AC investor-search
Build a sourced list of the family offices, investment groups, private equity firms, VCs and angels in a market — and say honestly how complete it is. Separates real investors from the advisers who sell to them, refuses to merge two firms into one row without proof, and writes CSVs where every claim carries its source and how well it was checked. Needs a web search tool and a fetch tool. Writes its files to the agent's working directory and reads them back, so a second run continues instead of repeating; where it cannot write, it prints the CSV into the chat and reports a partial result rather than claiming a completeness it cannot prove. Use for investor research, deal sourcing, fundraising and capital-raise prospect lists, investor databases, LP, HNW/UHNW and family-office lead generation, sovereign wealth research, CRM enrichment, or filling gaps in a list you already have.
Build a sourced list of the family offices, investment groups, private equity firms, VCs and angels in a market — and say honestly how complete it is.
As a process C 64/100 · Has gaps — weak spots: inputs and preconditions, execution cost, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 11753 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 64/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 13 mutating operations with no state check
- 40Execution cost. Instruction body is 11753 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, read, web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 46 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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)
- +3Description length 889: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- +1No license
- +2Single-language instructions
- +4Structure: 58 headings
- +3Step-by-step instructions: 46 items
- +3Output format is stated explicitly
- +4Has examples (20 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.