AC memory-management
AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.
The skill promises vector search across agent memory with up to 12,500x speedup and semantic solution retrieval. Files contain three modules with HNSW indexing, persistent storage, and backup logic. Quality score of 87 and safety at 100 look solid, but process score of 51 signals rough edges.
The catch: both backup and consolidate scripts exit with code 133—a hard failure signal, regardless of sandbox labeling them "quiet." The skill targets 10 platforms but has no runtime validation on any. Without working scripts, the promised cross-session memory sync is theoretical.
Skip it. Until scripts stabilize, data loss or consolidation hangs are guaranteed.
AgentDB memory system with HNSW vector search.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
The same skill appears in 1 more place: RA-Skills
How to improve
- 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: 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 14 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 693 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 495: enough signal without eating the budget
- +4Structure: 16 headings
- +3Step-by-step instructions: 14 items
- +4Has examples (12 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.
In the sandbox The scripts kept to themselves
The skill's scripts were run in a throwaway machine: no network, fake keys in the home directory, a tracer watching. We wrote down what they did. Reaching for the network or for secrets caps the technical grade at C; a quiet run adds no points.
Запущено 2 скрипта; каждому дали двадцать секунд, поддельный домашний каталог с ключами и сеть, в которой ничего нет.
scripts/memory-backup.sh | завершился с кодом 133 |
scripts/memory-consolidate.sh | завершился с кодом 133 |
4 Oct 2026