AB pitch-follow-up-tracker
Track outreach pitches and draft contextual follow-up emails. Monitors a pitch tracker (Google Sheet or local markdown), checks Gmail for replies, flags stale pitches, and drafts tiered follow-ups (Day 3, Day 7, Day 14) that reference the original pitch content. Use when you need to check on pitch follow-ups, draft follow-up emails, review outreach status, find pitches without replies, or manage an outreach pipeline. Triggers on: 'check follow-ups,' 'who hasn't replied,' 'draft follow-ups,' 'outreach status,' 'pitch tracker,' 'stale pitches,' or any request to manage pitch/outreach follow-up.
As a process B 70/100 · Nearly there — weak spots: result and completion, 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 · 0
✓ No critical or high findings
Files scanned: 3. 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 70/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 60Tools and files. Uses tools (read) 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
- 100Steps. 23 steps
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2106 tokens
- 100Running it twice. Mutating operations check current state
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 599: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (15 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.