How do I install the Ingest Resume History skill?

Run npx skillmds@latest add clickblipclick/ingest-resume-history in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Ingest Resume History safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Ingest Resume History?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Ingest Resume History free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Ingest Resume History?

clickblipclick (@clickblipclick) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Ingest Resume History by clickblipclick

Name: Ingest Resume History
Author: clickblipclick

Ingest Resume History

Use when the user has dropped existing resume PDFs, markdown notes, or text files into inbox/ and wants to bootstrap or update content/master.yaml. Extracts text via bun run ingest, then reconciles into master.yaml with per-change reasoning and explicit approval.

File contents

Ingest Resume History Skill

When to use

First-time setup, or whenever the user adds new source material (old resumes, work-history notes) to inbox/ and wants it merged into content/master.yaml.

Hard rules

Never overwrite master.yaml without showing diffs and getting explicit approval.
Always run bun run ingest first to produce the extracted text. Do not try to read PDFs directly.
Dedupe conservatively. Prefer flagging possible duplicates to the user over silently merging them.

Workflow

1. Extract

Run:

bun run ingest

This reads everything in inbox/ and writes plain-text versions to inbox/.extracted/.

2. Read everything

All files in inbox/.extracted/
Current content/master.yaml (if it exists; may be the example)

3. Propose a reconciled master

Build a proposed master.yaml that:

Collects roles across all sources, keyed by (company, title, start) for dedupe.
Merges bullet variants for the same role: prefer longer/more specific wording; flag conflicts to the user.
Assigns stable IDs. ID scheme: <company-slug>-<startYear> for roles; <role-id>-<keyword> for bullets.
Preserves any existing IDs in the current master.yaml exactly — do not renumber.

Present the proposal as:

A list of new roles being added (with reasoning: "from Acme-2023.pdf").
A list of new bullets per existing role.
A list of possible duplicates you'd like confirmation on.

4. Apply on approval

On explicit user approval, write the full proposed master.yaml. Commit:

git add content/master.yaml
git commit -m "Ingest history from inbox"

5. Archive originals

Move processed PDFs from inbox/ to jobs/archive/<inferred-company>/ (create folder if needed). For each moved PDF, create a stub job.md next to it with whatever context you can infer from filename or content. If inference is weak, write "inferred context TBD" and flag to the user.

Editing discipline

When re-running ingest on new files, update master incrementally — do not regenerate from scratch.
If a source file contradicts existing master content (e.g., different dates for the same role), raise the conflict to the user rather than picking a winner.

---name: ingest-resume-historydescription: Use when the user has dropped existing resume PDFs, markdown notes, or text files into inbox/ and wants to bootstrap or update content/master.yaml. Extracts text via bun run ingest, then reconciles into master.yaml with per-change reasoning and explicit approval.---# Ingest Resume History Skill## When to useFirst-time setup, or whenever the user adds new source material (old resumes, work-history notes) to `inbox/` and wants it merged into `content/master.yaml`.## Hard rules1. **Never overwrite `master.yaml` without showing diffs and getting explicit approval.**2. **Always run `bun run ingest` first** to produce the extracted text. Do not try to read PDFs directly.3. **Dedupe conservatively.** Prefer flagging possible duplicates to the user over silently merging them.## Workflow### 1. ExtractRun:```bun run ingest```This reads everything in `inbox/` and writes plain-text versions to `inbox/.extracted/`.### 2. Read everything- All files in `inbox/.extracted/`- Current `content/master.yaml` (if it exists; may be the example)### 3. Propose a reconciled masterBuild a proposed `master.yaml` that:- Collects roles across all sources, keyed by `(company, title, start)` for dedupe.- Merges bullet variants for the same role: prefer longer/more specific wording; flag conflicts to the user.- Assigns stable IDs. ID scheme: `<company-slug>-<startYear>` for roles; `<role-id>-<keyword>` for bullets.- Preserves any existing IDs in the current `master.yaml` exactly — do not renumber.Present the proposal as:- A list of new roles being added (with reasoning: "from Acme-2023.pdf").- A list of new bullets per existing role.- A list of _possible_ duplicates you'd like confirmation on.### 4. Apply on approvalOn explicit user approval, write the full proposed `master.yaml`. Commit:```git add content/master.yamlgit commit -m "Ingest history from inbox"```### 5. Archive originalsMove processed PDFs from `inbox/` to `jobs/archive/<inferred-company>/` (create folder if needed). For each moved PDF, create a stub `job.md` next to it with whatever context you can infer from filename or content. If inference is weak, write "inferred context TBD" and flag to the user.## Editing discipline- When re-running ingest on new files, update master incrementally — do not regenerate from scratch.- If a source file contradicts existing master content (e.g., different dates for the same role), raise the conflict to the user rather than picking a winner.

Frequently asked questions