AB Memory
Remembers, recalls, and organizes durable facts in a categorized markdown store at ~/Clawic/data/memory/, parallel to built-in agent memory. Use when the user says remember this, save this, note that for later, or don't forget; when they ask what did I tell you about X, when did we decide Y, or who is Z; when a stored fact is wrong, outdated, or contradicts what they just said; when they want something forgotten or deleted; when recall misses, returns stale facts, or slows down as the store grows; when duplicate or conflicting entries appear; when consolidating scattered notes, importing an existing vault, or sharing memory across devices and agents. Not for session-scoped context the runtime already holds, note-taking apps (notes), journaling practice (journal), or study techniques like spaced repetition (learn, active-recall).
Remembers, recalls, and organizes durable facts in a categorized markdown store at ~/Clawic/data/memory/, parallel to built-in agent memory.
As a process B 65/100 · Nearly there — weak spots: inputs and preconditions, running it twice, 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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 65/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 19 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 4872 tokens
- 100Steps. 46 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- high The skill tells the model to perform an irreversible action with no human approval
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
- +3Description length 840: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.