BC deep-research-framework
Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty statements. Use when the user asks for a research report, topic investigation, or competitive analysis.
The skill promises to structure deep research: define the question and tier sources first, cross-verify, then write reports with conclusions upfront and explicit uncertainty caveats. One instruction file at 973 tokens, no scripts or sandbox testing. Quality score 76, process score 57—the gap suggests methodology is documented but didn't pass validation. No critical errors, but no model runs either.
Works for Claude and Hermes if you already know how to organize research and want a checklist. Don't expect automated verification. Install it as a template, not a solution.
Framework for deep research reports: define the question and tier sources first, cross-verify, then write conclusion-first reports with explicit uncertainty…
As a process C 57/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
The same skill appears in 2 more places: agentic-awesome-skills, agentic-awesome-skills
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 260 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - note
frontmatter-keyunknown frontmatter key "risk" - note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_repo" - note
frontmatter-keyunknown frontmatter key "source_type" - note
frontmatter-keyunknown frontmatter key "date_added" - note
frontmatter-keyunknown frontmatter key "tools" - note
frontmatter-keyunknown frontmatter key "license_source"
Process rating: all ten parameters 57/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 26 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1060 tokens
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 260: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 26 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.