Install
$ agentstack add skill-kunalrawat425-fix-my-resume-resume-score ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Resume Score: Heuristic ATS Score Estimator
Invocation: /resume score
Scripts: scripts/score_resume.py at the plugin root.
Runs heuristic checks against a resume DOCX or text file and returns per-category scores plus a weighted overall (0–100). Mirrors the rubric in the parent resume skill's references/scoring-rubric.md.
Behavior
Always interview the user briefly before scoring — even though scoring is technically file-only, the score is more useful when contextualized to the role/seniority the user is targeting. Use mcp__conductor__AskUserQuestion (one question per call) to ask:
- Target role and seniority
- Years of experience
- Page-count preference (1 / 2)
- JD available? (paste if yes — used for keyword-coverage commentary)
Skip any answers already inferable from the file's content (e.g., title in header). Then run the score script and present the results with the user's target context applied.
Quick Reference
| Step | What it does | |---|---| | 1 | Brief interview (target role, YoE, page count, optional JD) via AskUserQuestion. | | 2 | Extract text from DOCX (zipfile + ElementTree) or read raw text. | | 3 | Detect bullets via standard markers + strong-verb prefix heuristic. | | 4 | Score 7 categories independently. | | 5 | Compute weighted overall and print breakdown with target-role commentary. |
Categories
- Parsability — column/whitespace-bleed detection.
- Headings — count of standard section headings present.
- Quantification — fraction of bullets containing a number.
- Verb variety — flags any verb used 3+ times.
- Active voice — regex for passive constructions.
- Vague filler — exact-match list of buzzwords.
- Length — word count vs typical 1–2 page range.
Output
ATS score estimate for: my_resume.docx
--------------------------------------------------
parsability 100/100
headings 100/100
quantification 98/100
> 27/27 bullets quantified (100%).
verbs 95/100
> No verb used 3+ times.
active_voice 96/100
> No passive constructions detected.
vague 96/100
length 95/100
visual 95/100
--------------------------------------------------
Overall (weighted) 97.0/100
Caveat
This is a heuristic, not a real ATS scan. For the actual score against a specific scanner, run the file through Jobscan, Resume Worded, Enhancv, or TopResume. Use this skill to catch issues before submission.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kunalrawat425
- Source: kunalrawat425/fix-my-resume
- License: MIT
- Homepage: https://github.com/kunalrawat425/fix-my-resume
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.