agentsclimarketplace

Lesson plan

Skill Jellypod-Inc/school-skills/skills/lesson-plan

One-shot standards-aligned lesson plans — Common Core, NGSS, TEKS, IB, Cambridge, state frameworks. Takes a topic, grade, and duration; returns a fully formatted plan with objectives, standards, materials, Gradual Release pedagogy (I do / we do / you do), 13 sections, and ELL/SPED/Gifted differentiation. Covers K-12, college, and homeschool. USE THIS SKILL when the user says "write a lesson plan," "I need a lesson on X for Y grade," "plan a lesson," "45-minute lesson on," "Common Core lesson," "NGSS lesson," "emergency sub plan," "homeschool lesson," "multi-day unit," "IB MYP lesson," "first-year-teacher SOS," "TEKS-aligned lesson," or any phrase combining a topic + a grade + a duration. Output: markdown with YAML footer for sibling-skill handoff; optional PDF.From its SKILL.md

Install
npx -y skills add Jellypod-Inc/school-skills --skill lesson-plan

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 1 command, including `python3 shared/scripts/pdf_render.py --input <markdown-file.md> --output <output-file.pdf> --style lesson-plan`.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

9.8 KB, ~2.3k tokens by cl100k_base, as published. Nobody here has run it

Lesson Plan Skill

Generate standards-aligned, pedagogy-grounded lesson plans ready to print or drop into a planner.

When to use this skill

Trigger on any phrase combining topic + grade + duration, or any of these concrete cues:

  • "Write me a lesson plan on [topic] for [grade]."
  • "I need a [duration] lesson on [topic] by tomorrow."
  • "Plan a [grade] NGSS lesson on [topic]."
  • "Build a Common Core ELA lesson on [topic] for [grade]."
  • "Make a homeschool lesson on [topic] for my [grade]er."
  • "Give me a [duration] high school [subject] lesson on [topic]."
  • "Draft a kindergarten lesson on [topic]."
  • "I need an emergency sub plan for [grade] [subject]."
  • "Plan a multi-day unit on [topic] for [grade]."
  • "Create an IB MYP lesson on [topic]."
  • "Cambridge / IGCSE / A Level lesson on [topic]."
  • "TEKS-aligned lesson on [topic] for [grade]."
  • "First-year-teacher SOS — [duration] lesson on [topic]."

Inputs

Required:

  • Topic — free-text.
  • Grade — K, 1, 2, … 12, college, grad, or homeschool-equivalent.
  • Duration — minutes (or days × minutes for units).

Optional (reasonable defaults applied if absent):

  • Standards framework — defaults by subject (CCSS for ELA/Math, NGSS for Science, general best practice otherwise).
  • Pedagogy — default Gradual Release (Fisher & Frey "I do / we do / you do"), with UDL as the lens for differentiation. Auto-overrides to 5E for Science lessons unless user specifies otherwise.
  • Class size, prior knowledge level, accommodations (ELL/SPED/Gifted).

Output

  • Markdown lesson plan (default). 13 sections — see references/templates/lesson-plan.md for the skeleton.
  • YAML footer — machine-readable handoff block for sibling skills (worksheet, quiz-generator, rubric). Spec in references/output-contract.md.
  • Optional PDF — via shared/scripts/pdf_render.py if the user asks for a printable version.

Inferring grade from phrasing (before asking)

Ask about grade ONLY if you cannot confidently infer it. Use these cues first:

Cue in user's phrasingLikely grade band
"my kindergartener," "my 5yo," "circle time," "calendar math"K
"my 3rd grader," "multiplication tables," "book report"3-5
"middle school," "pre-algebra," "ratios," "5 paragraph essay"6-8
"AP ___," "PSAT," "thesis statement," "MLA works cited"9-12
"syllabus," "semester," "lecture," "TA," "office hours"College
"dissertation," "my students' IRB," "cohort"Grad
"my ELL/EB student," "newcomer," "WIDA"pair with grade + add ELL strategies
"homeschool," "my own kid"use grade number; add home-friendly mods

If confidence is still low, ask ONE clarifying question in this exact shape:

Quick check so I can calibrate this — which grade is this for? (e.g. K · 3rd · 7th · 10th · college)

Do not stack questions. Do not ask for framework, duration, class size, etc. unless the user explicitly wants tight customization.

Workflow (summary — full details in references/workflow.md)

  1. Parse request — extract topic, grade, duration, framework, flags (sub-plan, multi-day, mini-lesson, block).
  2. Infer, then clarify — attempt grade inference from the table above first. Only ask one question if grade is still unclear. Duration defaults to 45 min if unspecified.
  3. Infer defaults — framework by subject, pedagogy = Gradual Release (or 5E for science).
  4. Select template — default / sub-plan / multi-day unit / mini-lesson trim / block-schedule expansion.
  5. Load standards reference — read only the file(s) matching the framework.
  6. Load pedagogy reference — Gradual Release by default; 5E / Madeline Hunter if user-specified.
  7. Load differentiation catalog — plus learner-category file(s) as needed.
  8. Load grade-calibration rules — tone, vocabulary, session structure.
  9. Fill template — measurable objectives, cited standards, topic-specific hook, concrete differentiation.
  10. Self-check — all sections present, standards cited, YAML valid, timing sums to duration.
  11. Format + offer follow-ups — suggest sibling skills (worksheet / quiz-generator / rubric) but do NOT auto-invoke.

Progressive disclosure — reference files

Load on demand based on the request. Do NOT read all references for every request.

Standards (load one matching the user's framework)

  • references/standards/common-core-ela.md — CCSS ELA strands (RL, RI, W, SL, L, RH, RST, WHST) K-12.
  • references/standards/common-core-math.md — CCSS Math domains + Mathematical Practices K-12.
  • references/standards/ngss.md — NGSS Performance Expectations, DCIs, SEPs, CCCs.
  • references/standards/state-frameworks.md — TEKS, NY NGLS, CA, FL B.E.S.T., VA SOL (+ pointers to other states).
  • references/standards/ib.md — PYP, MYP, DP.
  • references/standards/cambridge.md — Primary, Lower Secondary, IGCSE, A Level.

Pedagogy

  • references/pedagogy/gradual-release.mddefault — Fisher & Frey.
  • references/pedagogy/udl.mdalways apply — Universal Design for Learning lens.
  • references/pedagogy/5e.md — auto-override for Science.
  • references/pedagogy/madeline-hunter.md — on explicit user request.

Differentiation

  • references/differentiation/catalog.mdalways load — cross-cutting strategy index.
  • references/differentiation/ell-strategies.md — WIDA + SIOP scaffolds.
  • references/differentiation/sped-strategies.md — IEP / 504 accommodations.
  • references/differentiation/gifted-strategies.md — depth-not-pace extensions.

Templates

  • references/templates/lesson-plan.mddefault 13-section template.
  • references/templates/sub-plan.md — emergency substitute plan.
  • references/templates/multi-day-unit.md — unit with daily sub-sections.

Meta

  • references/grade-calibration.md — tone + length + vocabulary + activity rules by band.
  • references/workflow.md — step-by-step generation procedure.
  • references/edge-cases.md — sub-plan, multi-day, mini-lesson, block schedule, cross-grade, sensitive topics, non-English-primary.
  • references/output-contract.md — YAML footer spec.

Locked defaults

SettingDefault
PedagogyGradual Release (I do / we do / you do)
Differentiation lensUDL (multiple means of engagement / representation / action & expression)
Framework — ELACCSS ELA
Framework — MathCCSS Math
Framework — ScienceNGSS (+ auto-override pedagogy to 5E)
Framework — otherGeneral best practice
OutputMarkdown + YAML footer
Cross-skill invocationNone — offer sibling-skill suggestions, do not auto-invoke.

Micro-example

User: "45-minute lesson on photosynthesis for my 7th grader"

Inferred: grade 7 (explicit), subject=Science → NGSS + 5E pedagogy, duration 45. Skill responds (no clarifying question needed): fully formed plan starting —

# Photosynthesis: How Plants Make Food (7th Grade Science)

**Standards:** NGSS MS-LS1-6 — Construct a scientific explanation based on evidence
for the role of photosynthesis in the cycling of matter and flow of energy…

**Objective:** Students will model the chemical equation of photosynthesis and
explain how light energy is captured by chloroplasts and converted into chemical
energy in glucose, with 80% accuracy on the exit ticket.

## 5E Workflow (45 min)
1. **Engage (5 min)** — Show a sped-up timelapse of a seedling sprouting in light…
2. **Explore (10 min)** — Lab: observe two elodea sprigs, one in light one in dark…
…

Full YAML footer follows the plan. Sibling-skill suggestions appear at the end.

PDF export (optional)

When the user asks for a PDF, run the shared script from the repo root:

python3 shared/scripts/pdf_render.py \
  --input <markdown-file.md> \
  --output <output-file.pdf> \
  --style lesson-plan

The script expects lesson-plan-style formatting (letterhead, section headers). If the --style lesson-plan flag is unsupported (first-time run against a worksheet-only script), fall back to --style default and note to the user: "PDF rendered with default style — the lesson-plan-specific template is planned for a later update."

Quality bar

Every generated plan must satisfy:

  • All required template sections present.
  • Standards cited with framework + code + full text (or explicit "no framework applies" note).
  • Objectives use measurable Bloom's verbs (NOT "understand," "know," "learn about" as sole verb).
  • Differentiation has ELL + SPED + Gifted subsections with 2+ concrete strategies each.
  • Materials list matches activity requirements.
  • Timing sums to the requested duration.
  • Grade-band calibration applied.
  • YAML footer present and valid.

What NOT to do

  • Do not invent standards codes. If uncertain, describe the strand and note "Verify the specific code with your district."
  • Do not use "understand," "know," or "learn about" as the sole verb in any objective.
  • Do not skip the Differentiation section, even for short lessons.
  • Do not auto-invoke sibling skills — just suggest.

What ships with it: 22 files

82.4 KB alongside SKILL.md

evals/

Gives 0 of the 12 instructions most docs writing skills give in ~2.3k tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • infer grade from user phrasing before asking
  • ask only one clarifying question if grade is unclear
  • apply Gradual Release pedagogy by default
  • apply 5E pedagogy for science lessons
  • apply UDL lens for differentiation
  • cite standards with framework, code, and full text

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.