Conciseness

The body is lean and every line carries instruction — "Do the first unit by hand to learn the recipe, then build the tool. Prove it by rerunning it on that unit and diffing against your hand-done version" — with no padding and no explanation of concepts Claude already knows. It matches anchor 5: every token earns its place.

Actionability

Concrete, executable guidance throughout: a prove-it loop (rerun and diff against the hand-done unit), a task-to-tool mapping ("Codemod or script for edits, generator for repetitive files, a dump-to-sqlite query for analysis, a rerunnable check for verification"), and a triviality escape hatch. It is below anchor 5 only because some guidance stays at the heuristic level (e.g., the delegate skill's 'verification contract' and 'do-not-touch fences' are named but not shown).

Workflow Clarity

A clear sequence is present — do the first unit by hand, build the lever, prove it by rerunning and diffing, apply, commit when the work outlives the session — and it includes an explicit validation checkpoint ("Prove it by rerunning it on that unit and diffing against your hand-done version"). It sits at 4 rather than 5 because the sequence is spread across bullets rather than laid out as an ordered workflow, making the step order implicit.

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into clearly labeled sections (Why, Pattern, Balance), which per the short-skill exception qualifies for 5. Cross-links to sibling principles ([Laziness Protocol], [Encode Lessons in Structure], [Prove It Works]) are clearly signaled and one level deep.

Specificity

The description lists several concrete artifacts and actions — "Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow)" — and names target domains ("edits, migrations, analyses, checks"). It falls short of anchor 5 because coverage has gaps (e.g., no mention of refactors, bulk renames, or scaffolding), but exceeds anchor 3's '1-2 concrete actions'.

Completeness

Both parts are present: 'what' is explicit ("Build the tool that does it or proves it... instead of working by hand") and 'when' is given as equivalent trigger guidance ("Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks"), so the 3-cap for missing trigger guidance does not apply. It stays at 4 rather than 5 because 'when' rests on the judgment-dependent phrase "non-trivial work" rather than fully concrete trigger phrases.

Trigger Term Quality

It includes natural terms users would plausibly say — "edits", "migrations", "analyses", "checks", "codemod", "script", "generator" — giving good keyword coverage. A few natural variations are missing ("refactor", "automate", "bulk rename"), keeping it below anchor 5.

Distinctiveness Conflict Risk

The build-a-lever action itself is a clear niche ("Build the tool that does it or proves it"), but the trigger scope "any non-trivial work, not just bulk work" is broad enough to overlap many work-oriented skills. It is more specific than anchor 2's generic breadth but does not reach anchor 4's 'mostly distinct'.