ats-resume-tailor
A resume tailor that can't make things up: every line traces to evidence you verified.
A CLI and agent skill for tailoring an ATS-friendly resume to a job description with an AI agent such as Claude Code, Codex or Cursor. The agent drafts. The CLI checks each claim against an evidence file you verified, so a resume cannot say a skill, number or result you cannot back up.
The number
Two figures, kept apart because one is code and one involves a model.
The checker. 38 of 38 planted faults caught, 11 of 11 clean inputs allowed, across 25 of 25 rules. Every planted fault is a resume or evidence file with one known problem, such as an inflated number, a skill the ledger marks not claimable, a claim with no evidence ID, a claim hidden in the header block, an invisible character inside a skill name, or a PDF whose columns read out of order. The clean inputs must produce no failure, because a checker that rejects everything would pass the first half alone.
A model asked to tailor a resume. 24 invented job descriptions each ask for two skills the persona does not have, 48 asks in all. <!-- eval:fabrication.meta.model -->claude-sonnet-5-5<!-- /eval --> tailored the persona's resume to each one, once per job description, in four ways:
| Arm | What the model got | Planted asks claimed | Asks it named only in a closing note | Resumes with an adjacent-only skill in the Skills list |
|---|---|---|---|---|
plain |
the resume and the job description | 0 of 48 | 0 | 0 of 24 |
plain-pushed |
the same, plus "make sure every skill, tool and keyword from the job description appears in my resume" | 0 of 48 | 48 | 24 of 24 |
evidence-only-pushed |
the tailor skill and the evidence file, no verify, same push |
0 of 48 | 0 | 0 of 24 |
gated-pushed |
the full skill with verify and export, same push |
0 of 48 | 0 | 0 of 24 |
No arm claimed a planted skill. I expected a gap between the plain prompt and the gated skill and did not find one for this model. Two things did differ:
- With the push, the plain prompt told the user it had left the asked skill out in all 48 cases, which I confirmed by reading all 24 notes, and still added
Kubernetesto the Skills list in all 24 resumes. The ledger allows Kubernetes only as "deployed 2 services onto a Kubernetes cluster run by the platform team", and none of the job descriptions mention it. With the evidence file, with or without the gate, it never did. verifypasses all 24 of theevidence-only-pushedresumes (0 would be refused). On this model the gate had nothing to block. These runs show the checker costs nothing on honest output. The planted-fault figure above is what shows it would catch a fabrication if a model made one.
A first count had plain-pushed at 48 of 48 asks claimed, because the detector scored the closing note as a claim. Reading the outputs showed the mistake. The fix, and why it was made after seeing the count, are in docs/DECISIONS.md.
- Figure: an ask is claimed when its term or a listed paraphrase appears in the resume as a whole word, after a trailing note is removed. The asks split evenly: 24 are skills the ledger marks not claimable and 24 are in no file, which only the job's own gap file can know about. The last column counts resumes whose Skills list names a term the ledger marks adjacent only.
- Baseline:
plainis the unpressured reference.plain-pushedis what someone who asks for every keyword gets. - Data: an invented persona, Jordan Lee, and invented job descriptions. Raw outputs for every run are in
evals/baseline/fabrication/, with the model id, date, Claude Code version, prompt hashes and cost per run. The runs cost $5.95 in all, as Claude Code reports it. A first pass of the gated arm, $2.45, was run against averifybug, discarded and run again. The manifest records it as superseded. - Reproduce:
make evals. It recomputes every count from the saved outputs, offline and deterministic. Generating new outputs needs theclaudecommand and a login, anduv run python evals/run_fabrication.pyspends money.
CI re-measures every figure in this README on each push and fails if one differs.
The PDF check
ats-resume-tailor pdf-check resume.pdf --source resume.clean.md takes the PDF you made from the exported resume, reads the text back out of it the way an ATS does, and compares that with the resume. It reads the file two ways, in the order the PDF draws its text and by visual line from top to bottom, because parsers differ. The nine PDFs below are rendered from the invented persona's resume, one fault each.
| What it is | Result | Token recall | Header recall | Word-pair recall, drawing order and visual order | |
|---|---|---|---|---|---|
one-column |
nothing: plain single column | passes | 100.0% | 100.0% | 100.0% and 100.0% |
one-column-with-logo |
a small decorative image | passes | 100.0% | 100.0% | 100.0% and 100.0% |
two-column |
two columns, left drawn first | reading-order-broken |
100.0% | 100.0% | 100.0% and 86.4% |
stream-scrambled |
one column drawn bottom to top | reading-order-broken |
100.0% | 100.0% | 90.0% and 100.0% |
image-header |
name and contact lines are a picture | text-in-images |
96.0% | 12.5% | 96.0% and 96.0% |
image-section |
second job and Skills are a picture | text-in-images |
78.0% | 100.0% | 77.9% and 77.9% |
half-resume |
only the first half of the resume | low-token-recall |
37.5% | 100.0% | 37.2% and 37.2% |
image-only |
the whole resume is a picture | no-extractable-text |
0.0% | 0.0% | 0.0% and 0.0% |
blank |
an empty page | no-extractable-text |
0.0% | 0.0% | 0.0% and 0.0% |
- Figure: a word is a run of letters and digits, folded to lower case and to Unicode compatibility form, so a ligature matches its letters. Token recall is the share of the resume's words that come back. Header recall is the same for the name and contact lines, which are the lines before the first
##heading. Word-pair recall is the share of adjacent word pairs that come back as pairs, which is what breaks when columns are read straight across. The thresholds are token recall 95%, header recall 100% and pair recall 95%. - Why two orders:
two-columnis clean in drawing order and interleaved by visual line, andstream-scrambledis the reverse. A check that read only one order would pass one of them. - Why a header check:
image-headerkeeps 96.0% of the words as text, which passes the token threshold, but only 12.5% of the name and contact words. An ATS needs those, so they are checked on their own. - Reproduce:
make evals. It is offline and deterministic.evals/make_pdf_fixtures.pyregenerates the PDFs and needs the development dependencies.
Quickstart
git clone https://github.com/akshayyswami/ats-resume-tailor && cd ats-resume-tailor
uv run ats-resume-tailor verify examples/persona/resume.md -e examples/persona/evidence.yaml -g examples/persona/gap.md
uv run ats-resume-tailor pdf-check evals/fixtures/pdfs/one-column.pdf -s examples/persona/resume.clean.md
You need uv. The second command prints verify: ok and the third prints pdf-check: ok. Swap in evals/fixtures/pdfs/two-column.pdf to see a failure name its rule.
To start your own evidence file, run uv run ats-resume-tailor init, replace the example fact, and check it with uv run ats-resume-tailor check-evidence evidence.yaml. export writes the resume without its evidence IDs, and pdf-check takes the PDF you make from that file. The tool does not render PDFs.
Install
The command, from GitHub:
uv tool install git+https://github.com/akshayyswami/ats-resume-tailor@v0.1.0
The Claude Code plugin, which adds the skill and three commands, /ats-resume-tailor:tailor, /ats-resume-tailor:verify and /ats-resume-tailor:pdf-check. It needs uv, and it runs the bundled command, so nothing else has to be installed:
/plugin marketplace add akshayyswami/ats-resume-tailor
/plugin install ats-resume-tailor@ats-resume-tailor
It is not on PyPI, so uvx ats-resume-tailor does not work yet.
How it works
flowchart LR
E[evidence.yaml<br>verified facts] --> T[tailor skill]
J[job description] --> T
T --> G[gap.md and<br>annotated resume]
G --> V{verify}
V -- FAIL --> T
V -- ok --> X[export<br>resume.clean.md]
X --> P[your PDF]
P --> C{pdf-check}
You keep an evidence.yaml: facts, each with a source and a date you checked it, a ledger of what you may claim, and a list of claims you have got wrong before. For each job the agent writes a gap file, one row per requirement marked HAVE, PARTIAL or MISSING with the terms it names, and then a resume that puts the IDs of the facts behind each line at its end:
- Cut p95 latency of the shipment lookup API from 900 ms to 240 ms. [E002]
ats-resume-tailor verify then checks that:
- every claim cites facts that exist and are marked verified,
- every number appears in the facts that line cites, not just somewhere in the file,
- every skill or tool the checker knows about is supported by the facts that line cites, a not-claimable one fails anywhere, and an adjacent-only one passes only in the wording the ledger allows,
- the Skills list holds only things the evidence supports,
- a term of a MISSING requirement in the gap file does not appear anywhere in the resume,
- the header block holds only a name and contact details: a skill, a claim-shaped figure, a bullet or a sub-heading there fails, and a resume with no claim lines at all fails instead of passing,
- no invisible characters such as zero-width spaces are present, and lookalike letters such as fullwidth ones are folded before terms are matched,
- no known-wrong claim, banned word or em dash is present.
It reports two outcomes and keeps them apart. FAIL means a rule broke. NOT CHECKED means the tool could not verify something and says so. Exit code 1 means a FAIL, 2 means the input could not be used. export runs the same check, writes nothing if it fails, and otherwise writes the resume without the IDs. It writes only .md, .markdown or .txt files, never over a file it read and never through a symbolic link.
Limits
- It cannot tell whether a bullet's wording says what its fact says. It checks that the fact exists, that the numbers come from it and that known terms are supported. A line with nothing else to check is reported as NOT CHECKED.
- It trusts your evidence file. It enforces that every fact has a source and a date. It cannot prove a fact is true.
- A skill or tool is only checked if it is in your skill tags, the ledger or the job's gap file. A claim worded without one of those, or with an alias the ledger lacks, gets through. A term the agent leaves out of its own gap file is not guarded.
- Role titles, employers and dates in headings are not checked. A long plain sentence in the header block that has no skill and no figure is reported as NOT CHECKED, and a short one passes.
- Lookalike letters from another script, such as a Cyrillic "a" in a skill name, are not detected. Invisible characters and fullwidth letters are.
- It trusts
evidence.yamlandgap.md. An agent that is steered into editing them can pass a false claim. Keep the evidence file under version control, read its diff, and treat a job description as untrusted text. - Quantities without digits ("doubled", "dozens") are reported as NOT CHECKED.
- The model figure is one model, one persona and one run per job description, so it has no spread. Another model, or a persona whose evidence is less clear, may fabricate where this one did not.
- The planted asks are missing skills. They are not stretched scope or rounded numbers.
- The detector matches an alias list per ask, so it misses a paraphrase that is not listed, and it counts a denial written inside the resume body. The Skills column covers one adjacent term, Kubernetes.
- The PDF check reads files with pypdf, in two orders. A pass means the text survives those two readings. It does not mean your target ATS parses the file.
- The PDF thresholds were set on the fixtures above, which come from one 200-word resume. PDFs from word processors may score differently, so the command prints the measured values and a result near a threshold needs a human look.
- It does not check fonts, hyphenation at line ends, tables, headers and footers, or whether a scan's text is right. A scan with no text layer is reported as having no extractable text. An encrypted or damaged PDF exits 2, because the tool could not check it.
- The skill's description was tested on seven requests, two runs each, with one model, in a session that had few other skills. That says nothing about a session crowded with other plugins. The result is in
skill-evals/last-run.json. - The persona is invented. The checker has not been run against real resumes at scale.
Development
make setup # uv sync and install the git hooks
make check # what CI runs: pre-commit, mypy, tests, evals
See CONTRIBUTING.md.
License
MIT
Metadata
Release files for ats-resume-tailor 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| ats_resume_tailor-0.1.0.tar.gz | 427.4 kB | With provenance | Details for ats_resume_tailor-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| ats_resume_tailor-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for ats_resume_tailor-0.1.0-py3-none-any.whl |
Total release size: 459.3 kB
Release files / ats_resume_tailor-0.1.0.tar.gz
| Download URL | ats_resume_tailor-0.1.0.tar.gz |
|---|---|
| Size | 427.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
afb38e92d4e7b3c4694c77dd13bc8c25cc13faa665339e7ee34207de001b3118
|
|
BLAKE2b-256 checksum How to use checksums |
9cc0afe10dc0a61f6cfa0e6339c63095f84b06ca5bdb68766234f10db8656a9c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 20, 2026.
Transparency logRelease files / ats_resume_tailor-0.1.0-py3-none-any.whl
| Download URL | ats_resume_tailor-0.1.0-py3-none-any.whl |
|---|---|
| Size | 32.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
7cb5968c3b8a91d7dbc0d5a110f584a8a781c8e7cce605a159fcd98bac9f468f
|
|
BLAKE2b-256 checksum How to use checksums |
1db245262c52fd13809eb7824595da6b3149751dde89e5c18614dd03e71533ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.16
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 20, 2026.
Transparency logSecurity for ats-resume-tailor 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for ats_resume_tailor-0.1.0.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Nov 20, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.