resume-job-match-lab

Tailor resumes and project bullets to a target role, quantify gaps, and prepare an interview-ready evidence map.

Security Scan

The skill is internally consistent with its stated purpose: it uses a small local Python helper and a local keywords CSV to produce ATS-style keyword matches; it requests no credentials, has no remote installs, and does not perform unexpected actions.

Purpose & Capability

The skill's name/description (tailor resumes, rewrite bullets, gap analysis, interview evidence map) align with the included materials. The bundled script, however, only computes a keyword-based match score, top keywords, and missing keywords — it does not itself rewrite bullets or produce a full evidence map. That gap is acceptable if the LLM is intended to perform the more sophisticated text transformations using the script's structured output, but the script alone does not implement all promised outputs.

Instruction Scope

SKILL.md instructs the agent to use the local script and resource file and to ask for minimal user inputs. Runtime instructions do not request reading unrelated files, environment variables, or network endpoints. The helper script reads only the two user-supplied text files and writes a JSON result.

Install Mechanism

No install spec is provided (instruction-only skill). The only declared runtime dependency is python3. There are no downloads, remote installers, or archive extraction steps in the package.

Credentials

The skill declares no required environment variables, no credentials, and no config paths. The code does not reference environment variables or external secrets. Requested inputs (resume text, job description, etc.) are appropriate for the stated purpose.

Persistence & Privilege

The skill is not force-included (always: false) and does not request persistent privileges or modify other skills or system settings. It uses local, auditable files only.

Assessment

This skill appears safe and coherent: it is local, needs only python3, and asks for the resume and job description you provide. Note the included script is a small keyword matcher that outputs a score and missing keywords — the LLM is expected to generate rewritten bullets, gap analysis, and an evidence map using that output. Before using generated bullets in real applications, review them carefully (do not accept fabricated metrics or claims). If you care about privacy, avoid pasting highly sensitive PII into the tool or run the script locally on your machine (it is auditable). If you need the script to do more (e.g., automated file edits or bulk processing), verify those actions explicitly before granting permission.

Purpose

Tailor resumes and project bullets to a target role, quantify gaps, and prepare an interview-ready evidence map.

Trigger phrases

• 简历匹配岗位
• tailor my resume
• ATS 优化
• job match analysis
• 面试证据图

Ask for these inputs

• resume text
• job description
• target seniority
• region/industry
• portfolio or projects if any

Workflow

1. Extract must-have and nice-to-have requirements from the job description.
2. Score resume coverage against the keyword template.
3. Rewrite bullets to emphasize outcome, scope, and tools without fabricating claims.
4. Generate a gap analysis and interview evidence map.
5. Return both a conservative ATS version and a human-friendly version.

Output contract

• match scorecard
• rewritten bullets
• gap analysis
• interview evidence map

Files in this skill

• Script: {baseDir}/scripts/resume_match.py
• Resource: {baseDir}/resources/ats_keywords_template.csv

Operating rules

• Be concrete and action-oriented.
• Prefer preview / draft / simulation mode before destructive changes.
• If information is missing, ask only for the minimum needed to proceed.
• Never fabricate metrics, legal certainty, receipts, credentials, or evidence.
• Keep assumptions explicit.

Suggested prompts

• 简历匹配岗位
• tailor my resume
• ATS 优化

Use of script and resources

Use the bundled script when it helps the user produce a structured file, manifest, CSV, or first-pass draft. Use the resource file as the default schema, checklist, or preset when the user does not provide one.

Boundaries

• This skill supports planning, structuring, and first-pass artifacts.
• It should not claim that files were modified, messages were sent, or legal/financial decisions were finalized unless the user actually performed those actions.

Compatibility notes

• Directory-based AgentSkills/OpenClaw skill.
• Runtime dependency declared through metadata.openclaw.requires.
• Helper script is local and auditable: scripts/resume_match.py.
• Bundled resource is local and referenced by the instructions: resources/ats_keywords_template.csv.