BD verified-capability-evolver
Extends Capability Evolver with verification, rollback, and promotion gating. Use when an agent logs a learning, proposes a self-improvement, or wants to promote a learning to permanent memory. Before promotion, define a deterministic spec, verify actual output via SettlementWitness, then PASS → promote with receipt_id, FAIL → rollback and log counter-evidence, INDETERMINATE → hold for review." Verification is performed via an external SettlementWitness service. This skill defines the verification requirement and workflow but does not embed API clients or credentials; integration is handled by the runtime or connected verification layer.
Extends Capability Evolver with verification, rollback, and promotion gating.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- 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: 16. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Unexpected scalar at node end at line 2, column 413: …nce, INDETERMINATE → hold for review." Verification is performed via an extern… ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
body-longSKILL.md body ≈ 5781 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 46/100
- 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. 18 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, git, node) that frontmatter does not declare
- 70Execution cost. Instruction body is 5781 tokens
- 85Steps. 155 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 645: enough signal without eating the budget
- +4Structure: 62 headings
- +3Step-by-step instructions: 155 items
- +4Has examples (22 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.