Harness docs init
File-native project continuity and engineering standards for coding agents.
npx -y skills add cekrauseee/harness --skill harness-docs-initAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Create or repair the concise, English, versioned developer documentation baseline for a repository. Use when a project needs a README, documentation index, project overview, architecture guide, development guide, module documentation structure, or artifact index without overwriting existing content.
SKILL.md
2.3 KB, 422 tokens by cl100k_base, as published. Nobody here has run it
Harness Docs Init
Create the smallest useful canonical documentation surface. Keep agent memory, handoffs, drafts, and provisional findings outside the repository documentation.
Procedure
- Inspect the repository, existing documentation, configuration, and relevant source files.
- Run
scripts/init_docs.py <project-root>to create only missing baseline files and directories. - Replace generic content with facts verified from source, configuration, tests, or explicit user decisions.
- Preserve existing user content. Resolve conflicts deliberately instead of overwriting files.
- Link focused documents from
docs/index.mdwith a clear reason to read each one. - Run the checker bundled with
harness-docs-auditwhen that skill is available.
Canonical Layout
README.md
docs/
index.md
project.md
architecture.md
development.md
modules/
artifacts/
index.md
File Roles
README.md: short project entry point, basic development path, and link todocs/index.md.docs/index.md: routing map for the rest of the documentation.docs/project.md: purpose, scope, concepts, and stable product boundaries.docs/architecture.md: system components, boundaries, data flow, and invariants.docs/development.md: prerequisites, setup, commands, testing, and contribution rules.docs/modules/*.md: one bounded subsystem or capability per file.docs/artifacts/index.md: catalog of final, user-facing HTML visualizations.
Writing Rules
- Write all repository documentation in English.
- Use simple, objective, coherent, and concise language.
- Prefer active voice, short paragraphs, descriptive headings, and exact commands.
- Keep one canonical explanation and link to it elsewhere.
- State unknowns plainly. Never invent behavior, commands, or architecture.
- Use Mermaid only when relationships or sequences are materially clearer than prose.
- Keep draft HTML and intermediate work in the Harness workspace. Route final HTML visualizations through
harness-artifact.
What ships with it: 2 files
3.1 KB alongside SKILL.md, 1 of them executable
agents/
- openai.yaml281 B
scripts/
- init_docs.pyruns2.8 KB