BB accelerator-application-coach
End-to-end coach for founders applying to startup accelerators (Y Combinator / Techstars / 500 Global / Antler / a16z Crypto Speedrun / Plug and Play / Mass Challenge / SOSV / Founder Institute / Entrepreneur First / regional / vertical accelerators). Use when a founder asks "should I apply to YC", how to write the YC application, video pitch tips, partner-call interview prep, accept-vs-reject decision (multiple accelerators), how to evaluate accelerator quality (terms, network, partners), or what to do with a rejection. Triggers on phrases like "YC application", "Y Combinator essay", "YC video", "accelerator application", "Techstars application", "should I apply YC", "YC interview", "accelerator equity terms", "MFN clause", "post-money SAFE accelerator", "rejected from YC", "accelerator vs angels".
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5578 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 67/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 5 branches
- 70Execution cost. Instruction body is 5578 tokens
- 100Tools and files. No external tools needed
- 100Steps. 194 steps
- 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 10 top-level sections: this looks like several domains in one skill
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 810: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 11 headings
- +3Step-by-step instructions: 194 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.