alignment-review
Skill0 starsChanged 56 days agoMITView on GitHub
Checking objective-content-practice-assessment alignment and evidence support in course designs and built courses. Used by CourseForge alignment and final instructional reviewers.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- meta-pytorch/OpenEnvtheir own version, first seen Oct 8, 2026
- huggingface/OpenEnvtheir own version, first seen Apr 18, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- meta-pytorch/OpenEnv★ 2.8ksame name
- huggingface/OpenEnv★ 2.8ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- accessibility-reviewSkill
- assessment-designSkill
- assessment-reviewSkill
- course-gap-analysisSkill
- editorial-humanizationSkill
- fact-checkSkill
- html-intake-reviewSkill
- instructional-designSkill
- instructional-graphicsSkill
- research-authoringSkill
- research-planningSkill
- research-reviewSkill
- scenario-designSkill
- storyboard-authoringSkill
- ui-reviewSkill
- ux-reviewSkill
- visual-directionSkill
The file
Files
Alignment review
Alignment means four things line up for every objective: the evidence that makes it teachable, the content that teaches it, the practice that rehearses it, and the assessment that measures it, all at the same cognitive level.
Build the alignment chain
For each objective, write down (mentally or in notes):
- Evidence: the claim IDs that contain what a learner needs. Do they cover the whole objective, or only part?
- Teaching: the modules and specific content points or screens that teach it. Listing the objective in
loIdsis not teaching; look for the actual explanation. - Practice: the formative items or activities, and their level.
- Assessment: the graded items or method, and their level.
A break anywhere in the chain is a finding.
Level matching
| Objective verb (typical level) | Teaching needs | Practice and assessment that fit |
| identify, recognise (remember/understand) | clear definitions and examples | classification, single choice with realistic examples |
| explain, describe (understand) | mechanism and reasons | choose the best explanation; reveal with model answer (practice only) |
| distinguish, compare, classify (analyse) | explicit contrasts, worked comparisons | categorisation, matching, scenario items that hinge on the distinction |
| interpret (analyse) | worked interpretation of real-looking information | items presenting a label, report or data extract to interpret |
| select, determine, apply (apply) | decision criteria, worked examples | scenario items with plausible alternative choices |
| evaluate, justify (evaluate) | criteria and trade-offs, limits of evidence | scenarios requiring the best-supported choice and its reason |
| sequence (apply) | the process and why its order matters | sequencing with a genuinely required order |
| escalate, document (apply) | boundaries, triggers, who to involve | scenarios where escalation or documentation is the correct action |
Recall items for analyse or evaluate objectives are misaligned even if the content is right.
Common misalignments
- Orphan objective: listed but never actually taught.
- Unassessed objective: fewer than two graded items, or items below the objective's level.
- Untaught assessment: an item needs a fact, distinction or procedure not taught before it.
- Level drift: teaching at "understand", assessing at "evaluate" (unfair) or the reverse (invalid).
- Evidence mismatch: the objective promises more than the claims support.
- Compound objectives: "identify and evaluate and document" cannot be assessed cleanly; split or focus.
- Weighting: the most important objectives get the fewest items.
- Practice gap: first contact with a decision type happens in the graded assessment.
Writing alignment findings
Location is the objective ID (or item ID for an untaught item). Evidence lists the chain: objective statement, the claims, the teaching content point or screen, and the item stem, showing where it breaks. Recommend the smallest fix: add a teaching point to a named module, retarget an item's level, split an objective.
What code already checks
Code confirms every objective appears in a module and in the alignment table, every module objective exists, IDs resolve, and each objective has at least two graded items. It cannot judge whether teaching is real, levels match, or evidence is sufficient.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.