# Evaluate

> Evaluate a JD before applying — 7-block assessment with go/no-go score. Argument: [paste JD text or URL here]

- **Type:** Skill
- **Install:** `agentstack add skill-aksheyw-career-command-center-template-evaluate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [aksheyw](https://agentstack.voostack.com/s/aksheyw)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [aksheyw](https://github.com/aksheyw)
- **Source:** https://github.com/aksheyw/career-command-center-template/tree/main/skills/evaluate

## Install

```sh
agentstack add skill-aksheyw-career-command-center-template-evaluate
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

You are evaluating a job description using the 7-block evaluation framework. The user has pasted a JD or provided a URL.

## STEP 1: Read required files

- `${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/references/evaluation-framework.md` — the 7-block rubric and scoring dimensions
- `${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/SKILL.md` — company-type strategies, verified metrics
- `${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/references/star-stories.md` — STAR stories for Block F mapping
- `${CLAUDE_PLUGIN_ROOT}/skills/resume-customizer/references/story-bank-index.md` — cross-indexed story selection
- `${CLAUDE_PLUGIN_ROOT}/references/YOUR_PROFILE.md` — the user's verified background

## STEP 2: If URL provided, fetch the JD

If the user provided a URL instead of JD text, use WebFetch to retrieve the job description content.

## STEP 3: Run all 7 evaluation blocks

Follow `evaluation-framework.md` exactly:

- **Block A**: Classify the role (archetype, seniority, domain, remote, team size, fit level)
- **Block B**: Cross-reference every JD requirement against the user's verified experience. Use ONLY metrics from `YOUR_PROFILE.md`. Flag gaps with mitigation strategies.
- **Block C**: Assess seniority match and positioning strategy
- **Block D**: Research compensation using WebSearch (Glassdoor, Levels.fyi, Blind, regional equivalents). Cite exact sources with URLs.
- **Block E**: List top 5 resume customizations + top 3 LinkedIn changes
- **Block F**: Map STAR stories to JD requirements using `story-bank-index.md`. Flag any story gaps.
- **Block G**: Assess posting legitimacy (freshness, company health, red flags)

## STEP 4: Score and verdict

Calculate scores for all 6 dimensions (1-5 scale each):

- CV Match, North Star Alignment, Compensation, Culture, Red Flags, Global Score
- Compute average
- Apply threshold: >= 3.5 = GO | 2.5-3.4 = CAUTION | < 2.5 = SKIP

## STEP 5: Output the evaluation report

Use the exact output format from `evaluation-framework.md`. Include:

- All scores with brief justifications
- Verdict with reason
- Key strengths and gaps with mitigations
- Recommended STAR stories for interview prep
- Legitimacy assessment
- Clear next-step recommendation

## STEP 6: If CAUTION or SKIP

Explain specifically what would need to change for this to become a GO. Be honest — don't soft-pedal gaps.

## RULES

- Never invent metrics — only use verified data from `YOUR_PROFILE.md`
- Never overclaim ownership — follow the accuracy guardrails in `SKILL.md`
- Compensation research must cite sources with URLs and dates
- If posting is older than 60 days, flag it prominently
- If the role is clearly below the user's target level, note the downlevel risk

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [aksheyw](https://github.com/aksheyw)
- **Source:** [aksheyw/career-command-center-template](https://github.com/aksheyw/career-command-center-template)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-aksheyw-career-command-center-template-evaluate
- Seller: https://agentstack.voostack.com/s/aksheyw
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.