Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →agentii-ai/full-equity-research
The Auto 档 scenario — a soft-plan orchestrator for a complete fundamental equity research thesis: understand → financials → valuation → synthesize. The body is a soft plan (stages), not a rigid DAG; correctness is enforced by each referenced skill's own requires: preconditions, never by this plan's rigidity (Q2).
Passed 18 of 25 test cases with the skill, and 6 of 25 without it.
and 13 more in the full report
13 fixed5 passed either way6 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
When handing off results from the valuation-methods stage to the DCF stage for Meta Platforms Inc, what is the required context format?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies file paths to generated artifacts as the context format. | Missed | Passed |
The instructions your model reads when the skill loads.
scenario: full-equity-research
stages:
- skill: business-model
- skill: competitive
- skill: recent-quarter
- skill: valuation-methods
- skill: dcf
notes: >-
Foreign issuers use 20-F/6-K instead of 10-K/8-K; small caps may skip dcf.
Dispatch each stage as its own subagent (context isolation, Q2); handoff
passes artifact PATHS, never content (Q13 rule 3).
Validated by validate_scenes.py: registry-key references + acyclicity.
test cases passed, vs 6 / 25 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.