BB job-search-tracker
Use this skill when someone is actively managing a job search and references applications, interviews, offers, or recruiter communication. Specific triggers: 'I applied to [company],' 'just submitted an application,' 'track this job,' 'job search dashboard,' 'what jobs have I applied to,' 'any responses from [company] yet,' 'haven't heard back from [company],' 'prep me for the [company] interview,' 'draft a cover letter for [company/role],' 'write a follow-up email to [company/recruiter],' 'thank-you note for the [company] interview,' 'got rejected from [company],' 'got an offer from [company],' 'help me negotiate the [company] offer,' 'salary negotiation,' 'which resume should I send for [posting],' 'does this [draft] sound desperate or templated,' or any message that explicitly names a company in a hiring context. Do NOT trigger on general productivity questions, calendar requests, or unrelated email tasks. Covers: application tracking in a local markdown file, stale-application detection, follow-up and cover-letter drafting with tracker context, interview prep, salary negotiation analysis and counter-offer drafting, tone checks on user drafts, resume-variant recommendations, and optional Gmail/LinkedIn lookups (user-mediated, see Data Handling).
As a process B 71/100 · Nearly there — weak spots: inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1268 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5289 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 71/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 70Execution cost. Instruction body is 5289 tokens
- 100Steps. 133 steps
- 100Failures and branches. 11 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
- low No test case covers injection arriving through data
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)
- +3Description length 1268: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 35 headings
- +3Step-by-step instructions: 133 items
- +3Output format is stated explicitly
- +4Has examples (4 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 49.