he-skill-repo/he-maintainer/SKILL.md

name, description

name	description
he-maintainer	Create, audit, update, and maintain project-specific AI harness files for software repositories. Use when the user wants to bootstrap or evolve AGENTS.md, AI working guides, task templates, validation commands, project maps, guardrails, or harness health checks for a codebase.

HE Maintainer

Use this skill when the task is to build or maintain a repository's harness engineering setup.

What this skill owns

This skill helps with:

• creating or updating project AI guide files such as AGENTS.md, CLAUDE.md, or AI_GUIDE.md
• maintaining project maps, task templates, validation commands, and guardrails
• auditing harness quality and identifying missing feedback loops
• keeping harness files aligned with the real repository state

Core idea

Harness engineering is not mainly about clever prompting. It is about giving the coding agent a stable work surface:

• a clear repo map
• reliable commands
• explicit constraints
• short feedback loops
• repeatable task formats

This skill should prefer improving those assets over writing abstract advice.

Workflow

Follow this sequence unless the user asks otherwise.

1. Inspect the repository
2. Identify the stack and tooling
3. Find existing harness files and conventions
4. Check whether commands are real and runnable
5. Update or create harness artifacts with minimal disruption
6. Report harness health, gaps, and next actions

Inspect the repository

Look for:

• README.md
• package.json, pnpm-workspace.yaml, turbo.json
• Cargo.toml
• go.mod
• pyproject.toml, requirements.txt
• CI files under .github/, .gitlab/, or similar
• test directories and test config
• existing AI-facing files such as AGENTS.md, CLAUDE.md, AI_GUIDE.md

Do not invent commands or architecture details. Ground all harness content in the real repo.

Preferred outputs

Depending on the request, create or update one or more of:

• AGENTS.md
• ai/project-map.md
• ai/task-templates.md
• ai/risk-guardrails.md
• ai/harness-health.md

Prefer short, maintainable files over one giant document.

Update policy

Prefer targeted edits over full rewrites.

• preserve useful human-written guidance
• remove clearly stale commands and paths
• add missing constraints and validation steps
• mark uncertain items as needing confirmation

If a file is mostly wrong or empty, a rewrite is acceptable.

Guardrail policy

When defining harness rules, strongly prefer:

• minimal diffs
• no dependency upgrades unless requested
• no schema or migration changes unless requested
• no disabling tests just to get green
• targeted validation before full validation when possible

Project-specific exceptions are fine if the repo clearly requires them.

Harness health rubric

Assess these areas briefly:

• project map clarity
• runnable validation commands
• fast feedback availability
• task template quality
• guardrail clarity
• alignment between docs and codebase

Use simple ratings like strong, partial, or weak.

References

Read only the most relevant reference file for the current stack:

• references/node-typescript.md
• references/go.md
• references/rust.md
• references/python.md
• references/monorepo.md
• references/scoring-rubric.md

Do not read all references by default.

Deliverable style

Keep deliverables practical. Good outputs include:

• an updated AGENTS.md
• concise task templates
• a harness gap report with top priorities
• a small list of suggested next improvements

Avoid long theory dumps unless the user explicitly asks for theory.