Is the Synapptic skill free?

Yes. The skill itself is free from appcuarium/synapptic. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Synapptic SkillProof Score?

7.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.

How do I install Synapptic?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Synapptic with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Synapptic

Mines your Claude Code session transcripts into a living user/AI-failure profile and guard list

by appcuarium · appcuarium/synapptic

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 260244a

Actually pip-installed the real PyPI package and ran the full CLI against a synthetic session transcript with obvious correction signals ('stop explaining, just do it', 'read an existing service first'); `index`/`stats`/`extract`/`install` all behaved exactly as SKILL.md documents (min-lines gating, provider config, SessionEnd hook + settings.json registration all really got written), and the pipeline only stopped at the final LLM call because it needs a logged-in `claude` CLI or an API key -- an honestly-disclosed, expected requirement, not a skill defect.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 4/5

What Synapptic does

Filters Claude Code session JSONL transcripts (~626x compression), runs an LLM extraction pass to pull user preferences, AI failure patterns, and behavioral guards, then writes a narrative archetype to the memory system so future sessions start informed. Triggers on 'run synapptic', 'update my profile/archetype', 'what do you know about me', or requests to analyze how the user works with their AI coding assistant.

How to install Synapptic

git clone https://github.com/appcuarium/synapptic
cd synapptic
mkdir -p ~/.claude/skills
cp -r src/synapptic/bundle/skill ~/.claude/skills/synapptic

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Synapptic

/synapptic Mines your Claude Code session transcripts into a living user/AI-failure profile and guard list

It also activates on plain-language prompts like these:

Analyze my past Claude Code sessions and build a profile of my preferences
What do you know about how I like to work with my coding assistant
Update my archetype from recent sessions where I corrected your approach

Frequently asked questions

Is the Synapptic skill free?: Yes. The skill itself is free from appcuarium/synapptic. SkillProof publishes the install command and an independent test verdict at no cost.
Does Synapptic work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. Actually pip-installed the real PyPI package and ran the full CLI against a synthetic session transcript with obvious correction signals ('stop explaining, just do it', 'read an existing service first'); `index`/`stats`/`extract`/`install` all behaved exactly as SKILL.md documents (min-lines gating, provider config, SessionEnd hook + settings.json registration all really got written), and the pipeline only stopped at the final LLM call because it needs a logged-in `claude` CLI or an API key -- an honestly-disclosed, expected requirement, not a skill defect.
What is the Synapptic SkillProof Score?: 7.6/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 4/5.
How do I install Synapptic?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Synapptic with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.