resume generated in perfect format and skills are aligned
Browse files- graph.py +3 -1
- resume.py +1 -1
- skills/generate-resume.md +77 -26
graph.py
CHANGED
|
@@ -217,7 +217,9 @@ def build_graph(api_key=None, profile_data=None):
|
|
| 217 |
])
|
| 218 |
return {"messages": [AIMessage(content=format_ats_report(analysis))]}
|
| 219 |
|
| 220 |
-
|
|
|
|
|
|
|
| 221 |
|
| 222 |
def resume_generation(state: ChatState):
|
| 223 |
"""Draft, check and render a one-page .docx resume for the loaded job description."""
|
|
|
|
| 217 |
])
|
| 218 |
return {"messages": [AIMessage(content=format_ats_report(analysis))]}
|
| 219 |
|
| 220 |
+
# Cap at 4096 β a one-page resume never needs more, and reasoning models
|
| 221 |
+
# on the free tier silently burn 20k tokens on CoT with nothing left for output.
|
| 222 |
+
resume_llm = build_llm(api_key=api_key, model=RESUME_MODEL, max_tokens=75000)
|
| 223 |
|
| 224 |
def resume_generation(state: ChatState):
|
| 225 |
"""Draft, check and render a one-page .docx resume for the loaded job description."""
|
resume.py
CHANGED
|
@@ -37,7 +37,7 @@ logger = logging.getLogger(__name__)
|
|
| 37 |
# Free model with 131K context β handles the full profile+JD prompt reliably.
|
| 38 |
# The default openrouter/free model silently returns empty content for large prompts.
|
| 39 |
# Override with the RESUME_MODEL env var (a non-reasoning model is faster and never returns empty).
|
| 40 |
-
RESUME_MODEL = os.getenv("RESUME_MODEL", "nvidia/nemotron-3-
|
| 41 |
|
| 42 |
MAX_ATTEMPTS = 3
|
| 43 |
COVERAGE_TARGET = 0.9
|
|
|
|
| 37 |
# Free model with 131K context β handles the full profile+JD prompt reliably.
|
| 38 |
# The default openrouter/free model silently returns empty content for large prompts.
|
| 39 |
# Override with the RESUME_MODEL env var (a non-reasoning model is faster and never returns empty).
|
| 40 |
+
RESUME_MODEL = os.getenv("RESUME_MODEL", "nvidia/nemotron-3.5-lightning:free")
|
| 41 |
|
| 42 |
MAX_ATTEMPTS = 3
|
| 43 |
COVERAGE_TARGET = 0.9
|
skills/generate-resume.md
CHANGED
|
@@ -13,36 +13,82 @@ surface at least 90% of those the candidate documents honestly support, using
|
|
| 13 |
the job description's own wording where the candidate has the skill (for
|
| 14 |
example write "Model Context Protocol (MCP)" or "Retrieval-Augmented
|
| 15 |
Generation (RAG)" if that is how the job description says it).
|
| 16 |
-
Place them in the Skills lines
|
| 17 |
-
|
| 18 |
-
|
| 19 |
|
| 20 |
## Tailoring rules (what makes it job-aligned, not just keyword-stuffed)
|
| 21 |
|
| 22 |
- Order the Skills lines, and the items inside each line, so the terms the job
|
| 23 |
description asks for come first. Rename the three category labels if a
|
| 24 |
better-fitting label is supported (e.g. "Agentic AI & GenAI").
|
| 25 |
-
-
|
| 26 |
-
|
| 27 |
-
-
|
| 28 |
-
Choose which Volunteer and Project entries to keep by relevance to the job.
|
| 29 |
- Reuse the real numbers from the documents (percentages, accuracy, counts).
|
| 30 |
Never invent a number.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
## Strict output rules
|
| 33 |
|
| 34 |
1. Output ONLY the resume. No preamble, no explanation, no closing note, no code fences.
|
| 35 |
-
2. No italics, code spans or tables. The ONLY allowed inline markup is `**bold**`
|
| 36 |
3. No first-person pronouns (I, me, my).
|
| 37 |
-
4. No placeholders such as [ADD METRIC]. If a number is not in the documents,
|
| 38 |
5. Follow the exact structure below; the formatter parses it line by line.
|
| 39 |
6. The result MUST fit on one US Letter page (0.44in side margins, 10pt Times New Roman).
|
| 40 |
|
| 41 |
## Line length
|
| 42 |
|
| 43 |
- Full-width lines: 120 characters maximum.
|
| 44 |
-
- Bullets: 115 characters maximum including the leading "- ".
|
| 45 |
-
- Skills lines may wrap
|
| 46 |
- Row lines (`### Left | Right`): keep Left + Right under 120 characters.
|
| 47 |
|
| 48 |
## Required output format
|
|
@@ -58,19 +104,24 @@ City, State | [Email](mailto:email) | Phone | [LinkedIn](url) | [GitHub](url)
|
|
| 58 |
|
| 59 |
## Experience
|
| 60 |
### Company - Job Title, City, State | Month Year β Month Year
|
| 61 |
-
-
|
|
|
|
|
|
|
|
|
|
| 62 |
|
| 63 |
## Volunteer Experiences & Leadership
|
| 64 |
### Organisation: Role | Remote | Month Year β Month Year
|
| 65 |
-
- Bullet
|
|
|
|
| 66 |
|
| 67 |
## Projects
|
| 68 |
### Project Name https://github.com/user/repo | Month Year
|
| 69 |
-
- Bullet
|
|
|
|
| 70 |
|
| 71 |
## Awards & Honors
|
| 72 |
- Award or publication title | Month Year
|
| 73 |
-
- Award sentence
|
| 74 |
|
| 75 |
## Education
|
| 76 |
### University Name | City, Country
|
|
@@ -85,22 +136,22 @@ Details:
|
|
| 85 |
- Section order is fixed: Skills, Experience, Volunteer Experiences & Leadership,
|
| 86 |
Projects, Awards & Honors, Education. Omit a section only if the documents
|
| 87 |
have nothing for it.
|
| 88 |
-
- Experience roles in reverse-chronological order,
|
| 89 |
starting with a strong past-tense verb (Built, Deployed, Reduced, Engineered...).
|
| 90 |
- Contact line: keep exactly the details found in the documents, with the
|
| 91 |
LinkedIn and GitHub URLs as `[LinkedIn](url)` / `[GitHub](url)` links.
|
| 92 |
Keep the name's wording; no blank line between name and contact line.
|
| 93 |
-
- Skills: exactly three labelled lines
|
| 94 |
-
|
| 95 |
-
|
|
|
|
| 96 |
|
| 97 |
## Bold emphasis
|
| 98 |
|
| 99 |
In Experience, Volunteer and Project bullets, wrap the single most important
|
| 100 |
-
metric or technology phrase
|
| 101 |
`cutting per-query inference cost **30% at production scale**`). At most one
|
| 102 |
-
span per bullet, only where there is a real number or key technology.
|
| 103 |
-
bold anything else.
|
| 104 |
|
| 105 |
## Grounding rules
|
| 106 |
|
|
@@ -108,9 +159,9 @@ These override everything else:
|
|
| 108 |
|
| 109 |
- The candidate documents are the only source of truth about the candidate.
|
| 110 |
Never invent employers, titles, dates, metrics, technologies or outcomes.
|
| 111 |
-
- The job description describes what the employer wants, not what the
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
- If no job description is provided, produce the best general resume from the
|
| 116 |
documents alone and skip the keyword step.
|
|
|
|
| 13 |
the job description's own wording where the candidate has the skill (for
|
| 14 |
example write "Model Context Protocol (MCP)" or "Retrieval-Augmented
|
| 15 |
Generation (RAG)" if that is how the job description says it).
|
| 16 |
+
Place them in the Skills lines AND reword experience/project bullets to use the
|
| 17 |
+
JD's exact terminology where the work honestly involved those technologies.
|
| 18 |
+
If a keyword has no support in the candidate documents, leave it out.
|
| 19 |
|
| 20 |
## Tailoring rules (what makes it job-aligned, not just keyword-stuffed)
|
| 21 |
|
| 22 |
- Order the Skills lines, and the items inside each line, so the terms the job
|
| 23 |
description asks for come first. Rename the three category labels if a
|
| 24 |
better-fitting label is supported (e.g. "Agentic AI & GenAI").
|
| 25 |
+
- Reword experience bullets to use the JD's own language and emphasise the
|
| 26 |
+
matching technologies β do not change the facts, only the framing.
|
| 27 |
+
- Within each role, put the bullets most relevant to the job description first.
|
|
|
|
| 28 |
- Reuse the real numbers from the documents (percentages, accuracy, counts).
|
| 29 |
Never invent a number.
|
| 30 |
|
| 31 |
+
## EXACT PAGE LAYOUT β match this structure precisely
|
| 32 |
+
|
| 33 |
+
The resume must fill exactly one US Letter page (0.44 in side margins, 10pt
|
| 34 |
+
Times New Roman). Use the following section structure and bullet counts β no
|
| 35 |
+
more, no less. This is derived from the validated reference layout.
|
| 36 |
+
|
| 37 |
+
```
|
| 38 |
+
Name + contact line β 2 lines
|
| 39 |
+
|
| 40 |
+
SKILLS (heading) β 1 line
|
| 41 |
+
3 skill category lines (each may wrap) β ~6 lines
|
| 42 |
+
|
| 43 |
+
EXPERIENCE (heading) β 1 line
|
| 44 |
+
Role 1 header β 1 line
|
| 45 |
+
4 bullets β 4 lines
|
| 46 |
+
Role 2 header β 1 line
|
| 47 |
+
4 bullets β 4 lines
|
| 48 |
+
|
| 49 |
+
VOLUNTEER EXPERIENCES & LEADERSHIP β 1 line
|
| 50 |
+
Role 1 header + 2 bullets β 3 lines
|
| 51 |
+
Role 2 header + 2 bullets β 3 lines
|
| 52 |
+
Role 3 header + 2 bullets β 3 lines
|
| 53 |
+
|
| 54 |
+
PROJECTS (heading) β 1 line
|
| 55 |
+
Project 1 header + 2 bullets β 3 lines
|
| 56 |
+
Project 2 header + 2 bullets β 3 lines
|
| 57 |
+
Project 3 header + 2 bullets β 3 lines
|
| 58 |
+
|
| 59 |
+
AWARDS & HONORS (heading) β 1 line
|
| 60 |
+
3 award / publication lines β 3 lines
|
| 61 |
+
|
| 62 |
+
EDUCATION (heading) β 1 line
|
| 63 |
+
University 1 name + degree line β 2 lines
|
| 64 |
+
University 2 name + degree line β 2 lines
|
| 65 |
+
```
|
| 66 |
+
|
| 67 |
+
Rules for staying on one page:
|
| 68 |
+
- **Experience: exactly 4 bullets per role.** If a bullet is long, shorten it β
|
| 69 |
+
do not drop it.
|
| 70 |
+
- **Volunteer: exactly 3 roles, 2 bullets each.** Use all three from the documents.
|
| 71 |
+
- **Projects: exactly 3 projects, 2 bullets each.** Pick the 3 most JD-relevant.
|
| 72 |
+
- **Skills: exactly 3 labelled category lines.** Each line may wrap to 2 rendered
|
| 73 |
+
lines; keep each category under 330 characters.
|
| 74 |
+
- **Bullet line length: 115 characters maximum** including the leading "- ".
|
| 75 |
+
Split long bullets across two logical parts rather than one very long line.
|
| 76 |
+
- Education: university name line + one degree/italic line each. No extra lines.
|
| 77 |
+
|
| 78 |
## Strict output rules
|
| 79 |
|
| 80 |
1. Output ONLY the resume. No preamble, no explanation, no closing note, no code fences.
|
| 81 |
+
2. No italics, code spans or tables. The ONLY allowed inline markup is `**bold**`.
|
| 82 |
3. No first-person pronouns (I, me, my).
|
| 83 |
+
4. No placeholders such as [ADD METRIC]. If a number is not in the documents, omit it.
|
| 84 |
5. Follow the exact structure below; the formatter parses it line by line.
|
| 85 |
6. The result MUST fit on one US Letter page (0.44in side margins, 10pt Times New Roman).
|
| 86 |
|
| 87 |
## Line length
|
| 88 |
|
| 89 |
- Full-width lines: 120 characters maximum.
|
| 90 |
+
- Bullets: 115 characters maximum including the leading "- ".
|
| 91 |
+
- Skills lines may wrap; keep each category under 330 characters.
|
| 92 |
- Row lines (`### Left | Right`): keep Left + Right under 120 characters.
|
| 93 |
|
| 94 |
## Required output format
|
|
|
|
| 104 |
|
| 105 |
## Experience
|
| 106 |
### Company - Job Title, City, State | Month Year β Month Year
|
| 107 |
+
- Bullet 1
|
| 108 |
+
- Bullet 2
|
| 109 |
+
- Bullet 3
|
| 110 |
+
- Bullet 4
|
| 111 |
|
| 112 |
## Volunteer Experiences & Leadership
|
| 113 |
### Organisation: Role | Remote | Month Year β Month Year
|
| 114 |
+
- Bullet 1
|
| 115 |
+
- Bullet 2
|
| 116 |
|
| 117 |
## Projects
|
| 118 |
### Project Name https://github.com/user/repo | Month Year
|
| 119 |
+
- Bullet 1
|
| 120 |
+
- Bullet 2
|
| 121 |
|
| 122 |
## Awards & Honors
|
| 123 |
- Award or publication title | Month Year
|
| 124 |
+
- Award sentence | Month Year
|
| 125 |
|
| 126 |
## Education
|
| 127 |
### University Name | City, Country
|
|
|
|
| 136 |
- Section order is fixed: Skills, Experience, Volunteer Experiences & Leadership,
|
| 137 |
Projects, Awards & Honors, Education. Omit a section only if the documents
|
| 138 |
have nothing for it.
|
| 139 |
+
- Experience roles in reverse-chronological order, 4 bullets each, every bullet
|
| 140 |
starting with a strong past-tense verb (Built, Deployed, Reduced, Engineered...).
|
| 141 |
- Contact line: keep exactly the details found in the documents, with the
|
| 142 |
LinkedIn and GitHub URLs as `[LinkedIn](url)` / `[GitHub](url)` links.
|
| 143 |
Keep the name's wording; no blank line between name and contact line.
|
| 144 |
+
- Skills: exactly three labelled lines (e.g. ML & GenAI / Languages & Frameworks /
|
| 145 |
+
MLOps, Cloud & Data). Include every tool from the candidate's documents that is
|
| 146 |
+
relevant to the JD. Add JD-matched terms first within each line.
|
| 147 |
+
- Awards: one line per item; add " | Month Year" at the end when a date is known.
|
| 148 |
|
| 149 |
## Bold emphasis
|
| 150 |
|
| 151 |
In Experience, Volunteer and Project bullets, wrap the single most important
|
| 152 |
+
metric or technology phrase in `**double asterisks**` (e.g.
|
| 153 |
`cutting per-query inference cost **30% at production scale**`). At most one
|
| 154 |
+
span per bullet, only where there is a real number or key technology.
|
|
|
|
| 155 |
|
| 156 |
## Grounding rules
|
| 157 |
|
|
|
|
| 159 |
|
| 160 |
- The candidate documents are the only source of truth about the candidate.
|
| 161 |
Never invent employers, titles, dates, metrics, technologies or outcomes.
|
| 162 |
+
- The job description describes what the employer wants, not what the candidate
|
| 163 |
+
has. A requirement is never evidence of a skill the candidate has.
|
| 164 |
+
- Do not remove any employer, project or volunteer role from the documents.
|
| 165 |
+
Reword bullets to match the JD's language; do not drop them.
|
| 166 |
- If no job description is provided, produce the best general resume from the
|
| 167 |
documents alone and skip the keyword step.
|