agentleFS
Sign inStart free
aksheywaksheyw/career-command-center-template/skills/evaluate/SKILL.md

evaluate

Skill1 starsChanged 4 months agoMITView on GitHub

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

25 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use compare, triage and 5 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • n24q02mSkill

    compare

    Structured comparison of 2+ alternatives with consistent criteria and decision matrix

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 4 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 3 projects that use this

  • SentrySkill

    review

    Fixture review skill.

    Also in 4 projects that use this

  • NVIDIASkill

    research

    Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

7 rules. 0 are common, 4 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

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

    line 18
  2. Very specific:

    Use the exact output format from evaluation-framework.md.

    line 42
  3. Distinctive:

    All scores with brief justifications

    line 44
  4. Very specific:

    Never invent metrics — only use verified data from YOUR_PROFILE.md

    line 57
  5. Very specific:

    Never overclaim ownership — follow the accuracy guardrails in SKILL.md

    line 58
  6. Distinctive:

    If posting is older than 60 days, flag it prominently

    line 60
  7. Distinctive:

    If the role is clearly below the user's target level, note the downlevel risk

    line 61

“Common” is measured: kept by at least 6 in 10 of the 24 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free