BF local-deep-research
Multi-cycle deep research using locally-hosted LDR (Local Deep Research) service. Use when user asks for comprehensive research with citations, literature reviews, competitive intelligence, or any research requiring exhaustive web search with iterative question generation. Triggers on: "deep research", "research this topic", "comprehensive analysis with sources", "literature review", "investigate [topic]", "quick summary on [topic]", "detailed report on [topic]", "research in Spanish/French/etc", or when academic-deep-research is requested but using local LDR instance.
As a process F 49/100 · Will not run — References files that are not bundled: url
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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- The text references files that are not there: add them or drop the references.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Exfiltration
net-credential-usescripts/ldr-research.sh:116Credential used in a network call (verify the destination is the intended service)response=$(curl -s -w "\n%{http_code}" -b "$COOKIE_JAR" -H "X-CSRFToken: $CSRF_TOKEN" --max-time "$HTTP_TIMEOUT" \
Files scanned: 6. 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: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Multi-cycle deep research using locally-hosted LDR (Local Deep Res… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value - warning
missing-refreference to a missing file: url - note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: url
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Steps. 54 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2280 tokens
- low 10 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -42 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 575: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 54 items
- +4Has examples (7 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.