pinpoint-lesson

pinpoint-lesson is a skill for Claude Code, Codex from ajs7270/zotero-ai-summary. It costs 70 tokens per session (5,651 once invoked), scanned A, original, MIT.

A Zotero note-making skill for turning one academic paper into a detailed lesson with explanations, mathematical background, derivations, and reusable rules. Zotero is a reference manager for papers and research notes.

In plain words
What is it for?
Use it with a paper PDF, title, or citation key when you need a deep technical reading and a long-form child note in Zotero.
Why use it?
It is for understanding and remembering how a paper's method works, not just recording its main points. The lesson is saved under the matching paper in Zotero.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it with a paper PDF, title, or citation key when you need a deep technical reading and a long-form child note in Zotero.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ajs7270/zotero-ai-summary/pinpoint-lesson
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add ajs7270/zotero-ai-summary --skill pinpoint-lesson
Clone the repo
git clone --depth 1 https://github.com/ajs7270/zotero-ai-summary

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pinpoint-lesson

README.md
[![agentmods](https://agentmods.dev/badge/skills/ajs7270/zotero-ai-summary/pinpoint-lesson/github.svg)](https://agentmods.dev/skills/ajs7270/zotero-ai-summary/pinpoint-lesson)
Your own site
<a href="https://agentmods.dev/skills/ajs7270/zotero-ai-summary/pinpoint-lesson"><img src="https://agentmods.dev/badge/skills/ajs7270/zotero-ai-summary/pinpoint-lesson/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pinpoint-lesson

Your own site · 80×15
<a href="https://agentmods.dev/skills/ajs7270/zotero-ai-summary/pinpoint-lesson"><img src="https://agentmods.dev/badge/skills/ajs7270/zotero-ai-summary/pinpoint-lesson.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.05651
Opus 5 $0.00035 $0.02825
Sonnet 5 $0.00014 $0.01130
Haiku 4.5 $0.00007 $0.00565

Measured 12d ago against content hash e604a1b59d03, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pinpoint-lesson scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/prepare_pdf_artifacts.py, scripts/zotero_register_note.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/pinpoint-lesson/SKILL.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pin Point Lesson

Compose a long-form pin-point lesson note from one paper and register it as a child note under the matching Zotero item. A pin-point lesson is centered on what a researcher should remember and reuse: mathematical preliminaries, idea provenance, method derivations, fundamental whys, and a list of reusable rules.

When to invoke

Invoke this skill when the user asks for a deep reading, lesson, derivation, fundamental analysis, or pin-point note from a paper. If the user only wants a quick reference summary, call the summary skill instead.

Invocation schema

Use:

/pinpoint-lesson <PDF-path | Zotero-paper-title | citation-key> [language: <language>]

Examples:

/pinpoint-lesson /path/to/paper.pdf
/pinpoint-lesson "Paper title already in Zotero" language: Korean
/pinpoint-lesson @citationKey language: Japanese

Language resolution:

  1. If language: <language> is present, use that language for the note body.
  2. Otherwise, if the user's request contains natural-language instructions, use that request language.
  3. Otherwise, default to English.

Pipeline

  1. Identify the target Zotero item via zotero-mcp, the same way as the summary skill.
  2. Extract evidence with scripts/prepare_pdf_artifacts.py <pdf> --out <work-dir> --render-pages. Use pdftotext output as the primary text source.
  3. Read existing Zotero context, including any prior summary note. The pin-point lesson is allowed to coexist with a summary note, but should not duplicate it.
  4. Compose the lesson in Markdown following the structure below.
  5. Run the quality gate below before registration. If any gate fails, revise the Markdown first; do not register a thin note.
  6. Register the note via scripts/zotero_register_note.py to http://localhost:23119/aisummary/note.

Note structure

The note is one Markdown file with these sections in order. Each section is the answer to one essence question — and the section's opening sentence should restate that question or the section's reason for existing. Without that opening, sections degenerate into rote checklists. H2 headings carry an emoji prefix exactly as listed.

Read the full file on GitHub · 216 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 216 lines · 70 tokens per session scan A e604a1b59d03

Subscribe to this mod's changes

pinpoint-lesson is a skill published in the GitHub repository ajs7270/zotero-ai-summary (19 stars, last pushed 3mo ago), licensed MIT. It adds 70 tokens to every session and 5,651 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

learning-assistant

An interactive study assistant that turns a learning goal into a structured plan and guides the learner through it. It uses a local knowledge graph, a connected record of topics and learning state, as its long-term memory.

cafe3310/public-agent-skills · 26 tokens

project-learner

An interactive project-teaching assistant that explains a codebase, files, or underlying technologies and records the lessons in Markdown logs. It can continue from earlier learning records.

cafe3310/public-agent-skills · 46 tokens

study

Guide structured learning for a topic by diagnosing current level, defining stage goals, building a learning path, generating practice, and running review loops. Use when the user wants to learn something step by step, start from zero, build a study plan, prepare for an exam or skill, get guided practice, or continue…

flc1125/skills · 76 tokens

eli5

Create a simple, picture-first explanation of a topic, defaulting to self-contained HTML. Use when the user says ELI5, asks to explain something like they are five, or wants a visual explanation with very few words; do not use for ordinary concise explanations that do not ask for this style.

flc1125/skills · 64 tokens

subject-learning-assistant

A structured learning assistant that turns study material into a plan of subjects, topics, and individual concepts. It can guide lessons and track progress using a connected knowledge map.

cafe3310/public-agent-skills · 59 tokens

mental-health-psychoeducation

Comprehensive psychoeducation on mental health conditions, therapy modalities, evidence-based coping techniques, psychiatric medications, and self-assessment frameworks. Educational resource only — not medical advice, diagnosis, or treatment. Use when learning about mental health concepts, understanding therapy…

firstsun-dev/skills · 111 tokens