SKILLEMALL.ai
GitHub ↗ RU Sign in

DB install-memex

Make Claude, Cursor, Cline, Continue, and Zed remember every AI conversation forever — one local SQLite corpus shared across all of them. Installs memex (local-first MCP server) in ~60 seconds via curl one-liner. Includes auto-capture daemon for Claude Code / Cowork / Cursor / Obsidian; v0.10 Telegram auto-detect (export from Desktop → memex stages it → AI proactively asks which to import, privacy-first per-chat consent); v0.8 SessionStart hook for the Brian Chesky moment ("Claude already knows what you were doing"); URL / Perplexity / AI chat share capture via memex_store_document. 18 MCP tools, no cloud, no account, verbatim storage. Use when the user says "install memex", "set up memex", "add memory to my AI", "make my agent remember across sessions", "сохрани мои чаты", or similar.

Not recommendedcritical or high security findings · low grade D
ClawHub Agent Skills author: sedelev v1.5.1 MIT-0 4 files body ≈ 5 651 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 74/100 · Nearly there — weak spots: result and completion

GeneratorTelegramObsidianGitHubAI 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
D
52/100
safety, quality, tests
Safety 60%
36
Quality 40%
77
Run on models
none yet
Process rating
B
74/100
Nearly there
Result and completion w 14
0
Tools and files w 18
60
Inputs and preconditions w 11
70
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 10

  • high Dangerous commands cmd-pipe-to-shell README.md:63
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    > curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
  • high Dangerous commands cmd-pipe-to-shell SKILL.md:89
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
Medium and low: 8
  • medium Dangerous commands cmd-pipe-to-shell examples.md:27
    Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file)
    > curl -fsSL https://memex.parallelclaw.ai/install.sh | bash
    fixture
  • medium Dangerous commands cmd-pipe-to-shell README.md:10
    Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)
    2. **Fast path (v1.1+)** — `curl -fsSL https://memex.parallelclaw.ai/install.sh | bash`: one hosted bash script does npm install (with EACCES auto-fix to `~/.npm-global`), daemon setup, v0.8 auto-cont
    quoted
  • medium Dangerous commands cmd-pipe-to-shell SKILL.md:28
    Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)
    | `curl -fsSL https://memex.parallelclaw.ai/install.sh \| bash` | Fast-path installer (the user can `\| less` first to inspect) | [docs/install.sh](https://github.com/parallelclaw/memex-mvp/blob/main/
    table
  • medium Dangerous commands cmd-persistence SKILL.md:32
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (documentation table row)
    | `memex-sync install` (LaunchAgent) | Registers a macOS LaunchAgent so memex daemon auto-starts on login. **The daemon itself is local-only**: it watches `~/.claude/projects/`, `~/Downloads/Telegram
    table
  • medium Dangerous commands cmd-shell-rc SKILL.md:133
    Writes to a shell startup file
    echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.zshrc
  • low Dangerous commands cmd-pipe-to-shell examples.md:5
    Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file; quoted — discussed, not commanded)
    > **Note (v1.1+):** The skill now leads with the **fast-path one-liner** (`curl -fsSL https://memex.parallelclaw.ai/install.sh | bash`) after Discovery — see Example 0 below. The legacy five-step exam
    fixturequoted
  • low Dangerous commands cmd-shell-rc examples.md:148
    Writes to a shell startup file (test fixture / example file)
    > echo 'export PATH=~/.npm-global/bin:$PATH' >> ~/.zshrc
    fixture
  • low Dangerous commands cmd-shell-rc SKILL.md:30
    Writes to a shell startup file (documentation table row)
    | `echo 'export PATH=...' >> ~/.zshrc` | EACCES auto-fix — moves npm prefix to `~/.npm-global` so `npm install -g` works without sudo. **Idempotent** — re-running is safe. | Standard npm prefix workar
    table

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5651 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 74/100

  • 0Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, read, web, node) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 5651 tokens
  • 100Steps. 40 steps
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 23 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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

  • +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
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 6 example trigger phrases
  • +3Description length 796: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 40 items
  • +4Has examples (15 code blocks)

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

External checks

ClawHub: suspicious
This appears to be a real local memory installer, but it needs review because it runs an unpinned remote installer and persistently indexes private chat history across tools.
LLM: suspicious (high) · VirusTotal: · 29 May 2026