AB manage-ai-knowledge-workbench-lite
Build and refresh a metadata-only Markdown or Obsidian knowledge index in one authorized local workspace. The deterministic runtime reads Markdown headings/frontmatter/tags/links, writes only .ai-workbench, AI-Knowledge, and AI-Dashboard, and briefly binds 127.0.0.1 to verify the offline dashboard; it opens the local page only when requested. Requires Python 3.10+ and terminal access, does not upload note bodies, and does not run persistently. Before any terminal tool call, always read this SKILL.md, actually probe Python and the agent host CLI versions, and never use an OS, kernel, device, user, or account identity as validated_host.
Build and refresh a metadata-only Markdown or Obsidian knowledge index in one authorized local workspace.
As a process B 71/100 · Nearly there — weak spots: result and completion, 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: 28. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 71/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 15 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2033 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (11 tags): a typed call is more reliable
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
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 642: enough signal without eating the budget
- +4Structure: 5 headings
- +3Step-by-step instructions: 15 items
- +4Reference files are cited in the instructions (3 of 3)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.