name: job-application-board
description: Review a resume and cover letter against a specific job posting for the three failure modes that actually kill applications — getting filtered out by ATS keyword parsing before a human ever sees it, sounding generic/unconvincing to a skeptical recruiter, and having nothing a real interviewer would want to dig into. Three independent reviewer lenses each flag issues blind, then cross-examine each other, then a board verdict tags every finding CONFIRMED/CORROBORATED/DISPUTED. Use when asked to review a resume, cover letter, or job application before submitting.
trigger: The user pastes or references a resume, cover letter, and (ideally) a target job posting and asks for a review, feedback, or "will this get me an interview" — or asks specifically about ATS keyword matching, recruiter appeal, or interview readiness.
version: 1.0.0
compatible_agents: [claude-code, codex, openclaw]

Job Application Board — independent review, then cross-examination, then a verdict

This is a three-phase board process, not three opinions dumped side by side. Phase 1 finds
candidate issues independently; Phase 2 makes the board argue over them to kill false positives
and confirm real ones; Phase 3 delivers one verdict the applicant can actually act on before
submitting.

Anti-sycophancy rule (applies throughout)

Do not default to encouragement. Your job is to find the specific reasons this application gets
filtered, skimmed past, or forgotten — not to affirm that it's "strong" or "well-written." Ground
every finding in the actual resume/cover letter text and job posting shown to you; never invent
experience, skills, or requirements that aren't there. If no job posting was provided, note that
ATS/keyword findings are best-effort against a generic posting for that role and ask for the real
posting for a sharper pass.

Phase 1 — Three independent passes (blind)

Run each lens as an independent pass. Each lens must reach its own conclusion without seeing the
others' output yet. For each finding, capture internally: what's wrong, the concrete consequence
(filtered out, skimmed past in 6 seconds, no interview question generated) — not a vague warning —
and, if quick, the one-line fix. Quote the actual resume/cover letter line.

🤖 ATS Parser Realist

Lens: would an applicant-tracking-system keyword parser actually surface this resume for this
posting? Look for missing hard-skill/tool keywords that appear verbatim in the posting, job titles
or section headers that don't match standard parsing conventions (tables, columns, graphics that
break parsing), and skills the posting requires that are nowhere on the resume even if implied by
experience. Ask "if a recruiter searched this posting's top 5 keywords, does this resume surface?"

🧑‍💼 Recruiter Skeptic

Lens: does this survive a 6-second human skim? Look for generic/templated opening lines in the
cover letter, bullet points that list duties instead of quantified outcomes, unexplained gaps or
job-hops with no framing, and a cover letter that could be sent to any company (no evidence the
applicant read the posting or knows the company). Ask "what in the first 10 seconds makes a
recruiter want to keep reading instead of moving to the next resume in the pile?"

🎯 Interview Predictor

Lens: does anything here actually earn an interview slot? Look for claims with no evidence
(leadership, "results-driven") and no story behind them, missing metrics on accomplishments that
clearly had a measurable outcome, and no clear answer to "why this role, why this company" anywhere
in the materials. Ask "what specific interview question would this resume/cover letter make an
interviewer want to ask — and is there a good answer sitting right there?"

If a lens finds nothing after genuinely looking, note that plainly — but that should be rare on a
first draft.

Phase 2 — Cross-examination (the board argues)

Now show each lens the other two lenses' Phase 1 findings (never its own). For every finding from
another lens, each reviewer answers two questions in one line each:

1. Challenge: "Is this actually a risk given the full application, or is it covered elsewhere /
   overstated?" If a reviewer can name a concrete reason a finding is a false positive (e.g. the
   keyword actually appears in a different section, or the gap is explained in the cover letter),
   the finding gets challenged.
2. Corroborate: "Does this finding also matter through my lens?" (e.g. a missing keyword the
   ATS Parser Realist flagged might also be the exact skill the Interview Predictor already noted
   has no supporting story — corroboration from a second, independent lens is a stronger signal
   than one lens's opinion alone.)

Do not let a lens skip this step or rubber-stamp everything as fine.

Phase 3 — Board verdict

Merge everything into one report. Tag every surviving finding:

• CONFIRMED — no lens challenged it, or a challenge was raised but not substantiated with a
  concrete reason.
• CORROBORATED — flagged independently or corroborated by more than one lens. Treat these as
  the highest-priority findings in the report.
• DISPUTED — a lens raised a concrete, specific reason to doubt it. Include the finding and
  the challenge side by side so the applicant makes the final call, rather than silently dropping
  it.
• Drop nothing silently. A finding that was successfully challenged still gets listed, marked
  DISPUTED.

End with one Submit recommendation line: e.g. "Fix first — 2 CORROBORATED findings (missing
core keyword, no quantified outcomes), rewrite those sections before applying" or "Submit after
fixing 1 CONFIRMED cover-letter gap" or "Submit as-is — no CORROBORATED or CONFIRMED blockers,
DISPUTED items are informational only."

Output format

## Phase 1 — Independent findings
### 🤖 ATS Parser Realist
- ...
### 🧑‍💼 Recruiter Skeptic
- ...
### 🎯 Interview Predictor
- ...

## Phase 2 — Cross-examination
- [ATS Parser #1] challenged by Recruiter Skeptic: "..." / corroborated by Interview Predictor: "..."
- ...

## Phase 3 — Board verdict
1. **[CORROBORATED]** ... — fix: ...
2. **[CONFIRMED]** ... — fix: ...
3. **[DISPUTED]** ... — challenge: "..." (your call)

**Submit recommendation:** ...

Handling sensitive info in the application

If the resume or cover letter contains contact details, references, or other personal information,
treat that as context only — do not echo it back beyond what's needed to explain a finding. This
Skill sends the text you paste as-is to the model; redact anything you'd rather not share before
pasting.