ai-shakespii

I help with tidying up messy notes whenever it seems useful.

Use when the user asks to create, write, compose, or design a new agent skill — turning an idea, notes, requirement, or repeated workflow into a SKILL.md with eval cases and a trigger set through an interview → draft → critique → refine loop.

Use when the user asks to lint, audit, test, benchmark, validate, or fix an agent skill — from a single SKILL.md frontmatter check to trigger-accuracy measurement or a corpus-wide audit of installed skills for duplication — driving the shakespii CLI (init, lint --json, test --run, bench) to resolve findings until clean.

A tiny practice skill that summarizes shell command output into one line.

Use when the user asks for a one-word acknowledgement drill — replies with exactly the word the drill names.

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

Use when exercising co-existing evals.json defects in shakespii test.

Use when exercising the missing-evals error path of shakespii test.

Use when exercising the thin-eval warning path of shakespii test.

"TODO(shakespii): Use when <trigger>… — third person, concrete searchable keywords; do not summarize the workflow."

Use when verifying anatomy alias overrides against a fixture skill.

Use when verifying config overrides against a version-less fixture skill.

Use when verifying corpus discovery against a clean fixture pair.

Use when verifying corpus discovery against a clean fixture pair.

Use when verifying near-clone detection against a fixture pair.

Use when verifying near-clone detection against a fixture pair.

Use when verifying duplicate-block detection across a fixture trio.

Use when verifying duplicate-block detection across a fixture trio.

Use when verifying duplicate-block detection across a fixture trio.

Use when verifying that one broken skill does not abort the corpus run.

Use when verifying that corpus discovery reports skipped directories.

Use when verifying the shakespii seed rules against a known-clean fixture skill.

Use when testing warning-only exit code behavior.

Use when testing malformed percent links.

Use when testing placeholder detection.

Use when testing broken sibling links.

Use when testing valid sibling links.

Use when testing parent-directory escapes.

Use when testing alias heading matching.

Use when testing generic-prose rejection.

Use when testing missing Examples detection.

Use when testing placeholder Examples detection.

Use when testing trigger-list exclusion.

Use when I need to test first-person detection.

Helps with testing skill descriptions.

A helper that is nice to use when testing.

Use when testing the kebab-case name rule.

Use when testing the name-equals-directory rule.

Use when testing unknown-field warnings.