Skills9History

agentpack-cli

Use the agentpack CLI correctly when treating knowledge as a package. Apply the authored skill lifecycle, compiler/materialization workflow, source-backed validation, install flow, and runtime state model without mixing those stages together.

173 lines

authoring-skillgraphs-from-knowledgecore

Use when authoring packaged skills from source knowledge with valid SKILL.md structure, package.json release fields, provenance source bindings, and skill imports in agentpack.

158 lines

compiler-mode-authoringcore

Use when writing agentpack declaration blocks, source bindings, skill imports, and contextual body references in SKILL.md files for compiler-mode skill authoring.

422 lines

developing-and-testing-skillscore

Use when iterating locally on a packaged skill with agentpack author dev, the localhost workbench, repo-local materialization, and runtime testing feedback loops.

124 lines

getting-started-skillgraphslifecycle

Use when starting from an empty repo or empty skillgraph and needing the first correct authoring loop, lifecycle framing, repo-root routing, and inspect/validate/dev command flow in agentpack.

117 lines

identifying-skill-opportunitiescore

Use when deciding what raw knowledge should become a packaged skill, a reusable capability boundary, or an import edge in an agentpack skillgraph.

118 lines

maintaining-skillgraph-freshnesslifecycle

Use when validating authored skills, checking stale state, and keeping compiled metadata aligned with changing knowledge in an agentpack skillgraph.

111 lines

multi-skill-packagescore

Use when deciding how to structure multi-skill packages, configure agentpack.root for named export discovery, and manage dependency edges between exported skills in agentpack.

399 lines

publishing-skill-packageslifecycle

Use when preparing and publishing agentpack skill packages to npm or GitHub Packages, including package.json configuration, registry setup, and release validation.

358 lines