BB super-memori
Local-first hybrid memory skill for OpenClaw agents. Use when the agent needs to find, recall, search, or reuse past knowledge across episodic, semantic, procedural, and learning memory; when the user asks things like "what did we do about X", "remember", "find in memory", "что мы делали", or "найди в памяти"; when exact match and meaning-based recall both matter; or when designing, operating, or improving long-term agent memory on a local Ubuntu host. Includes manual-review learning improvement surfaces and memory-health guidance for degraded-mode detection, backup awareness before major operations, and risk-aware memory changes. Optimized for weak models by exposing a small command surface and clear degraded-mode rules.
As a process B 71/100 · Nearly there — weak spots: result and completion, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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.
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
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-shell-rcauto-learner.sh:18Writes to a shell startup fileecho " Configure PROMPT_COMMAND in ~/.bashrc to enable."
-
low Dangerous commands
cmd-autorun-instructionSKILL.md:278Instructs the agent to auto-run a script on every session (detector / deny-list definition)**Precedence rule:** for normal degraded-mode routing, always execute `./health-check.sh --json` and decide `OK` vs `WARN` vs `FAIL` from the parsed JSON `status` field plus payload details. Treat the
detector
Files scanned: 51. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7302 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Result and completion. Does not say what the result is
- 30Running it twice. 7 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7302 tokens
- 100Steps. 89 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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
- low The response is described with custom markup (6 tags): a typed call is more reliable
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
- -36 of 6 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 731: enough signal without eating the budget
- +4Structure: 39 headings
- +3Step-by-step instructions: 89 items
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (1 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.