SKILLEMALL.ai
RU Sign in

AC claw-recall

Searchable conversation memory that survives context compaction. Indexes session transcripts into SQLite with full-text and semantic search so your agent can recover context after compaction, search past conversations, and find what other agents discussed. Works across multiple agents (OpenClaw + Claude Code). Also indexes Gmail, Google Drive, and Slack. Self-hosted, open source, no cloud dependency. Use when: recovering lost context, searching conversation history, cross-agent knowledge sharing. NOT for: replacing MEMORY.md or storing secrets.

ClawHub Agent Skills author: Rod v2.1.2 2 files body ≈ 1 283 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 60/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting

ProcedureSlackGmailGoogle DriveGitHubAI 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
A
95/100
safety, quality, tests
Safety 60%
100
Quality 40%
88
Run on models
none yet
Process rating
C
60/100
Has gaps
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
the three weakest of ten parameters · all ten

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 · 0

    ✓ No critical or high findings

    Files scanned: 2. 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 60/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 2 mutating operations with no state check
    • 50When it triggers. No condition that starts the skill
    • 55Failures and branches. 1 branches
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 12 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1283 tokens

    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
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 550: enough signal without eating the budget
    • +4Structure: 14 headings
    • +3Step-by-step instructions: 12 items
    • +4Has examples (9 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.

    External checks

    ClawHub: suspicious
    Claw Recall is a coherent memory-search skill, but it indexes broad private content and exposes shared memory across agents or remote HTTP without enough access-control guidance.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026