BC Speaking
Finds and tracks paid speaking opportunities that fit your own topics by scraping conference CFPs and speaker pages, ranks them by fit and urgency with deadlines, and drafts talk and panel proposals. USE WHEN speaking engagements, speaking opportunities, find speaking, conferences, keynote, CFP, paid speaking, where should I speak, propose talks, panel topics. NOT FOR media appearances, podcasts, or general PR.
Promises to find conferences by CFP, rank them by relevance to your topics, and draft talk proposals. Nine files and one script, 1147 tokens total. Quality score 82, process score 54. No critical errors, linter passes.
Should parse conference pages and rank by deadlines and expertise match. Files look intact, but no model runs—unclear how well it handles real CFPs. Process score of 54 signals potential issues in scraping or ranking logic, though the system found no critical problems.
Worth installing if you hunt speaking gigs regularly. It will work, but verify the first ranking manually before trusting the ranking logic.
Finds and tracks paid speaking opportunities that fit your own topics by scraping conference CFPs and speaker pages, ranks them by fit and urgency with…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 9. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - note
frontmatter-keyunknown frontmatter key "evals"
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 6 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1147 tokens
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 414: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.