hyuga611
UserOne command for agent config: reflint + skills-lint + carrylint over one tree, one report, one exit code, one GitHub Action.
Categories
Indexed Skills (6)
agent-config-lint
Check agent config for things that break silently on someone else's machine. Use before publishing or committing a SKILL.md, AGENTS.md, CLAUDE.md or llms.txt, before publishing a skill to ClawHub, when a skill "works on my machine" but not for a teammate, when a skill fails to trigger, or when asked to review agent config. Catches references to files that do not exist, absolute paths under the author's home directory, undeclared CLI dependencies, a frontmatter name that does not match the skill's directory, and two skills whose descriptions are so similar the agent fires the wrong one.
narai-learn
Turn the corrections narai has recorded into rules for AGENTS.md / CLAUDE.md. Use when the user asks what narai has learned, wants rules distilled from their edits, asks "what are my habits", or says narai learn. Reads ~/.claude/narai/corrections and writes a validated rules file. Not for setting narai up, and not for reading a single diff — that is what `narai log` is for.
leaky-image-gen
Generate an image. Use when the user asks to create or generate an image.
portable-image-gen
Generate an image from a Japanese prompt via an external image CLI. Use when the user asks to create or generate an image.
portable-thing
A minimal portable example skill, used to prove that tenken stays quiet on a clean tree. Reads one reference file and writes its output to a relative path.
leaky_skill
Read the template at `references/missing-template.md` first.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.