agentsclimarketplace
Sign in

Resume reorder bullets

Skill g-kartik/agent-skills/skills/resume-reorder-bullets

Reorders resume bullets and subsections to match a job description. Use when the user wants to tailor their resume for a specific role by surfacing the most relevant bullets first.From its SKILL.md

Install
npx -y skills add g-kartik/agent-skills --skill resume-reorder-bullets

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.0 KB, 676 tokens by cl100k_base, as published. Nobody here has run it

Setup

Read config.md from this skill's directory to get RESUME_PATH, CANDIDATE_NAME, and OUTPUT_DIR.

If config.md is missing or any of those variables are not set, tell the user:

"No resume path configured. Edit config.md in the skill directory and set RESUME_PATH, CANDIDATE_NAME, and OUTPUT_DIR." Then stop.

Steps

  1. Validate that the user provided a JD file path as an argument. If not, tell the user and stop.
  2. Read the JD file.
  3. Read the resume file at RESUME_PATH.
  4. Analyze the JD: identify the top priorities (e.g. cloud infra, backend performance, security, data platform). Also extract company_name and position from the JD content.
  5. Produce the reordering recommendation below.
  6. After printing the recommendation, ask the user:

    "Does this ordering look good? Reply yes to save the tailored resume, no to skip, or describe any changes you'd like."

  7. If the user wants adjustments:
    • Incorporate their feedback into a revised recommendation.
    • Print the updated == Recommended Order == and == Summary == sections.
    • Re-ask the same confirmation question (step 6). Repeat until the user says yes or no.
  8. If the user confirms:
    • Apply the recommended ordering to the full resume content (reorder subsections and bullets within them; do not change any text).
    • Derive the output filename as: {CANDIDATE_NAME}_{company_name}_{position}.pdf
      • Use underscores between words, lowercase, no special characters (e.g. karthik_siemens_senior_software_engineer.pdf).
    • Write the reordered resume to OUTPUT_DIR/{filename}.
    • Confirm to the user: Saved to OUTPUT_DIR/{filename}.
  9. If the user declines, acknowledge and stop without writing any file.

Output Format

Print two sections — nothing else — before asking for confirmation.

Recommended Order

List subsections ranked by JD relevance. Within each subsection, list bullets ranked by relevance. Use only the first 5–6 words of each bullet to identify it:

== Recommended Order ==

1. Cloud and Infrastructure
   1. Cut new-region deployment...
   2. Introduced data-sovereign...
   3. Built async Lambda pipeline...
   4. Cut developer onboarding...

2. Performance and Backend
   1. Drove annotation write latency...
   2. Centralized multi-model creation...

3. Data Platform
   ...

4. Security and Auth
   ...

Summary

3–5 sentences explaining the ranking decisions: why the leading subsection leads, which subsections were deprioritized and why, and any notable intra-subsection reordering.

== Summary ==
...

Rules

  • Do not edit any bullet text.
  • Do not add or remove bullets.
  • Do not read any files other than the JD and RESUME_PATH during the recommendation phase.
  • Output only the two sections above before asking for confirmation — no preamble, no explanation outside them.

What ships with it: 1 file

104 B alongside SKILL.md

Gives 0 of the 12 instructions most hr recruiting skills give in 676 tokens

Counted across 356 of the 357 authors here whose files we hold, read 2026-08-07

  • Quantify achievements with specific metricsin 14 of 356, across 6 files
  • Keep the resume under two pagesin 14 of 356, across 6 files
  • Request the full job description if not providedin 12 of 356, across 4 files
  • Extract keywords and prioritize job requirementsin 12 of 356, across 4 files
  • Stop and ask for clarification if required inputs are missingin 12 of 356, across 5 files
  • Map candidate experience to job requirementsin 11 of 356, across 3 files
  • Ask if the user wants adjustmentsin 11 of 356, across 3 files
  • Provide strengths and gap analysis after the resumein 10 of 356, across 2 files
  • Request candidate background details if not providedin 10 of 356, across 2 files
  • Format experience bullets as action verb plus resultin 10 of 356, across 2 files
  • Ask for missing inputs before startingin 10 of 356, across 9 files
  • Use exact job description terminologyin 9 of 356, across 1 file

Said here and by no other author read

  • read config md for required variables
  • require a job description file path
  • identify top priorities in the job description
  • print only recommended order and summary sections
  • ask for confirmation before applying changes
  • revise recommendation based on user feedback

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.