Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Development

vitaecontext-build

Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before editing platform-specific assets.

vitaecontext · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add vitaecontext/vitaecontext --skill vitaecontext-build

About this skill


name: vitaecontext-build description: Build, normalize, and maintain the user's Career Context file so downstream platform outputs stay factual and consistent. Use when the user wants an agent to consolidate CV data, LinkedIn exports, GitHub history, project summaries, bio facts, achievements, or positioning into one professional source of truth before editing platform-specific assets. license: MIT metadata: homepage: https://vitaecontext.github.io/ repository: https://github.com/vitaecontext/vitaecontext

VitaeContext Agent Context Optimization

Overview

Work through the lens of a meticulous biographer, fact-checker, and positioning partner assembling the user's professional source of truth. The user supplies raw career material and decides what matters, where they are going, and which interpretations are unwanted. Build a file that is factually reliable, personally representative, and useful for future decisions rather than merely compliant with a fixed biography template.

Workflow

  • Need to decide whether a Career Context file is needed: references/why-and-when.md
  • Discovering direction, priorities, and claim boundaries: references/personalization-and-interview.md
  • Drafting, validating, or restructuring the file: references/spec-and-structure.md
  • Creating a new file or repairing a weak one: references/drafting-template.md
  • Integrating new material or checking integrity: references/maintenance-and-validation.md
  • Combining the Career Context file with platform skills: references/operating-workflow.md

Normalize the user's facts before writing any LinkedIn, CV, GitHub, web portfolio, or X/Twitter output.

Wiki context

  • Read wiki/index.md when the task asks what a Career Context file is, how it should be structured, how source-of-truth behavior works, how validation and VERIFIED FACTS work, or how to handle context-file failure modes.
  • Read wiki/knowledge.md only after wiki/index.md routes the current task there.
  • If a wiki file is unavailable in an older install, continue with the relevant references/ file and mark wiki-specific guidance as unavailable when it affects confidence.

Token discipline

  • Do not load all references by default.
  • Use the QUICK REFERENCE block first when an existing context file is long.
  • Read detailed entries only for claims used in the current output.
  • Ask for missing inputs instead of reading unrelated platform material.
  • Prefer explicit source files, pasted exports, and named URLs over broad workspace or account scanning.
  • Keep source ledgers compact: list input groups, not every small note unless it affects a conflict.
  • Name next inspection if bounded.

Depth contract

Use the smallest honest context pass:

  • Quick scan: check whether a context file exists, read QUICK REFERENCE, and identify obvious structural gaps.
  • Default pass: quick scan plus relevant entries for the requested platform, supplied source material, and hard-fact consistency checks.
  • Deep reconciliation: full context file review, all supplied sources, chronology checks, platform conflicts, unsupported claims, and targeted repairs across sections.

Default to Default pass for broad context-file work. Major creation, restructuring, or repositioning work also requires the personalization interview. Offer Deep reconciliation as an optional next step when the current answer would benefit from more evidence. Do not choose Deep reconciliation silently unless the user asks for full normalization, complete validation, or cross-platform reconciliation.

Personalization contract

  • Treat factual completeness, semantic usefulness, and faithful personalization as equal quality requirements.
  • For a new file, major reconciliation, or positioning change, run the discovery workflow in references/personalization-and-interview.md before drafting the full body.
  • Confirm a short positioning synthesis before a large rewrite. Capture long-term direction, current priorities, defining evidence, unwanted identities, acceptable claim strength, and preferred content hierarchy.
  • Let importance control body order and depth. Keep QUICK REFERENCE first and use stable semantic tags, but do not force education, experience, projects, research, or community work into one universal order.
  • Explain the relationship between prior work and future direction. Distinguish an objective from a method, tool, domain, or credential used to reach it.
  • Give defining entries more space and compress peripheral history. Historical completeness does not require equal narrative weight.

Intake workflow

  • If the user supplies an existing context file path, read it first.
  • If no path is supplied, ask where the file should live before writing: in the current workspace, at an explicit user path, or at a portable default such as ~/.vitaecontext/<name-surname>-career-context.md.
  • Do not assume the agent can write outside the current workspace. If writing requires permission, ask before writing.
  • For large context files, prefer writing to a confirmed file path over returning the whole Markdown document in-chat. If writing is unavailable, return a compact outline, identify missing inputs, and ask whether to emit the full draft section by section.
  • When building or repairing a context file, capture the user's direction, not just their history. Ask what future agents must understand, which experiences define the user now, what long-term paths should remain open, which past subjects are supporting capabilities rather than desired identities, and which claims would feel misleading. Also capture practical targeting such as roles, locations, work
Read the complete source ↗