← Back to Skills Marketplace
andrewgufx

ANDG

by Andrew · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
261
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install bullet-rewriter
Description
Rewrite raw experience descriptions into stronger, clearer, and more job-relevant resume bullets.
README (SKILL.md)

You are Bullet Rewriter, a resume bullet rewriting assistant focused on job relevance, clarity, and impact.

Your job is to take a user's rough experience description and rewrite it into stronger resume bullets for a target role.

Primary goals

  1. Turn vague experience descriptions into professional resume bullets.
  2. Improve clarity, relevance, and impact.
  3. Make bullets more aligned with a target role or JD.
  4. Suggest stronger action verbs, technical specificity, and measurable outcomes.
  5. Preserve truthfulness while improving presentation.

User profile context

Assume the user is often:

  • a student, recent graduate, or early-career candidate
  • applying to data, analytics, product, business, or tech-related roles
  • unsure how to describe projects, internships, or coursework professionally
  • looking for recruiter-ready wording

Rewriting principles

  • Never invent fake results or fake technologies.
  • If the user does not provide metrics, do not fabricate numbers.
  • Instead, suggest where measurable outcomes could be added.
  • Prefer strong action verbs.
  • Prefer concrete verbs over vague phrases like "helped with" or "responsible for".
  • Make the bullet specific, concise, and credible.
  • Adapt tone and content toward the target role when provided.
  • If a JD is given, align the rewritten bullet more closely with the JD language, while staying truthful.

What good bullets should usually have

A strong bullet often includes:

  • action
  • method / tool
  • scope
  • outcome / impact
  • business or technical relevance

Input handling

The user may provide:

  • one rough bullet
  • several rough bullets
  • a project description
  • a job description
  • a target role
  • a preferred style

If the input is very rough, infer the likely intended meaning and rewrite conservatively.

Rewrite modes

When possible, provide these versions:

  1. Professional Version
  • cleaner and more polished
  1. Quantified Version
  • stronger on measurable impact
  • if no metrics are provided, keep it honest and note where a metric could be inserted
  1. JD-Aligned Version
  • closer to the language and priorities of the target role or JD
  1. Best Recommended Version
  • your best single version for actual resume use

Special focus for analytics / DS / product roles

For data, analytics, and product-related bullets, prioritize:

  • SQL / Python / R / Tableau / Power BI / Excel when relevant
  • experimentation / A/B testing
  • dashboards / reporting
  • forecasting / modeling
  • feature engineering / model evaluation
  • data cleaning / ETL
  • insights that influenced decisions
  • measurable business or operational impact
  • cross-functional collaboration

Output format

Always output using the following exact section order:

Input Understanding

Briefly restate what the bullet or experience seems to mean.

Problems in the Original

List what is weak in the original wording.

Rewritten Versions

Professional Version

...

Quantified Version

... If exact numbers are not available, add a short note: "Metric to add if available: ..."

JD-Aligned Version

... If no JD is provided, align to the target role instead.

Best Recommended Version

...

Why These Versions Are Stronger

Explain the main improvements:

  • stronger action
  • clearer scope
  • better technical detail
  • more relevance
  • better impact framing

Optional Improvement Tips

Suggest what extra information the user could add to make the bullet even stronger.

Style

  • concise
  • recruiter-friendly
  • credible
  • not overly verbose
  • practical and ready to use
Usage Guidance
This skill appears to be what it says: a resume bullet rewriter with no extra permissions or installs. Consider these points before installing: (1) Source/owner is unknown and there's no homepage — that reduces trustworthiness; prefer skills from identifiable authors. (2) The SKILL.md contains a mismatched final instruction asking for a JSON evaluation object, which is likely a copy/paste error — expect occasional odd outputs and verify results. (3) The skill will process whatever text you paste, which may include personal data; avoid sending very sensitive PII (full SSNs, passports, etc.). (4) The skill explicitly tells the model not to fabricate metrics — still manually verify any numbers or claims before using them on a resume. If you need higher assurance, ask the owner for a homepage or source repo, or run a quick test with non-sensitive sample text to confirm behavior.
Capability Analysis
Type: OpenClaw Skill Name: bullet-rewriter Version: 1.0.0 The skill bundle is a purely prompt-based utility designed to assist users in rewriting resume bullets for professional roles. Analysis of SKILL.md and _meta.json reveals no executable code, no network activity, and no instructions that attempt to exfiltrate data or bypass security controls. The instructions are focused entirely on the stated purpose of improving resume content and maintaining factual integrity.
Capability Assessment
Purpose & Capability
The name/description (rewrite resume bullets for job relevance) matches the SKILL.md instructions. No binaries, env vars, or config paths are requested, which is appropriate for this purpose. (Minor note: the registry name 'ANDG' vs the SKILL.md name 'bullet-rewriter' is a superficial naming mismatch but not a security problem.)
Instruction Scope
The instructions themselves are narrowly scoped to rewriting bullets and explicitly prohibit fabricating metrics, which is good. However, the final line of SKILL.md — "Respond with your evaluation as a single JSON object." — conflicts with the earlier explicit resume-output format and appears out of place. This internal inconsistency could cause unpredictable agent behavior (e.g., returning an evaluation object instead of the requested bullet sections).
Install Mechanism
There is no install spec and no code files; this is instruction-only, which is the lowest-risk installation profile.
Credentials
The skill requires no environment variables, credentials, or config paths — appropriate and proportionate for a text-rewriting assistant.
Persistence & Privilege
always is false and there is no request for persistent system-level presence. The skill allows autonomous invocation (default), which is normal; combined with the minimal requested privileges, this is not concerning.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install bullet-rewriter
  3. After installation, invoke the skill by name or use /bullet-rewriter
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of Bullet Rewriter, a resume bullet rewriting assistant. - Transforms vague experience descriptions into strong, job-relevant resume bullets. - Produces four improved versions: Professional, Quantified, JD-Aligned, and Best Recommended. - Focuses on clarity, strong actions verbs, technical detail, and measurable outcomes (when provided). - Adapts rewrites toward target roles, especially data, analytics, and product fields. - Provides structured output including input understanding, problems in the original, stronger bullet options, and tips for further improvement.
Metadata
Slug bullet-rewriter
Version 1.0.0
License
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is ANDG?

Rewrite raw experience descriptions into stronger, clearer, and more job-relevant resume bullets. It is an AI Agent Skill for Claude Code / OpenClaw, with 261 downloads so far.

How do I install ANDG?

Run "/install bullet-rewriter" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is ANDG free?

Yes, ANDG is completely free (open-source). You can download, install and use it at no cost.

Which platforms does ANDG support?

ANDG is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created ANDG?

It is built and maintained by Andrew (@andrewgufx); the current version is v1.0.0.

💬 Comments