# Artifact Eval

> The spec-based judge-and-revise loop for job-search artifacts. Use it to grade and improve a resume, cover letter, or outreach message before it's sent ("evaluate this resume", "is this cover letter good enough?", "score my outreach", or automatically inside resume-tailor / cover-letter / networking-and-referrals). Picks the rubric by artifact_type, runs writing-quality DETECT as stage 0, JUDGES against weighted dimensions + hard gates returning PASS/REVISE/FAIL with specific fixes, REVISES surgically, and RE-JUDGES as a fresh pass so nothing rubber-stamps itself. The scored judge. For a slop check on its own with no rubric or score, use `writing-quality`.

- Skill: `guerrilla2799/artifact-eval-2` (Agent Skill)
- Install (CLI): `npx get-skill add guerrilla2799/artifact-eval-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/guerrilla2799/artifact-eval-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: guerrilla2799 (https://skillmd.com/u/guerrilla2799)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/guerrilla2799/artifact-eval-2

---


# Artifact Eval

A lightweight evaluation harness for the three artifacts that leave the system and reach a human: **resume, cover-letter, outreach.** It scores against a fixed spec, gives actionable fixes (never vague), revises only what's flagged, and re-judges independently until PASS. The generator never grades its own work.

## When to use
- "Evaluate / grade / score this resume | cover letter | outreach message."
- "Is this good enough to send?" / "What would make this stronger?"
- **Automatically** as the final quality gate inside `resume-tailor`, `cover-letter`, and `networking-and-referrals` before their output is handed to the user.

## Inputs
- Reads: the artifact text (from the calling skill, a `workspace/` path, or pasted), and the `artifact_type` (`resume` | `cover-letter` | `outreach`). For a resume/cover letter, also read the JD from `workspace/pipeline/applications/<id>-*.md` so JD-match can be scored against real text.
- Needs from user: `artifact_type` if not obvious. For outreach: who it's to and the intended ask, if not clear from the text.

## Workflow
1. **Select the spec** by `artifact_type` (the three rubrics are inline below). If type is ambiguous, ask. Do not guess a rubric.
2. **Stage 0, `writing-quality` DETECT.** Run it first. Its output feeds the no-slop dimension AND is a hard input to the gate check (heavy slop can fail the gate outright). Never skip stage 0.
3. **JUDGE (independent pass).** Score every weighted dimension 0–100 and check each hard gate. Judging must be adversarial and specific: every deduction names the exact line/phrase and the fix. Vague feedback ("make it stronger," "add more impact") is not allowed. Say *what* to change to *what*.
   - Compute weighted score = Σ(weight × dimension_score) / 100.
   - Verdict:
     - **FAIL.** Any hard gate fails (fabrication, over length, wrong/no recipient, etc.). Gate failures are non-negotiable. A beautiful résumé that lies or runs 3 pages FAILs.
     - **REVISE.** All gates pass but weighted score < 80.
     - **PASS.** All gates pass AND weighted score ≥ 80.
4. **If PASS** → log and return (score + verdict + the artifact). Done.
5. **If REVISE (or a salvageable FAIL)** → **revise surgically.** Fix only what the judge flagged and keep everything that scored well. Do not rewrite wholesale. That discards working material and drifts from facts. For a FAIL on fabrication, the fix is to cut or correct the false claim, never to dress it up.
6. **RE-JUDGE as a fresh pass.** Re-run steps 2–3 on the revised artifact *from scratch*. The judge does not trust the reviser's self-assessment and does not rubber-stamp. Re-run stage 0 too (a revision can introduce new slop).
7. **Loop** REVISE ↔ RE-JUDGE until PASS or until two revise cycles yield no score gain. Then stop and hand the user the specific blockers (usually a missing real fact only they can supply). Never fabricate to force a PASS.
8. **Log every cycle.** Including failed ones, because the failures are the trend data.

## The three specs (inline)

### resume
- **Hard gates (any fail → FAIL):**
  - **No fabrication.** Every title, date, metric, and claim traces to the user's real history/`profile/`. No invented numbers.
  - **ATS-parseable.** Single-column-friendly, standard section headers, no tables/text-boxes/images/headers-footers that break parsers, real bullet characters, a plausible keyword match to the JD.
  - **≤ 2 pages** (≤ 1 for early-career).
- **Weighted dimensions (→ /100):**
  - JD / keyword match, 30 (does it mirror the JD's real requirements and language without stuffing?)
  - Quantified impact, 25 (bullets show outcome + metric, not duties)
  - Relevance / cut, 20 (irrelevant roles and bullets trimmed, with the top third targeting this JD)
  - Clarity & scannability, 15 (strong verbs, consistent tense, skimmable in 10 seconds)
  - No-slop, 10 (from stage 0)

### cover-letter
- **Hard gates:**
  - **One page** (~250–400 words).
  - **No fabrication.**
  - **Addressed to a real person** (named hiring manager/team lead). A generic "Hiring Team" is acceptable only when no name is findable. "To Whom It May Concern" fails.
- **Weighted dimensions:**
  - Angle strength, 30 (a specific reason-to-believe / throughline, not a résumé in prose)
  - Proof specificity, 25 (concrete evidence + numbers, tied to their needs)
  - Company fit / insight, 20 (shows real knowledge of the company/role, not boilerplate)
  - Voice + no-slop, 15 (sounds like a person and passes stage 0)
  - Close, 10 (specific, confident next step, no empty CTA)

### outreach
- **Hard gates:**
  - **< 90 words.**
  - **Exactly one ask** (one clear, low-friction request, not two and not zero).
  - **Genuine personalization** (a real, specific detail about this person/company, not a mail-merge token).
- **Weighted dimensions:**
  - Hook, 30 (the opener earns the next line, and is specific rather than "I hope this finds you well")
  - Specificity / evidence, 30 (a concrete reason for reaching out, with credible relevance)
  - Clarity of the ask, 25 (the one ask is unmistakable and easy to say yes to)
  - No-slop, 15 (from stage 0)

## Output
- Writes to: the calling skill's output file by default. If run standalone, it returns to chat (and appends to an eval log at `workspace/output/eval-log.md`).
- Format, every run:
  1. **Score.** Weighted /100 + each dimension's score.
  2. **Verdict.** PASS / REVISE / FAIL, with gate results (pass/fail per gate).
  3. **Fix list.** Specific, actionable, line-referenced. No vague notes.
  4. **The revised artifact** (if a revision ran), the final PASS-ing version.
  5. **Cycle log line.** `artifact-eval: <type> | cycle N | score M | verdict` (all cycles, including failures).

## Rules & quality bar
- **The generator never grades itself.** JUDGE and RE-JUDGE are fresh, adversarial passes. The reviser's opinion of its own work counts for nothing.
- **Gates are absolute.** No weighted score buys back a failed gate. Fabrication, over-length, or no real recipient = FAIL, full stop.
- **Fixes must be specific.** Every deduction says which line and what to change it to. Ban "tighten this" / "add impact" with no target.
- **Revise surgically.** Touch only what's flagged and preserve what scored well. No wholesale rewrites.
- **Never fabricate to pass.** If the only path to ≥80 is inventing a metric or a recipient, stop and tell the user what real input is needed.
- **Log every cycle, failures included.** That's the trend signal.
- **PASS = all gates pass AND weighted ≥ 80.** Both, always.

## Related skills
- Runs: `writing-quality` (DETECT) as stage 0.
- Called by: `resume-tailor`, `cover-letter`, `networking-and-referrals` before they finalize. `interview-followup` and `linkedin-presence` run `writing-quality` directly (no dedicated spec here yet).
- Sibling pattern to: the ID/quality discipline in `application-tracker` (structured, logged, no fabrication).

