Skip to content
View jacob-balslev's full-sized avatar

Block or report jacob-balslev

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
.github/profile/README.md

Jacob Balslev

Building agent-skills infrastructure: protocols, audit loops, and the tooling that keeps a skill library honest as it grows.

I work on the machinery between an LLM and a useful coding agent. The thread across the projects below is typed metadata + deterministic gates + a Karpathy-style keep-or-revert loop applied to skills, audits, and routing decisions.

Public projects

skill-graph — Skill Metadata Protocol + audit-loop toolchain

The authoring + audit-time contract for SKILL.md files. Typed frontmatter, a JSON Schema (schema_version: 6), a lint + manifest + router + drift sentinel, and a doctor subcommand that runs every deterministic gate in one pass. Ships as @skill-graph/cli on npm.

The differentiator: a Karpathy-style keep-or-revert audit loop applied to skill libraries instead of training scripts. Each edit ships as one field per commit with a hard pass/fail gate; if the gate fails, git revert HEAD. The loop is what keeps a library trustworthy as it crosses 100+ skills.

Install: npm install -g @skill-graph/cliQuickstart: author your first skill in 30 minutesPrimer: the mental model

skills — published Agent Skills

The public skill library that the marketplace at skills.sh/jacob-balslev/skills indexes. Plain Agent-Skills-format SKILL.md files exported from skill-graph's authoring repo. Install:

npx skills add jacob-balslev/skills

Historical canonical docs for the protocol and audit loop. Both repos were consolidated into skill-graph on 2026-05-18 (ADR 0009). They remain readable so existing inbound links stay valid; new development lives in skill-graph.

What I read into the work

  • Karpathy on autoresearch — one experiment, one editable field, one scalar metric, keep-or-revert. The whole audit loop is structured around this discipline.
  • Diátaxis — explanation, tutorial, reference, how-to. Every doc surface in skill-graph is tagged with its Diátaxis genre.
  • OntoClean — what makes a category rigid, what makes it anti-rigid. The four skill archetypes (capability / workflow / router / overlay) come from this analysis.
  • Anthropic Skills + the Agent Skills spec — the base format Skill Metadata Protocol extends.

Contact

  • GitHub Issues on any of the repos above
  • npm: @skill-graph/cli

Popular repositories Loading

  1. jb-next-24 jb-next-24 Public

    SCSS

  2. jb-html-24 jb-html-24 Public

    HTML

  3. jacob-balslev-portfolio-april-2024 jacob-balslev-portfolio-april-2024 Public

    HTML

  4. skill-graph skill-graph Public

    Skills that know your codebase. Repo-grounded, contract-validated, agent-routable.

    JavaScript

  5. skills skills Public

    Public Agent Skills library exported from skill-graph. Install: npx skills add jacob-balslev/skills

  6. skill-metadata-protocol skill-metadata-protocol Public archive

    DEPRECATED docs-only mirror. The protocol now lives in jacob-balslev/skill-graph (see ADR 0009, 2026-05-18).