research, or when you only need to drill one channel instead of merging many.
When should I use this skill?
After research agents return results from multiple channels and a Tome research session is active; not for single-channel refinement.
What do I get? / Deliverables
You get a ranked, theme-grouped report (or brief/transcript) ready to share or to hand into scoping, positioning, or content work.
- Sectioned markdown report
- Condensed 1–2 page brief or raw transcript
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
First appears where raw research lands—Idea research—before validation or build commitments, even though the same report can inform later phases. Research subphase is the canonical shelf because the skill merges, ranks, and formats findings rather than collecting them.
Where it fits
Merge channel outputs after `/tome:research` into a ranked opportunity brief.
Produce a condensed brief to seed landing-page claims and FAQ copy.
How it compares
Downstream packaging step after research agents—not a replacement for `/tome:research` or single-channel `/tome:dig`.
Common Questions / FAQ
Who is synthesize for?
Solo builders and agent authors using Claude Night Market / Tome workflows who already ran research and need consolidation, not more scraping.
When should I use synthesize?
After research agents return from multiple channels during Idea discovery, Validate competitor sizing, or Launch positioning reviews—once a session is active and raw findings exist.
Is synthesize safe to install?
Check the Security Audits panel on this page; the skill processes research text you already collected and does not by itself define external tool permissions.
SKILL.md
READMESKILL.md - Synthesize
# Finding Synthesis ## When To Use - After research agents return results from multiple channels - Producing a final ranked report from raw findings ## When NOT To Use - No research session is active (run `/tome:research` first) - Refining a single channel (use `/tome:dig` instead) Merge findings from all channels into a ranked report. ## Workflow 1. Merge: `tome.synthesis.merger.merge_findings()` 2. Rank: `tome.synthesis.ranker.rank_findings()` 3. Group: `tome.synthesis.ranker.group_by_theme()` 4. Format: `tome.output.report.format_report()` ## Output Formats - **report**: Full sectioned markdown - **brief**: Condensed 1-2 pages - **transcript**: Raw session log