standards-core
Map K–12 Math/ELA standards (CCSS or state) to pages, lessons, tasks, and assessments in large PDF textbooks. Use when asked to compute alignment coverage, gaps, off-grade content, redundancy, or to output a per-standard evidence matrix with page anchors.
npx skills add majiayu000/claude-skill-registry --skill standards-core --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Standards-Core ## What this Skill does Given one or more PDF textbooks (teacher + student editions), produce: - **coverage_matrix.csv / .json** — standard ↔ {taught, practiced, assessed}, intensity, off-grade flags, redundancy. - **evidence.jsonl** — for each standard: top page hits with quoted spans and `book_id:page:start:end` anchors. - **pages.jsonl** — page-level text index (one JSON object per page). ## How to run 1. Prefer the installed `document-skills/pdf` to extract page text and tables. If not present, fall back to `pdftotext` (if available). 2. Build a page index: write `outputs/pages.jsonl` with {book_id, page, text}. 3. Load a **standards pack** (YAML) defining standards, grade ranges, and keyword lexicons. 4. Run `scripts/align_standards.py` to propose hits, then refine with LLM judgments for borderline matches. 5. Compute coverage, off-grade %, and redundancy per standard; write to `outputs/coverage.json` and `outputs/coverage.csv`. 6. For each standard with a rating, capture ≥1 quoted span + page anchor in `outputs/evidence.jsonl`. If none found, mark: `"unrated": "evidence not found"`. ## Inputs (ask the user or read CLI args) - subject: math|ela - grades: e.g.,
- What this Skill does
- How to run
- Inputs (ask the user or read CLI args)
- Deterministic first, generative second
- Scripts to call
- Evidence requirements
- Minimal standards pack example (save as standards/ccssmathsample.yaml)
- Output file formats
- coverage.json
- evidence.jsonl (one object per line)
- pages.jsonl (one object per page)
- Workflow example
- Error handling
scripts/align_standards.py --extract-pages math_grade3.pdf --out outputs scripts/align_standards.py \
What does the standards-core skill do?
Map K–12 Math/ELA standards (CCSS or state) to pages, lessons, tasks, and assessments in large PDF textbooks. Use when asked to compute alignment coverage, gaps, off-grade content, redundancy, or to output a per-standard evidence matrix with page anchors.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill standards-core --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.