← Back to Skills Marketplace
antoniovfranco

Algernon Synthesis

by Antonio V. Franco · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
203
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install algernon-synthesis
Description
Cross-material knowledge synthesis session for OpenAlgernon. Use when the user runs `/algernon synthesis`, says "quero conectar os materiais", "sintese entre...
README (SKILL.md)

algernon-synthesis

You run a cross-material synthesis session. The goal is to build explicit connections between concepts learned in different materials — the kind of holistic understanding that separates someone who memorized facts from someone who can actually design systems.

Constants

DB=/home/antonio/Documents/huyawo/estudos/vestibular/data/vestibular.db
NOTION_CLI=~/go/bin/notion-cli

Step 1 — Check Eligibility

sqlite3 $DB \
  "SELECT m.slug, m.name, COUNT(r.id) as review_count
   FROM materials m
   JOIN decks d ON d.material_id = m.id
   JOIN cards c ON c.deck_id = d.id
   JOIN reviews r ON r.card_id = c.id
   GROUP BY m.id
   HAVING review_count > 0
   ORDER BY review_count DESC;"

If fewer than 2 materials have reviews: "Synthesis requires at least 2 studied materials. Study more material first."

Step 2 — Identify Cross-Material Concept Overlaps

From the tags and topics of reviewed cards across all studied materials, identify 3-5 concept pairs that appear in multiple materials but may be understood differently in each context.

Examples of strong synthesis pairs:

  • "evaluation" in RAG vs LLMOps contexts
  • "chunking" in embedding vs RAG contexts
  • "latency" in inference vs retrieval contexts
  • "context" in prompt engineering vs agent memory contexts
  • "retrieval" in BM25 vs vector similarity vs caching contexts

Prefer pairs where the same word genuinely means something different in each context — that contrast is the richest learning opportunity.

Step 3 — Synthesis Questions

For each concept pair, ask:

AskUserQuestion (free text):

"[CONCEPT] appears in both [MATERIAL_A] and [MATERIAL_B]. How does the meaning or role of [CONCEPT] differ between these two contexts? Where do they overlap?"

After each answer, give brief feedback:

  • Name what the user connected well.
  • Name any distinction they missed (without lecturing — one sentence).

Step 4 — Production Scenario Challenge

AskUserQuestion (free text):

"If you were building a production AI system, how would the knowledge from [MATERIAL_A] and [MATERIAL_B] work together? Give a concrete scenario with specific design decisions."

Evaluate for:

  1. Coherence — does the scenario make technical sense?
  2. Specificity — are there real design decisions, not just buzzwords?
  3. Correct use of concepts — are terms from both materials used accurately?

Step 5 — Summary

Display:

Synthesis session complete.
Materials covered: [list]
Conceptual bridges built well: [list]
Bridges that need reinforcement: [list]

Send to Notion

Send to the Notion page of the most recent phase studied:

~/go/bin/notion-cli append --page-id PHASE_PAGE_ID --content "MARKDOWN"

Include:

  • Cross-material concepts explored
  • Gaps identified (bridges that need reinforcement)
  • The production scenario the user described

Save Memory

Append to today's conversation log:

[HH:MM] synthesis session
Materials: [list] | Bridges built: N | Needs reinforcement: [list]
Usage Guidance
Before installing or running this skill, be aware it will: 1) run sqlite3 on a hard-coded local DB path (/home/antonio/.../vestibular.db) — confirm you want the agent to read that file or update the skill to point to your DB; 2) call a local Notion CLI (~/go/bin/notion-cli) and append content to a Notion page (PHASE_PAGE_ID) — ensure you understand where the Notion credentials live and do not provide secrets implicitly; 3) append a line to the agent's 'conversation log' — clarify where that file is stored. Recommended actions: ask the author to parameterize the DB path and notion CLI/page-id (via declared requires.config or env vars), declare required binaries and env vars in the skill metadata, and document where conversation logs are saved. If you cannot verify those changes, avoid running the skill with access to sensitive local data or credentials — run it in an isolated/sandbox environment instead. Additional info that would raise confidence: explicit required config paths and env vars (DB path, NOTION_PAGE_ID, NOTION_TOKEN), or a prompt that asks the user to provide/confirm those values at runtime.
Capability Analysis
Type: OpenClaw Skill Name: algernon-synthesis Version: 1.0.0 The skill bundle contains a potential shell injection vulnerability in SKILL.md, where user-provided content (the production scenario and synthesis answers) is instructed to be passed directly into a shell command via the `notion-cli`. While the intent appears to be a legitimate educational tool for knowledge synthesis, the lack of input sanitization for shell execution poses a risk if the AI agent does not properly escape the content. Additionally, the skill relies on hardcoded local file paths (e.g., `/home/antonio/...`) and external CLI tools.
Capability Assessment
Purpose & Capability
The described goal (cross-material synthesis) matches the actions in SKILL.md (identify reviewed cards, ask synthesis questions, summarize). However the skill assumes access to a specific local SQLite DB and a Notion CLI, which are not declared in the skill metadata. That makes the claimed purpose plausible but the required runtime resources are not proportionately declared or parameterized.
Instruction Scope
The instructions tell the agent to run sqlite3 against a hard-coded DB path (/home/antonio/.../vestibular.db), to call a user-local binary (~/go/bin/notion-cli) with a PHASE_PAGE_ID placeholder, and to append to 'today's conversation log'. These are concrete filesystem and network actions not reflected in the skill's declared requirements. The instructions also send content to an external service (Notion) via notion-cli without specifying where the Notion credentials or page ID come from. That surface is broader than the skill metadata indicates.
Install Mechanism
There is no install spec (instruction-only), so nothing will be downloaded or installed by the registry itself. That reduces installer risk. Note: the runtime still depends on local binaries (sqlite3 and notion-cli) that are not declared, which is an operational mismatch rather than an installer risk.
Credentials
The skill implicitly requires access to a local SQLite database file, a Notion CLI executable, and a Notion page ID / credentials, but the registry metadata declares no required env vars or config paths. Requesting unspecified local file access and external service access without declaring those needs is disproportionate and opaque.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. It does instruct writing/saving results to a Notion page and a 'conversation log' (expected for a note-taking/synthesis skill). Autonomous invocation is allowed (platform default) but is not an additional flagged privilege here.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install algernon-synthesis
  3. After installation, invoke the skill by name or use /algernon-synthesis
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of algernon-synthesis skill for cross-material knowledge synthesis. - Enables users to connect concepts between at least two materials with reviewed cards. - Identifies key concept pairs that appear across different materials for deeper comparison and understanding. - Guides users through synthesis questions and provides targeted feedback on their connections and distinctions. - Concludes with a production scenario challenge to apply cross-material knowledge. - Summarizes session strengths and gaps, with automatic logging and Notion integration.
Metadata
Slug algernon-synthesis
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Algernon Synthesis?

Cross-material knowledge synthesis session for OpenAlgernon. Use when the user runs `/algernon synthesis`, says "quero conectar os materiais", "sintese entre... It is an AI Agent Skill for Claude Code / OpenClaw, with 203 downloads so far.

How do I install Algernon Synthesis?

Run "/install algernon-synthesis" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Algernon Synthesis free?

Yes, Algernon Synthesis is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Algernon Synthesis support?

Algernon Synthesis is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Algernon Synthesis?

It is built and maintained by Antonio V. Franco (@antoniovfranco); the current version is v1.0.0.

💬 Comments