Conciseness

The body is lean and assumes domain competence: no padding, no explanation of what slabs or catalysis are, and every line carries tool-specific guidance. It matches the 'every token earns its place' anchor.

Actionability

Guidance is concrete — named tools (build_slab, fix_atoms_by_layers, fix_atoms_by_height, supercell) with specific parameters (slab_thickness, layer_tol, z_ranges, centralize) and real behavioral constraints ('freeze_layers must not exceed the detected layer count'). It is not a 5 because there are no example invocations or command lines a user could copy-paste for the common cases.

Workflow Clarity

A clear three-step sequence with ordering rationale ('Expand cells only after fixing policy is understood') and a guardrail for the destructive operation ('supercell … drops all selective-dynamics information, so do not call it after you have already finalized atom constraints'). The Output Contract also requires reporting whether supercell invalidated prior flags, which serves as a verification checkpoint, so the destructive/batch cap at 3 does not apply; it misses 5 only because there is no explicit validate-and-retry loop.

Progressive Disclosure

The skill is under 50 lines, needs no external reference files (none exist in the bundle), and is organized into well-labeled sections (Overview, Quick Start, Suggested tools, Workflow, Output Contract, References) with a clean hand-off to the adsorption-site-screening skill. This matches the rubric's simple-skill guideline for a full score.

Specificity

The description names the domain and four concrete action areas — 'slab construction, vacuum and layer choices, surface supercell setup, and atom-fixing strategy' — matching the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because it omits capabilities the body actually covers, such as termination selection and Miller-index handling.

Completeness

Both what and when are present: 'Use this skill for slab construction, … atom-fixing strategy in heterogeneous catalysis workflows' gives capabilities plus an explicit trigger clause, so it clears the 3-cap for missing 'Use when' guidance. It is not a 5 because the when-clause is a topic list rather than concrete user-phrase triggers like 'when the user asks to build a slab or fix slab atoms'.

Trigger Term Quality

Good natural keyword coverage for the domain: 'slab construction', 'supercell', 'atom-fixing', 'heterogeneous catalysis' are phrases users would say. It is not a 5 because common variations like 'Miller index', 'surface model', or 'freeze atoms' are missing.

Distinctiveness Conflict Risk

The 'in heterogeneous catalysis workflows' qualifier gives it a clear niche with distinct triggers, but 'supercell' and 'vacuum' overlap slightly with closely related structure-editing and adsorption skills. It is mostly distinct rather than minimal-conflict, so 4 rather than 5.