BC beckmann-x-self-improving-proactive
Combination skill that adds the Beckmann Knowledge Graph as a deep-reasoning escalation layer on top of the Self-Improving + Proactive Agent (ivangdavila). Everyday tasks run through the Self-Improving + Proactive Agent as usual. This skill defines exactly when and how to switch to the Beckmann Knowledge Graph and how to feed insights back into hot/warm/cold memory — only after explicit user consent. Uninstalling this skill leaves the Self-Improving + Proactive Agent fully intact and offers an optional clean removal of all #beckmann memory entries.
Combination skill that adds the Beckmann Knowledge Graph as a deep-reasoning escalation layer on top of the Self-Improving + Proactive Agent (ivangdavila).
As a process C 63/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
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
- note
frontmatter-keyunknown frontmatter key "requires"
Process rating: all ten parameters 63/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 100Tools and files. No external tools needed
- 100Steps. 32 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3142 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 554: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.