AC deep-research-via-gemini-cli-extension
Execute Gemini Deep Research using the gemini-deep-research MCP extension for the Gemini CLI. Use when user wants deep, comprehensive research on a topic — market analysis, industry research, geopolitical analysis, investment research, or any complex multi-source inquiry. Triggers on: deep research X, 帮我研究 X, gemini deep research X, research X thoroughly, 研究一下 X, do a deep search on X, 深度研究 X. Requires: (1) gemini CLI installed (`npm install -g @google/gemini-cli`), (2) gemini-deep-research extension installed, (3) a paid Google AI API key configured via `gemini extensions config gemini-deep-research`. See references/setup-guide.md for setup instructions.
As a process C 63/100 · Has gaps — 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-background-processSKILL.md:122Starts a background / autostarted processnohup bash poll.sh > /dev/null 2>&1 &
Files scanned: 7. 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 63/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 75Steps. 3 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1350 tokens
- low The response is described with custom markup (6 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- -31 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 663: enough signal without eating the budget
- +4Structure: 15 headings
- +3Step-by-step instructions: 3 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.