cv-scorer

Name: cv-scorer
Author: tronghieu

37stars20forks

How to install cv-scorer?

tronghieu/agent-skills/cv-scorer

$npx -y skills add tronghieu/agent-skills --skill cv-scorer

Installs into the current project.

Summary

Score candidate CVs on a 100-point scale against a Job Description. Use this skill when the user wants to evaluate, score, rank, or screen candidate CVs/resumes against a JD. Also trigger when the user mentions 'review CV', 'screen resume', 'rate candidates', 'shortlist', or any

Files · 1

View on GitHub

SKILL.md

1	# CV Scorer — Candidate CV Evaluation
2
3	This skill evaluates how well a candidate's CV matches a specific Job Description (JD), producing a structured score out of 100.
4
5	## Workflow
6
7	### Step 1: Identify Inputs
8
9	Two inputs are required:
10	- Job Description (JD): The job posting with requirements, qualifications, and responsibilities
11	- CV(s): One or more candidate CVs (markdown, text, or PDF)
12
13	If the user hasn't provided a JD, ask for it. If the JD is already available in context (e.g., a file on Drive or in the project directory), read it directly.
14
15	Reading PDF files: Use the `/pdf` skill to extract text from PDF CVs — it handles multi-page documents and formatted layouts reliably.
16
17	### Step 2: Analyze the JD
18
19	Before scoring, extract from the JD:
20	- Must-have skills vs nice-to-have skills
21	- Experience requirements (years, seniority level, domain)
22	- Education requirements
23	- Special requirements (languages, certifications, travel, etc.)
24
25	### Step 3: Score Against Rubric
26
27	Score each CV across 5 criteria using `references/scoring-rubric.md`:
28
29	\| Criterion \| Weight \| Max Points \|
30	\|-----------\|--------\|------------\|
31	\| JD Matching \| ×3 \| 30 \|
32	\| Work Experience \| ×2.5 \| 25 \|
33	\| Project & Impact \| ×1.5 \| 15 \|
34	\| Education \| ×1.5 \| 15 \|
35	\| CV Quality \| ×1.5 \| 15 \|
36	\| Total \| \| 100 \|
37
38	### Step 4: Output
39
40	Output JSON for each CV using the format in `references/output-format.md`.
41
42	Recommendation thresholds:
43	- Recommend (≥ 70): Invite for interview
44	- Maybe (50–69): Consider if candidate pool is thin
45	- Pass (< 50): Not a fit
46
47	### Step 5: Batch Processing
48
49	When scoring multiple CVs:
50	1. Score each CV independently — no cross-comparison during scoring (safe to parallelize)
51	2. After all CVs are scored, produce a summary ranking (highest to lowest)
52	3. Use the batch summary format in `references/output-format.md`
53
54	## Scoring Principles
55
56	- Objective: Score based on facts in the CV, avoid over-inference
57	- Fair: Apply the same standard consistently across all candidates
58	- Red flag detection: Repetitive content, inflated metrics, unexplained career gaps, contradictory information
59	- Output language: Match the user's language (respond in the same language the user is using)
60	- No bias: Do not evaluate based on age, gender, ethnicity, or personal factors unrelated to the job

People who liked this also viewed

6 picks

Type

cv-scorer

37stars20forks

View on GitHub

How to install cv-scorer?

tronghieu/agent-skills/cv-scorer

$npx -y skills add tronghieu/agent-skills --skill cv-scorer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# CV Scorer — Candidate CV Evaluation
2
3	This skill evaluates how well a candidate's CV matches a specific Job Description (JD), producing a structured score out of 100.
4
5	## Workflow
6
7	### Step 1: Identify Inputs
8
9	Two inputs are required:
10	- Job Description (JD): The job posting with requirements, qualifications, and responsibilities
11	- CV(s): One or more candidate CVs (markdown, text, or PDF)
12
13	If the user hasn't provided a JD, ask for it. If the JD is already available in context (e.g., a file on Drive or in the project directory), read it directly.
14
15	Reading PDF files: Use the `/pdf` skill to extract text from PDF CVs — it handles multi-page documents and formatted layouts reliably.
16
17	### Step 2: Analyze the JD
18
19	Before scoring, extract from the JD:
20	- Must-have skills vs nice-to-have skills
21	- Experience requirements (years, seniority level, domain)
22	- Education requirements
23	- Special requirements (languages, certifications, travel, etc.)
24
25	### Step 3: Score Against Rubric
26
27	Score each CV across 5 criteria using `references/scoring-rubric.md`:
28
29	\| Criterion \| Weight \| Max Points \|
30	\|-----------\|--------\|------------\|
31	\| JD Matching \| ×3 \| 30 \|
32	\| Work Experience \| ×2.5 \| 25 \|
33	\| Project & Impact \| ×1.5 \| 15 \|
34	\| Education \| ×1.5 \| 15 \|
35	\| CV Quality \| ×1.5 \| 15 \|
36	\| Total \| \| 100 \|
37
38	### Step 4: Output
39
40	Output JSON for each CV using the format in `references/output-format.md`.
41
42	Recommendation thresholds:
43	- Recommend (≥ 70): Invite for interview
44	- Maybe (50–69): Consider if candidate pool is thin
45	- Pass (< 50): Not a fit
46
47	### Step 5: Batch Processing
48
49	When scoring multiple CVs:
50	1. Score each CV independently — no cross-comparison during scoring (safe to parallelize)
51	2. After all CVs are scored, produce a summary ranking (highest to lowest)
52	3. Use the batch summary format in `references/output-format.md`
53
54	## Scoring Principles
55
56	- Objective: Score based on facts in the CV, avoid over-inference
57	- Fair: Apply the same standard consistently across all candidates
58	- Red flag detection: Repetitive content, inflated metrics, unexplained career gaps, contradictory information
59	- Output language: Match the user's language (respond in the same language the user is using)
60	- No bias: Do not evaluate based on age, gender, ethnicity, or personal factors unrelated to the job

People who liked this also viewed

6 picks

Type