SKILLEMALL.ai
GitHub ↗ RU Sign in

BD memora

Memora — Personal AI Knowledge Base with interactive knowledge graph visualization. A self-hosted system for managing, retrieving, and querying your personal knowledge assets using vector search, hybrid retrieval, and LLM-driven intelligent Q&A. Features document upload/processing, semantic search, AI chat sessions, web scraping, and Obsidian-style knowledge graph visualization with force-directed layout. Use when: user wants to build a personal knowledge base, manage documents, perform semantic search, have AI-powered conversations about their knowledge, visualize document/entity relationships, or integrate knowledge management into their OpenClaw workflow.

ClawHub Agent Skills author: Probieren v1.0.0 MIT-0 3 files body ≈ 3 174 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Memora — Personal AI Knowledge Base with interactive knowledge graph visualization.

As a process D 41/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

ReferenceObsidianGitHubDockerWordInfrastructureSoftware developmentAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
93
Quality 40%
77
Run on models
none yet
Process rating
D
41/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Exfiltration net-credential-use SKILL.md:302
      Credential used in a network call (verify the destination is the intended service)
      curl -H "Authorization: Bearer $DEEPSEEK_API_KEY" \
    • low Exfiltration read-dotenv SKILL.md:133
      Reads a .env file
      cp .env.example .env
    • low Exfiltration read-dotenv SKILL.md:299
      Reads a .env file
      cat .env | grep API_KEY

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 41/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Progress reporting. Says nothing while it works
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 14 mutating operations with no state check
    • 40Consistency. Frontmatter name (memora) differs from the folder (memora-kb)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (web, git, python, node) that frontmatter does not declare
    • 85Steps. 107 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 3174 tokens
    • low 12 top-level sections: this looks like several domains in one skill
    • low The skill ranks results itself: that belongs to the system behind the tool, not the model

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -2localhost URLs: will not work for another user
    • -226 emoji in the instructions: noise for the model
    • -31 of 1 scripts are never mentioned in SKILL.md
    • +1No license
    • +2Single-language instructions
    • +3Description length 666: enough signal without eating the budget
    • +4Structure: 41 headings
    • +3Step-by-step instructions: 107 items
    • +4Has examples (8 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

    External checks

    ClawHub: suspicious
    Memora is a coherent personal knowledge-base skill, but its privacy claims conflict with documented cloud LLM and embedding provider use.
    LLM: suspicious (high) · VirusTotal: · 9 Jul 2026