btmoriarty/kochab / skills/opportunity-brief
opportunity-brief
VerifiedResearch a company and a specific role, then produce an honest brief on whether it is worth pursuing. Use this whenever the user mentions a recruiter reaching out, a job posting they found, a company someone told them about, or a role they are weighing. Triggers on "a recruiter contacted me," "should I apply to," "what do you know about [company]," "look into this company," "is this role real," "assess this posting," "vet this opportunity," "a friend mentioned a job at," or when the user pastes a job description, recruiter email, or LinkedIn InMail. Also triggers on "compare these two roles" and "what should I ask the recruiter."
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.4 KB |
| references/brief_template.md | markdown | 3.0 KB |
| references/fit_rubric.md | markdown | 2.5 KB |
| references/research_checklist.md | markdown | 3.6 KB |
references/fit_rubric.md
View on GitHub# Fit Rubric
Assign exactly one rating. Write the rating before you write the justification, so the justification does not drift into flattery.
## Strong
She clears the real screens, and the work matches something she said she wants.
A Strong rating still names the one thing that could sink it. There is always one. Common candidates: an unstated level mismatch, a commute she said she would not make, a certification the posting mentions once, a team that has churned.
Do not award Strong because the title is impressive or the company is well known.
## Stretch
Worth pursuing, and there is a named gap she would have to argue past.
Say what the argument is. "Stretch" without a stated argument is useless to her. If you cannot construct the argument, the rating is Skip.
Examples of a real Stretch: the posting asks for eight years in a domain where she has four, but her adjacent record is genuinely transferable and she can say how. The posting asks for a certification she could earn in a quarter.
## Skip
Name the disqualifier plainly and stop.
Do not soften a Skip into a Stretch to be kind. Reasons to Skip: it violates a hard no in her profile. The core requirement is a skill she does not have and cannot credibly claim. The location does not work and there is no remote variant. The organization shows serious instability. The level is far below or far above where she is.
A Skip is a useful result. It saves her a week.
## Rating hygiene
- **Never inflate.** If a scan produces no Strong, say the day was thin. Padding a brief with generous ratings destroys the tool's value on the day it matters.
- **Level mismatch cuts both ways.** A role asking for two years when she has fifteen is not a Strong just because she clears the bar. It is a level-down, and it should be labeled that way.
- **Prestige is not fit.** A well-funded, well-known company with the wrong role is still the wrong role.
- **Mission and comp.** Rank them the way her profile says to rank them, not the way you would.
- **One rating per role.** If a company has three postings, rate each one.
## Writing the gap
The gap sentence is the most valuable line in the brief. It should be specific enough that she can decide what to do about it.
Weak: "May need more experience in the domain."
Better: "The posting asks for five years running a regulated compliance program. She has three, in an adjacent function. She would need to open with the audit work, and she should expect the recruiter screen to test it."
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |