skills/agents-md-manager/SKILL.md
Audit, generate, update, and lint AGENTS.md files across all projects. Use when asked to check project context files, scaffold AGENTS.md for new projects, update stale ones, or run a cross-project audit.
npx skillsauth add espennilsen/pi agents-md-managerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Maintain AGENTS.md project context files across all ~/Dev projects.
Scan all projects and report AGENTS.md / .pi/ / td status:
# Use the project_init tool in batch mode
Use project_init with action: "batch" to get a full overview. Then provide a table:
| Project | Stack | AGENTS.md | .pi/ | td | Status | |---------|-------|-----------|------|-----|--------|
Flag projects that:
Use project_init with action: "detect" first to preview, then action: "init" to create.
After auto-generation, review and enhance the output by:
When a project has changed significantly:
project_init with action: "detect" to get fresh stack profileKey sections to check:
Use the edit tool for surgical updates — don't rewrite the entire file.
Compare AGENTS.md claims against reality:
# Check if referenced directories exist
# Verify scripts in package.json match what's documented
# Confirm referenced config files exist
# Check if new top-level dirs aren't documented
For each project with AGENTS.md:
project_init detect to get current profileCheck AGENTS.md files for common issues:
Report with severity:
When operating on multiple projects:
project_init for stack detection and initial generationworkon to switch context when doing deep updatestd to track large-scale AGENTS.md update campaignsread and edit for surgical file modificationstools
# pi-a2a Long-Running Tasks Skill ## Overview The pi-a2a extension supports **long-running tasks** that can execute for hours or days without timeouts. This is essential for: - Data processing pipelines - Batch operations - Research and aggregation tasks - External API jobs with unpredictable duration - Any A2A task that exceeds the standard timeout ## When to Use **Use long-running tasks when:** - Task execution time is unpredictable or known to exceed 10 minutes - The remote agent is proc
development
Orchestrate cmux terminal panes — split terminals, run parallel processes, read output from other panes, and use the built-in browser. Use when working inside cmux and you need to run a dev server, watch tests, spawn sub-agents, or preview web pages.
testing
Review UI designs and implementations for accessibility, consistency, usability, and visual quality. Use when asked to review a design, audit accessibility, check UI consistency, compare implementation against mockups, or evaluate a user interface.
tools
Create, review, and improve skills for Pi agents. A skill is a folder with a SKILL.md that teaches an agent specialized workflows, domain knowledge, or tool integrations. Use when asked to create a new skill, improve an existing skill, review a skill for quality, scaffold a skill from a workflow, or convert documentation into a skill. Also triggers on "make a skill for", "build a skill", "skill for [topic]", "teach the agent to", or "package this workflow as a skill".