YujxZJCN/teaching-skills-codex — Agents

6Stars on the repository

107Mods indexed here, across every type

2mo agoLast push, which is what freshness is scored on

MITLicence, which decides whether bodies are shown

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 75 mods

evidence_assembler_agent

Agent Claude Code

Assembles the evidence package behind a confirmed matrix — inventories what exists with provenance, lists what's missing with the cheapest honest fix; never fabricates data.

not rated 6 +1 2mo ago A 36 tokens copy · 100% MIT

matrix_builder_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Builds and maintains the LO × program-outcome × criterion mapping matrix — professor-claimed strengths, computed per-cell evidence status, hollow-cell and over-mapping flags.

not rated 6 +1 2mo ago A 37 tokens copy · 95% MIT

selfstudy_writer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Drafts self-study and continuous-improvement sections from the confirmed matrix + evidence index — claim strength capped by evidence status, every factual sentence traceable.

not rated 6 +1 2mo ago A 34 tokens copy · 100% MIT

standards_analyst_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Normalizes professor-supplied standards and program outcomes into a criteria register — verbatim text, evidence type demanded, vague-criterion flags.

not rated 6 +1 2mo ago A 34 tokens copy · 94% MIT

accommodation_designer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.

not rated 6 +1 2mo ago A 29 tokens copy · 98% MIT

answer_key_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Independently works every item to produce the verified answer key, worked solutions, and grading notes.

not rated 6 +1 2mo ago A 23 tokens copy · 100% MIT

blueprint_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Builds the test blueprint — content × Bloom matrix, point and time budgets — before any item exists.

not rated 6 +1 2mo ago A 24 tokens copy · 98% MIT

grade_analyst_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Closes the gradebook: final-grade distribution with shape diagnostics, a what-if cutoff/curve comparator, and a fairness note — aggregates only, the professor sets cutoffs.

not rated 6 +1 2mo ago A 40 tokens copy · 91% MIT

group_designer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Designs graded group projects with genuine interdependence, individual accountability, and a peer-assessment instrument that adjusts individual grades fairly.

not rated 6 +1 2mo ago A 30 tokens copy · 98% MIT

integrity_auditor_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Runs the AI-era integrity audit over assessment instruments per shared/aieraintegrity.md — read-only.

not rated 6 +1 2mo ago A 28 tokens copy · 95% MIT

item_analyst_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Post-exam item analysis from a professor-provided results table — difficulty, discrimination, distractors, per-item actions.

not rated 6 +1 2mo ago A 29 tokens copy · 100% MIT

item_writer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Drafts assessment items cell-by-cell against the confirmed blueprint; distractors from known misconceptions.

not rated 6 +1 2mo ago A 21 tokens copy · 95% MIT

project_designer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Writes TILT-structured project and assignment briefs with milestone staging, scope honesty, and group-work mechanics.

not rated 6 +1 2mo ago A 25 tokens copy · 94% MIT

rubric_designer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Designs analytic, holistic, or single-point rubrics with observable descriptors and TA calibration anchors.

not rated 6 +1 2mo ago A 24 tokens copy · 92% MIT

glossary_keeper_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Extracts candidate terms, proposes pairs with authority notes, runs professor confirmation, maintains the versioned glossary other skills consume.

not rated 6 +1 2mo ago A 29 tokens copy · 95% MIT

parallel_sync_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Maintains the paired-version registry, propagates changes glossary-bound, detects drift three-way; the professor chooses merge direction — never auto-merges.

not rated 6 +1 2mo ago A 32 tokens copy · 98% MIT

terminology_auditor_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.

not rated 6 +1 2mo ago A 29 tokens copy · 98% MIT

translator_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.

not rated 6 +1 2mo ago A 22 tokens copy · 95% MIT

calibration_advisor_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Turns a confirmed cohort profile into concrete teaching adjustments: reteach/activate/skip calls, misconception-targeted changes, pacing flags, within-classroom differentiation.

not rated 6 +1 2mo ago A 36 tokens copy · 100% MIT

cohort_analyst_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Computes per-concept readiness distributions, misconception prevalence, and heterogeneity from diagnostic data — aggregates only, with mandatory instrument-strength caveats.

not rated 6 +1 2mo ago A 34 tokens copy · 91% MIT

diagnostic_designer_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Designs ungraded diagnostics and pre-lesson questionnaires: prerequisite probes, two-tier misconception items, labeled self-efficacy items — analysis plan before deployment.

not rated 6 +1 2mo ago A 36 tokens copy · 91% MIT

grouping_strategist_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Builds evidence-based grouping plans matched to the pedagogical goal — heterogeneous, homogeneous, or role-based — pseudonymous, rotating, never ability-ranked in public.

not rated 6 +1 2mo ago A 38 tokens copy · 94% MIT

alignment_auditor_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Runs the constructive-alignment audit (Gate 1.5 checklist) over the Course Passport — read-only.

not rated 6 +1 2mo ago A 27 tokens original MIT

assessment_planner_agent

YujxZJCN/teaching-skills-codex

Agent Claude Code

Designs the assessment structure — types, weights, timing, AI-policy tiers — against confirmed outcomes.

not rated 6 +1 2mo ago A 24 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: