What This Skill Does

This skill executes a seven-role panel review of a curriculum framework artefact and returns structured scores, prose critiques, and a gate verdict. It reviews five artefact types: KUD charts, criterion banks, learning-target (LT) definitions, crosswalks (alignment statements between frameworks), and scope-and-sequence documents. Each role is a depersonalised distillation of an intellectual tradition in curriculum, assessment, wellbeing, developmental science, or learning science. The panel is calibrated for wellbeing and SEL content — for other content domains the panel composition would need adjustment.

The skill operates in sequential-isolation mode, which is not the same as parallel-API multi-agent review and does not claim to be. Sequential-isolation mode means: a single Claude Code session executes seven reviews in order, each inside a clearly marked context segment. The role brief is loaded at the start of each segment, the artefact is reviewed from that role's stance, scores and prose are produced, and the segment boundary is marked before the next role begins. Within a segment the prior role's critique is not referenced. This is a meaningful improvement on shared-context review — where seven voices get averaged into a single aggregated critique — but it does not fully eliminate cross-role influence the way a parallel-API architecture would. True parallel-API mode is deferred to a future version of this skill. The gate verdict is produced by an explicit aggregation rule (mean_overall >= 88 AND no role mean < 70) rather than by vibe-check synthesis.

Evidence Foundation

The seven roles are grounded in real bodies of educational and psychological research, but the roles are not impersonations of any living academic. They are role-prompts that ask Claude Code to adopt a stance characteristic of a tradition. Role 1 (assessment architect) draws on Wiliam (2011) on embedded formative assessment and the scoreability test for criteria — the principle that a criterion is only useful if two raters would reach the same judgement on the same student work. Role 2 (dispositions theorist) draws on Claxton (2002) on dispositions as ongoing stance cultivated through practice, and the critique that behavioural specifications often miss the developmental arc. Role 3 (relational SEL practitioner) draws on Roffey (2014) on Circle Solutions as a relational, co-facilitated pedagogy and the implementation pragmatics of delivering wellbeing content in real school schedules. Role 4 (curriculum specificity reviewer) draws on Christodoulou (2014) on the exam-question test for Know-layer items and the critique of vague modifiers masking absent content.

Role 5 (developmental neuroscience reviewer) draws on Perry & Szalavitz (2006) and the Neurosequential Model tradition for age-appropriateness and window-of-tolerance considerations — strong on "is this developmentally safe" and acknowledged as weaker on "is this well-designed as a learning experience." Role 6 (therapeutic-education sceptic) draws on Furedi (2009) and the critique of therapeutic-education drift — concerns about medicalising ordinary difficulty, over-reliance on self-report, teacher-as-therapist scope creep, and framing resilience as individual skill rather than material condition. Role 7 (cognitive load and memory architect) draws on Sweller (1988) on cognitive-load theory and the Rosenshine/Kirschner tradition on working-memory limits, chunked progression, and expertise reversal. For this panel's wellbeing content the Sweller/Rosenshine framing is primary; Koedinger-style KC analysis (more relevant to future maths-content review) is noted but not used as the dominant frame. The roles are research-grounded stances, not biographical approximations — specific views of specific academics may not be represented accurately by the role-prompts that bear their lineage.

Input Schema

Required.

• artefact — The full artefact to be reviewed. Paste as text or JSON. For a KUD chart this is the full table with all bands and cells. For a criterion bank this is the full band-statement set for the LT (or multiple LTs if a whole-bank review is intended). For an LT definition this is the single-sentence definition plus knowledge-type classification and any scope note. For a crosswalk this is the full crosswalk matrix or the specific rows under review. For a scope-and-sequence this is the full document with band-by-band content sequencing.

• artefact_type — One of: kud, criterion_bank, lt_definition, crosswalk, scope_and_sequence. Determines which dimension set is used by each role.