BB openclaw-sulcus-skill
Equip your agent with Sulcus — thermodynamic memory with a knowledge graph. Full SIU pipeline: SIVU (quality gate) → SICU (classifier) → SILU (entity extraction) → SIRU (adaptive recall). Apache AGE knowledge graph. Multi-signal recall with learned scoring weights. Interaction-based decay. Reactive triggers. Guardrails (output + tool guard). Session-scoped memory. Temporal supersession.
As a process B 66/100 · Nearly there — weak spots: when it triggers, execution cost, running it twice
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 0
✓ No critical or high findings
Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 9197 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 8 mutating operations with no state check
- 40Execution cost. Instruction body is 9197 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 83 steps
- 100Failures and branches. 4 branches, has a failure section
- 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 22 top-level sections: this looks like several domains in one skill
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)
- +1No license
- +2Single-language instructions
- +3Description length 389: enough signal without eating the budget
- +4Structure: 61 headings
- +3Step-by-step instructions: 83 items
- +3Output format is stated explicitly
- +4Has examples (27 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.