BC mnemosyne
Cognitive memory engine for AI agents: gives OpenClaw/Hermes human-like long-term memory using 140 years of cognitive psychology (compound-cue theory), not embeddings. Zero LLM API, zero vector DB, pure Markdown storage. Use when the agent needs cross-session recall of user facts, preferences, decisions, or conversation history; when setting up persistent memory that survives restarts; when the user asks 'do you remember X' or complains the agent forgets; when memory must stay 100% local with no API cost. Beats embedding-based systems on Memory-Native benchmarks (nDCG 0.238, 5.2x) with ~7ms keyword search.
As a process C 58/100 · Has gaps — weak spots: result and completion, inputs and preconditions, progress reporting
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: 5. 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 58/100
- 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
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 12 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 493 tokens
- 100Running it twice. No mutating operations
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
- -5TODO / placeholder text left in the skill
- -2localhost URLs: will not work for another user
- -43 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 613: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 12 items
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.