Conciseness

The body is lean: each technique gets only a one-line method, key insight, and red flag (e.g., "Test at extremes (1000x bigger/smaller, instant/year-long)"), with no padding explaining concepts Claude already knows. It sits at 4 rather than 5 because the 'When to Use' bullet list substantially duplicates the Quick Dispatch table, which is redundancy that could be trimmed to one section.

Actionability

For an instruction-only skill the guidance is mostly concrete: each technique has a specific heuristic with parameters ("Spot patterns appearing in 3+ domains", "Force unrelated concepts together"), plus diagnostic red flags ("Just need to add one more case...") that tell Claude exactly what to look for. It stops short of 5 because the Application Process steps like 'Apply systematically - Follow technique's process' are high-level, and no worked example appears in the body (details are correctly deferred to references).

Workflow Clarity

The Application Process is a clear five-step sequence (identify stuck-type, load reference, apply, document insights, combine if needed) fronted by a symptom-to-technique dispatch table, which is above the 3 anchor's implicit checkpoints. It is not 5 because there are no explicit validation checkpoints for whether a technique actually resolved the stuck-ness — step 4's 'Record what worked/failed' is a soft reflection step rather than a verify-then-proceed gate.

Progressive Disclosure

This is a textbook progressive-disclosure structure: a lean ~90-line overview with a Quick Dispatch table mapping each symptom to a specific reference file, all seven referenced files exist in ./references/, and the references are one level deep (when-stuck.md's dispatch table points to sibling technique files, not nested chains). This matches the 5 anchor's clear overview with well-signaled one-level-deep references.

Specificity

The description names the domain and several concrete techniques with their paired problem patterns ("simplification cascade (complexity spirals), collision-zone thinking (innovation blocks)...") plus an explicit action list ("simplify, analyze, recognize patterns, invert assumptions, scale thinking"). It falls just below the 5 anchor because the listed action verbs are somewhat generic ("analyze", "recognize patterns") compared to fully concrete actions, while clearly exceeding the 3 anchor's 1-2 actions.

Completeness

It explicitly answers both questions: the "what" via named techniques and actions, and the "when" via a literal "Use when: complexity spiraling, hitting innovation blocks, seeing recurring patterns, constrained by assumptions, uncertain about scale, generally stuck on problems" clause with concrete trigger phrases. This matches the 5 anchor exactly; the 4 anchor's weaker/'could be more explicit' when-clause does not apply.

Trigger Term Quality

The keyword list is comprehensive and natural for the domain: "problem solving, complexity spiral, innovation block, stuck, simplification, meta-pattern, assumption inversion, scale uncertainty, breakthrough thinking, root cause, systematic analysis, Microsoft Amplifier, debugging approach, creative solution" — covering synonyms and the colloquial phrases ("stuck", "root cause") a user would actually say. Not the 4 anchor since no common natural variations are obviously missing.

Distinctiveness Conflict Risk

The technique names ("collision-zone thinking", "scale game") are distinctive, but the trigger keywords "problem solving", "stuck", "root cause", "debugging approach", "creative solution" are broad and would overlap with debugging, root-cause-analysis, or general troubleshooting skills. It is somewhat specific but still carries overlap risk with closely related skills — the 3 anchor — rather than the mostly-distinct 4 anchor, because several keywords are not unique to this skill's niche.