๐Ÿงฉ
AI EngineeringPython

Synthesis Explore

by acogood

Synthesis Explore is an AI Engineering skill for Claude Code, published by acogood in diffmode_free.

161 stars0 forkson acogood/diffmode_freeAdded 2026/09/08+1% in starsRepository updated 2026/08/10
agentsaibootstrappedclaude-codeclaude-plugincodexdevtoolsfoundersgrowthgrowth-hackingmarketingmarketing-strategyopen-sourcesaasskillsstartupstartup-tools
Install in seconds
Install Synthesis Explore
Copy Synthesis Explore into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/acogood/diffmode_free/tree/main/plugin/skills/synthesis-explore ~/.claude/skills/synthesis-explore

Requires Node.js. Downloads this skill only โ€” not the rest of the repository โ€” into your Claude Code skills folder.

Without Node.js

git clone https://github.com/acogood/diffmode_free.git

Clones the whole repository, then copy the skillโ€™s own directory into your skills folder yourself.

In this catalog

Source file
plugin/skills/synthesis-explore/SKILL.md in acogood/diffmode_free
Installs to
~/.claude/skills/synthesis-explore
Collection
One of 13 skills cataloged from this repository
Category
AI Engineering โ€” 3670 skills

What Synthesis Explore does

Synthesis Explore generates blind vector combinations and derives the emergent mechanisms they could produce for the Diffmode growth-tactics pipeline. Use it when you need structural exploration before tactic design, with checks that reject conventional marketing patterns.

Synthesis Explore is cataloged under AI Engineering on DirSkills. Synthesis Explore comes from a repository tagged agents, ai, bootstrapped, claude-code and claude-plugin.

Documentation

README

Synthesis โ€” Explore (Phase 1 Blind Combinations โ†’ Phase 2 Emergent Mechanisms)

This is the FIRST synthesis stage. It fuses two jobs that MUST stay ordered: Phase 1 draws vector combinations BLIND (vector-first, before any tactic exists), and Phase 2 derives the NOVEL MECHANISM that emerges from each combination. Vector-first thinking is the novelty engine: you commit to combinations BEFORE knowing what tactic they might produce, which is how you escape conventional playbooks. Output: 15-20 raw vector combinations + 12-18 validated mechanisms. NO TACTIC NAMES. NO EXECUTION STEPS. (Tactic design is synthesis-build's job.)

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Synthesis Explore

  • What else does acogood publish alongside Synthesis Explore?

    Synthesis Explore is one of 13 skills that DirSkills catalogs from acogood/diffmode_free, the repository it ships in. Its siblings there include Acquisition Tactics Research, Audience JTBD Analysis and Competitor Gaps. Each one is a separate skill with its own page in this directory, installs the same way Synthesis Explore does, and is maintained by acogood in that same repository. The rest of the collection is listed on the acogood/diffmode_free page.

  • How does Synthesis Explore compare to other AI Engineering skills?

    Synthesis Explore ranks #3449 by stars among the 3670 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Synthesis Explore against them. Open each page to compare what they document and how they install.

More from acogood/diffmode_free

Synthesis Explore is one of 13 skills cataloged on DirSkills from acogood/diffmode_free.

See all 13 skills โ†’
๐Ÿ“ˆ
1h ago

Acquisition Tactics Research

Acquisition Tactics Research maps acquisition channels and tactics for a founderโ€™s industry using competitor, industry, platform, and unconventional case studies. Use it when you need a neutral audit of what tactics exist, how they are executed, and what resources they require.
Writing
1610
๐ŸŽฏ
1h ago

Audience JTBD Analysis

Audience JTBD Analysis identifies 3-4 customer segments for a product using Advanced Jobs To Be Done. It is used for founder product enrichment, segment scoring, and channel-fit analysis without web research.
Writing
1610
๐Ÿ”Ž
1h ago

Competitor Gaps

Competitor Gaps analyzes competitive channels, audiences, content, positioning, and execution to find structural advantages a bootstrapped founder can exploit. It is used for the think-tank gap-analysis stage, based on existing enrichment outputs rather than web research.
AI Engineering
1610
๐Ÿ”Ž
1h ago

Cross-Industry Tactic Transfer

Cross-Industry Tactic Transfer researches growth tactics from other industries and adapts the underlying mechanism to a founder's distribution challenge. It is used for exploratory think-tank analysis, including controversial tactics, without ranking or prioritizing options.
AI Engineering
1610
๐Ÿ“
1h ago

Diagnostics Intake

Diagnostics Intake captures founder input for the Diffmode growth pipeline and writes it into WS/01-diagnostics/founder-input.md. It is used at the start of a workspace to prefill researched fields and flag the missing founder-only details needed for enrichment.
Automation
1610
๐Ÿ”
1h ago

Enrichment Competitors Analysis

Enrichment Competitors Analysis maps a productโ€™s competitive landscape by identifying direct, indirect, and indie competitors, then documenting positioning and acquisition tactics. Use it when running the enrichment stageโ€™s competitors dimension or when you need a neutral market overview.
Data
1610