Synthesize
- 73 installs
- 325 repo stars
- Updated August 2, 2026
- athola/claude-night-market
synthesize is an agent skill that merges, dedupes, ranks, and formats multi-channel research into a themed report.
About
synthesize is a Tome-family agent skill that closes the loop on multi-channel research. After parallel research agents return raw hits, you invoke it to merge duplicates, rank signal, group by theme, and emit a polished markdown artifact—either a full sectioned report, a condensed brief, or a raw session transcript. Solo builders use it when Perplexity-style depth would otherwise stay fragmented across chat threads. The skill is intentionally narrow: it does not replace starting research (`/tome:research`) or deepening one channel (`/tome:dig`). That separation keeps agent workflows composable. Tag it as multi-phase because the same ranked report feeds Validate scoping, Build prioritization, and Launch messaging, but the canonical Prism shelf remains Idea research where synthesis first earns its keep. Intermediate complexity reflects dependency on an active research session and correct upstream payloads rather than beginner-one-shot prompts.
- 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
Synthesize by the numbers
- 73 all-time installs (skills.sh)
- Ranked #5,587 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Security screen: LOW risk (skills.sh audit)
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/athola/claude-night-market --skill synthesizeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 73 |
|---|---|
| repo stars | ★ 325 |
| Security audit | 3 / 3 scanners passed |
| Last updated | August 2, 2026 |
| Repository | athola/claude-night-market ↗ |
What it does
Turn noisy multi-channel research agent results into one ranked, themed markdown report after a Tome research session.
Who is it for?
Best when you're running Tome-style research stacks and 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 you get
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
By the numbers
- 4-step synthesis workflow (merge, rank, group, format)
- 3 output formats: report, brief, transcript
Files
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:researchfirst) - Refining a single channel (use
/tome:diginstead)
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
Exit Criteria
- [ ]
merge_findings(),rank_findings(), andgroup_by_theme()
all called in sequence before output is formatted
- [ ] Output formatted via
format_report()by default, or
format_brief() / format_transcript() when the flag is set
- [ ] Findings grouped by theme in the report, not presented as raw
per-channel lists
- [ ] If the merged finding count is 0, this is stated explicitly
rather than generating an empty or fabricated report
- [ ] If no active session exists, error emitted directing the user
to run /tome:research first
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10How it compares
Downstream packaging step after research agents—not a replacement for `/tome:research` or single-channel `/tome:dig`.
FAQ
Who is synthesize for?
Developers 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.