Conciseness

The body is dense and assumes competence — it never explains what an essay, narrative, or profile is, and the genre guidance ('look for tension, conflict, agency, change') is compressed rather than padded. A few discursive sentences could still be trimmed (e.g., 'Do not treat "show, don't tell"... as automatic verdicts' runs long), which matches anchor 4 ('efficient; minor instances of over-explanation that could be trimmed') rather than anchor 5's 'every token earns its place'.

Actionability

For an instruction-only skill the guidance is concrete: a bulleted interrogation list ('What has been shown through scene, action, image, voice, or consequence?'), specific revision moves ('keep the statement, replace it with a scene or detail, move it later, or cut it'), and per-genre directives. This is 'mostly executable guidance... with minor gaps' (anchor 4); it falls short of anchor 5 only because no worked example of the dialectic applied to a passage is provided.

Workflow Clarity

The stages are clearly sequenced — start with the intended discovery, stage the collision, move through the dialectic, judge the language — and include an explicit checkpoint ('Let the writer react before treating a revision as settled'), matching anchor 4 ('clear sequence with most checkpoints present; minor validation gaps'). It lacks the explicit validate-and-recover loop of anchor 5, though the 'Treat first-reader confusion as evidence to investigate' line gestures at one.

Progressive Disclosure

The ~45-line overview is appropriately split: provenance material lives in references/source-map.md (verified to exist and contain the index/draft paths), signaled by a clearly conditional pointer ('Read [references/source-map.md]... when a task calls for the provenance of a principle, comparison with a particular English 120 reading, or locating an original assignment or draft'). This matches anchor 5: a clear overview with a well-signaled, one-level-deep reference.

Specificity

The description names the domain ("essays, narratives, profiles, analytical papers, and humor writing") and essentially one action — "Trigger a dialectic about reader agency" — which matches anchor 3 ('names domain and 1-2 concrete actions, but not comprehensive'). It does not list several concrete actions like extracting, filling, or merging, so it is not a 4, but it is more concrete than a bare domain claim like 'Processes PDF files', so not a 2.

Completeness

It explicitly answers 'what' ("Trigger a dialectic about reader agency in Braden's essays, narratives, profiles, analytical papers, and humor writing") and 'when' with a concrete "Use when applying English 120 ideas such as..." trigger clause, plus negative boundaries ("Do not use for generic proofreading, citation research, or non-writing questions"). This matches anchor 5 ('clearly and explicitly answers both what AND when with concrete trigger phrases') and exceeds anchor 4, whose 'when' is present but less specific.

Trigger Term Quality

It includes natural phrases a user would plausibly say — "show-not-tell", "subtlety", "concrete detail", "tension", "not telling the reader what to think", plus genre names — giving good keyword coverage. It misses a few common variations users might say (e.g., 'revise my essay', 'feedback on my draft'), so it falls just short of anchor 5's comprehensive synonym/extension coverage, and well above anchor 3's 'some relevant keywords, missing common variations'.

Distinctiveness Conflict Risk

It carves a clear niche (English 120 writing critique for Braden's own work) with distinct trigger terms and explicit exclusions ("Do not use for generic proofreading, citation research, or non-writing questions"), matching anchor 5 ('clear niche with distinct triggers; minimal conflict risk'). It is more separable from adjacent skills than anchor 4's 'minor overlap risk' example.