AB saas-idea-scout
Chat-driven SaaS idea discovery and validation pipeline. Generates 8 idea seeds conversationally, then fans out 24 sub-agents across 3 phases — discovery, critique, and evaluation — to produce scored, ranked PRDs with adversarial validation and contextual founder-aware ranking. Key features: parallel agentic swarm with self-healing, adversarial critique gauntlet, separation of concerns across research/critique/evaluation roles, cron watchdog for auto-recovery, and 10-dimension scoring with holistic founder-contextual judgment. Use for first-pass validation of product opportunities, stress-testing startup ideas, or surfacing promising directions before committing to deeper research.
As a process B 67/100 · Nearly there — weak spots: result and completion, when it triggers, 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5604 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 19 mutating operations with no state check
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5604 tokens
- 100Tools and files. No external tools needed
- 100Steps. 47 steps
- 100Failures and branches. 10 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (9 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
- +1No license
- +2Single-language instructions
- +3Description length 690: enough signal without eating the budget
- +4Structure: 38 headings
- +3Step-by-step instructions: 47 items
- +4Has examples (32 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.