Markitdown
ImCa0/just-laws
Convert files and office documents to Markdown. An agent skill from ImCa0/just-laws.
A skill your agent uses when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
Install Resume Intake And Extraction
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extraction --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/resume-intake-and-extraction .claude/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .claude/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extractionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extraction --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/resume-intake-and-extraction .agents/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .agents/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extraction --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/resume-intake-and-extraction .cursor/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .cursor/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Li-Baichuan-James/cv-skill.git --path skills/resume-intake-and-extraction--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extraction --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/resume-intake-and-extraction .gemini/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .gemini/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extractionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/resume-intake-and-extraction .github/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .github/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Li-Baichuan-James/cv-skill resume-intake-and-extraction --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Li-Baichuan-James/cv-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/resume-intake-and-extraction .opencode/skills/resume-intake-and-extraction && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "resume-intake-and-extraction" agent skill from https://github.com/Li-Baichuan-James/cv-skill/tree/main/skills/resume-intake-and-extraction into .opencode/skills/resume-intake-and-extraction/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "resume-intake-and-extraction", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
resume-intake-and-extraction- GitHub stars
- 153
- Token cost
- ~1.6k tokens
- SKILL.md length
- 816 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
- Resume source material arrives as chat requirements
- SKILL.md covers Overview, Inputs, Preconditions and Required Behavior, plus 9 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Mixed artifacts and must be normalized before any 1-2 page resume drafting begins
What it does
Resume Intake And Extraction is an agent skill from Li-Baichuan-James/cv-skill. Use when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Documents & Office, covering PDF. It works with Microsoft Word. The licence is MIT.
When your agent uses it
- Resume source material arrives as chat requirements
- Mixed artifacts and must be normalized before any 1-2 page resume drafting begins
Example prompts
- “/resume-intake-and-extraction”
What it can do on your machine
Read from SKILL.md and the folder at commit eb92381. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Resume Intake And Extraction loads about 1.6k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 816 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Li-Baichuan-James/cv-skill at commit eb92381, republished under its MIT licence (© Li-Baichuan-James). 816 words, ~1,647 tokens.
Download SKILL.mdSave it as
.claude/skills/resume-intake-and-extraction/SKILL.md (or your agent's skills folder).- name
- resume-intake-and-extraction
- description
- Use when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
Resume Intake And Extraction
Overview
Normalize messy resume input into traceable working material. Extract first, map claims second, and stop before drafting when the source cannot safely support a concise 1-2 page resume.
Inputs
- Chat requirements
.docx.pdf- Images or screenshots
- Mixed bundles
Preconditions
- Use within a
resume-crafterworkspace that already hasinput/andwork/directories. - If no current workspace with
input/andwork/exists, invoke or resumeresume-crafter, or return a blocker asking for a workspace before writing files.
Required Behavior
- Use upstream
docxfor.docxinputs. - Use upstream
pdffor.pdfinputs. - Prefer platform-native image reading or OCR for image inputs.
- Save extracted content to
work/extracted.md. - Save gaps, conflicts, omissions, and user confirmations to
work/requirements-summary.md. - Save initial claim traceability to
work/claim-source-map.md; authoring must later update this map to cover the final rendered resume claims. - For every uncertain field, keep the raw source wording when available instead of normalizing it into a cleaner fact.
Confidence States
Mark each usable or requested fact as:
resolvedneeds-confirmationomitted-unresolvedmissing-blocking
Legacy confidence labels may appear inside notes, but the state above controls whether drafting can proceed.
Use [confirm] only for needs-confirmation items in working notes. Do not use [confirm] to bypass missing-blocking, and do not allow [confirm] or needs-confirmation claims in final resume prose.
Final output eligibility:
resolved: may appear in final resume prose.needs-confirmation: may appear only in working notes, never in final prose.omitted-unresolved: records an intentional omission and must not appear in final prose.missing-blocking: blocks authoring and finalization until resolved or audited as omitted with explicit user approval.
Quality-Critical Unknowns
Treat an uncertain fact as quality-critical when it affects identity/display name, localized name, target role/headline, required or user-visible contact-block choices, required photos, required language/style, user-explicit deliverable requirements, or any content whose omission would make the resume visibly worse or mismatched.
Quality-critical unknowns must be marked missing-blocking, not needs-confirmation, until the user confirms them or explicitly approves omission. Do not downgrade them merely to keep drafting moving.
Record the exact targeted question that should be asked in work/requirements-summary.md. Use a brainstorming-style question: clarify the purpose or constraint, ask one question at a time when it affects the next decision, and offer concise options when helpful.
Claim Map Format
Use this six-column table in work/claim-source-map.md:
| Claim | Source artifact | Source locator | Raw wording or user confirmation | State | Final handling |
|---|---|---|---|---|---|
| Candidate held role X at Y | input/source.pdf | p.1, experience section | "Role X, Y" | resolved | use |
| Led deployment for Z users | input/screenshot-01.png | visible project card, metric partly cropped | visible wording unclear; ask user to confirm Z | needs-confirmation | ask or keep out of final prose with working-note trace |
| Chinese display name for a Chinese resume is unknown | input/source.tex | header/name line | source only says LI Baichuan; ask user how to display name in Chinese resume | missing-blocking | ask before drafting |
This intake map covers source facts and uncertainties. After the final resume prose is drafted, resume-authoring-and-assembly must update the table so every final factual claim has a resolved row.
Show full SKILL.md (323 more words)Show less
Evidence Requirements
- PDFs: include page numbers.
- Images and screenshots: include filenames and visible regions.
- Chat: quote the user's wording or cite the user confirmation.
- Follow-up answers: record as user confirmation.
Omission Audit
For every intentionally omitted blocking item, record in work/requirements-summary.md:
- omitted field or claim
- reason for omission
- explicit user approval
- impact on final wording
Follow-Up Confirmation Update Mode
When the user answers clarification questions after intake:
- update
work/extracted.mdwith the confirmation wording and date/context of the answer - cite the answer as
user confirmationinwork/claim-source-map.md - change confirmed rows from
missing-blockingorneeds-confirmationtoresolvedonly when the answer directly supports the final claim - keep unresolved non-blocking uncertainty as
needs-confirmation; keep unresolved quality-critical or blocking uncertainty asmissing-blockingunless the user explicitly approves omission; do not silently delete unresolved rows - update
work/requirements-summary.mdso resolved blockers, remaining blockers, and omission audits stay current
Legacy Confidence Labels
If helpful, also label extraction snippets as commentary only:
high-confidencelow-confidencemissing-blocking
Legacy high-confidence and low-confidence commentary never controls final output eligibility. The Confidence States above are authoritative.
Stop Conditions
- If key chronology, identity, publication, title, or impact facts are missing, stop and ask targeted questions before drafting.
- If a quality-critical unknown exists, stop and ask a targeted question before drafting.
- Do not resolve quality-critical uncertainty by guessing, silently deleting the field, or converting it to a non-blocking note.
- If OCR or extraction damage makes facts unreliable, stop and report which fields are unsafe.
- If source artifacts conflict materially, ask for clarification before writing.
- Do not synthesize missing dates, names, venues, role scopes, or metrics from context.
- If the user requests a long academic CV, stop and ask whether to create a concise 1-2 page research resume.
Workspace And Runtime Rules
- Write normalized materials only inside the current workspace, typically under
work/. - Do not write guessed or low-confidence resume content into
skills/,templates/, or other repository paths. - Do not activate unrelated runtime skills to resolve core resume facts.
© Li-Baichuan-James, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/resume-intake-and-extraction of Li-Baichuan-James/cv-skill.
Open the folder on GitHubat commit eb92381
Compare with similar skills
Resume Intake And Extraction next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Resume Intake And Extraction this skillLi-Baichuan-James/cv-skill | 153 | — | ~1.6k | Automated safety check: Pass | MIT | |
| MarkitdownImCa0/just-laws | 781 | 14 repos | ~3.2k | Automated safety check: Notes | MIT | |
| Gzh Designisjiamu/gzh-design-skill | 4k | — | ~2.2k | Automated safety check: Pass | AGPL-3.0 | |
| GenOffice Document CLIgenspark-ai/genoffice | 9.2k | — | ~19k | Automated safety check: Pass | Apache-2.0 | |
| Translate Bookdeusyu/translate-book | 2.1k | — | ~5.5k | Automated safety check: Notes | MIT | |
| Docsagentdocsagent/docsagent | 625 | — | ~834 | Automated safety check: Pass | None |
Similar skills
Gzh Design
isjiamu/gzh-design-skill
微信公众号文章排版引擎，将 Markdown 转换为可直接粘贴到公众号编辑器的 HTML。主题风格从 references/theme-index.md 注册的自定义主题库中选取，自动章节编号、关键词下划线标记、引言卡片、目录导航、代码块、图片/GIF、作者签名。支持 Markdown / Word(.docx) / PDF / 纯文本输入（非 Markdown…
GenOffice Document CLI
genspark-ai/genoffice
Creates, converts, reads and edits real pptx, xlsx, docx and PDF files locally through the genoffice command line.
Translate Book
deusyu/translate-book
Translate books (PDF/DOCX/EPUB) into any language using parallel sub-agents.
Docsagent
docsagent/docsagent
Search and manage private, local document collections (PDF, PPTX, DOCX) offline.
PDF
zai-org/ZCode
Professional PDF toolkit covering four production workflows: reports, creative visuals, academic LaTeX, and existing PDF processing.
More from Li-Baichuan-James/cv-skill
Resume Authoring And Assembly
Li-Baichuan-James/cv-skill
A skill your agent uses when normalized resume material is ready and must be rewritten, organized, and assembled into a 1-2 page LaTeX resume without inventing facts.
Resume Review And Delivery
Li-Baichuan-James/cv-skill
A skill your agent uses when a LaTeX resume draft exists and needs factual review, ATS or research-resume risk checks, build validation, packaging, and final delivery.
Resume Crafter
Li-Baichuan-James/cv-skill
A skill your agent uses when creating, rewriting, or converting a source-backed 1-2 page resume from chat, documents, PDFs, images, or mixed artifacts.
Related
Works with
Categories
Questions about Resume Intake And Extraction
What does Resume Intake And Extraction do?
A skill your agent uses when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins. Resume Intake And Extraction is an agent skill from Li-Baichuan-James/cv-skill. Use when resume source material arrives as chat requirements, a Word file, a PDF, screenshots, or mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
When should I use Resume Intake And Extraction?
Resume Intake And Extraction fits situations like: resume source material arrives as chat requirements; mixed artifacts and must be normalized before any 1-2 page resume drafting begins.
How do I install Resume Intake And Extraction in Claude Code?
Run `npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a claude-code`. Or copy the skill folder (skills/resume-intake-and-extraction in Li-Baichuan-James/cv-skill) into .claude/skills/resume-intake-and-extraction in your project. Claude Code loads it when a task matches its description.
How do I install Resume Intake And Extraction in Codex?
Run `npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a codex`. Or copy the skill folder (skills/resume-intake-and-extraction in Li-Baichuan-James/cv-skill) into .agents/skills/resume-intake-and-extraction in your project. Codex loads it when a task matches its description.
Can I use Resume Intake And Extraction in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Li-Baichuan-James/cv-skill --skill resume-intake-and-extraction -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/resume-intake-and-extraction, .gemini/skills/resume-intake-and-extraction, .github/skills/resume-intake-and-extraction and .opencode/skills/resume-intake-and-extraction in your project.
What does Resume Intake And Extraction need to run?
SKILL.md names no scripts, command-line tools or credentials: Resume Intake And Extraction is instructions for the agent only.
Does Resume Intake And Extraction access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Resume Intake And Extraction safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Resume Intake And Extraction use?
Resume Intake And Extraction is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Resume Intake And Extraction use?
About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Resume Intake And Extraction?
Skills that share tags, products or a category with Resume Intake And Extraction: Markitdown (ImCa0/just-laws, 781 stars), Gzh Design (isjiamu/gzh-design-skill, 4k stars), GenOffice Document CLI (genspark-ai/genoffice, 9.2k stars) and Translate Book (deusyu/translate-book, 2.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Resume Intake And Extraction?
Li-Baichuan-James (a GitHub user) maintains it in Li-Baichuan-James/cv-skill, which has 153 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 5, 2026.
Source: Li-Baichuan-James/cv-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.