Draft Skill
I help with tidying up messy notes whenever it seems useful.
Fm04 No Trigger
Helps with testing skill descriptions.
St02 Broken Link
Use when testing broken sibling links.
Ph01 One Token
Use when testing placeholder detection.
Ct03 Trigger List Only
Use when testing trigger-list exclusion.
Using Shakespii
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.
No Evals
Use when exercising the missing-evals error path of shakespii test.
Ai Cortex
Structural code intelligence and persistent memory for AI coding agents, served over MCP (Claude Code, Codex).
[unclosed
A Claude skill from ai-creed/ai-shakespii.
Two Cases
Use when exercising the thin-eval warning path of shakespii test.
St02 Malformed Percent
Use when testing malformed percent links.
Fm04 First Person
Use when I need to test first-person detection.
Fm01 No Frontmatter
A Claude skill from ai-creed/ai-shakespii.
St02 Ok
Use when testing valid sibling links.
Ct03 Alias Heading
Use when testing alias heading matching.
Fm04 Trigger Not First
A helper that is nice to use when testing.
St02 Parent Escape
Use when testing parent-directory escapes.
Fm01 Unknown Field
Use when testing unknown-field warnings.
Bad Evals
Use when exercising co-existing evals.json defects in shakespii test.
Authoring Skills
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.
Bad Name
Use when testing the kebab-case name rule.
Ct03 No Examples
Use when testing missing Examples detection.
Other Name
Use when testing the name-equals-directory rule.