SKILLEMALL.ai

BF deep-research-framework

This skill should be used when the user requests a structured, in-depth research on a specific topic, industry, technology, product, market, person, organization, or any domain-specific subject. Trigger phrases include: "深度调研", "帮我研究一下", "做一份调研报告", "分析一下XX行业/市场/技术", "写一份研究报告", "deep research", "research report", "调研", "研究报告", "行业报告", "竞品分析", "market research", "技术调研", "可行性分析", "尽职调查". This skill guides a rigorous, multi-source, evidence-balanced research process that: - Defines research audience and objectives before starting - Decomposes the topic into structured dimensions - Gathers evidence from multiple sources with credibility ratings - Includes counterevidence and conflicting viewpoints - Flags information gaps honestly instead of fabricating - Delivers a structured report plus a one-page summary card

ClawHub Agent Skills author: orzmicke-coder v1.0.0 MIT-0 2 files body ≈ 1 737 tokens Open the sourceclawhub.ai analyzed 2 d ago

As a process F 47/100 · Will not run — References files that are not bundled: references/dimension-templates.md, references/credibility-rubric.md, assets/report-template.md

ProcedureData and analyticsWriting and documentsInfrastructuretype and topics are labelled automatically from the skill text
JSON
Technical rating
B
87/100
safety, quality, tests
Safety 60%
100
Quality 40%
68
Run on models
none yet
Process rating
F
47/100
Will not run
References files that are not bundled: references/dimension-templates.md, references/credibility-rubric.md, assets/report-template.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • 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: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: references/dimension-templates.md
  • warning missing-ref reference to a missing file: references/credibility-rubric.md
  • warning missing-ref reference to a missing file: assets/report-template.md
  • warning missing-ref reference to a missing file: assets/summary-card-template.md

Process rating: all ten parameters 47/100

Will not run. References files that are not bundled: references/dimension-templates.md, references/credibility-rubric.md, assets/report-template.md
  • 0Tools and files. 4 referenced file(s) missing: references/dimension-templates.md, references/credibility-rubric.md, assets/report-template.md
  • 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
  • 40Consistency. Frontmatter name (deep-research-framework) differs from the folder (chaoxiresearchskill)
  • 65Failures and branches. 3 branches
  • 100Steps. 58 steps
  • 100When it triggers. States when to use and when not to
  • 100Execution cost. Instruction body is 1737 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Description length 818: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • -222 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 58 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.

External checks

ClawHub: clean
This is an instruction-only deep research workflow that asks for web research and citation discipline, without installs, credentials, persistence, or hidden data access.
LLM: benign (high) · VirusTotal: · 29 May 2026