AB duru-obsidian-kb
Build and maintain a personal Obsidian-based knowledge base from articles, papers, repositories, datasets, spreadsheets, and local files. Use when the user wants to collect source material into a local markdown wiki, incrementally compile notes into structured knowledge pages, ask questions against the knowledge base, export research outputs such as markdown briefs or Marp slides, or run health checks for consistency, coverage, and broken links.
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The text contains phrases like "ignore previous instructions" or "you are now…". That is an attempt to hijack the agent: it may break your rules, the system limits or company policy.
An honest skill does not need them: state the role and the rules directly without overriding other instructions. Otherwise catalog scanners and corporate filters will block the listing.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Instruction override
en-ignore-previousscripts/kb_ingest.py:250Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition)if re.search(r"ignore previous instructions|system prompt|developer message|tool call|jailbreak", lower):
detector -
low Exfiltration
read-dotenvREADME.md:76Reads a .env filecp .env.example .env
Files scanned: 21. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Steps. 56 steps
- 100Failures and branches. 8 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2107 tokens
- 100Running it twice. Mutating operations check current state
- 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 (5 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
- +4Description does not say when NOT to use the skill (false activations)
- -32 of 14 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 449: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 56 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.