Project Context V2

Manage evidence-first memory across the full lifecycle of long-term scientific research and research engineering. Use when initializing a research project or adopting the memory system into an existing one, resuming work across AI sessions, formulating questions and hypotheses, planning or registering experiments, recording running/completed/failed experiments, preserving raw key tables and provenance, correcting invalid analyses, promoting findings into knowledge, auditing claim support, handing off work, or diagnosing documentation drift without losing reproducibility.

10 starsResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add poiuyjie/jev_project_context --skill project-context-v2

Manual install

git clone --depth 1 https://github.com/poiuyjie/jev_project_context.git /tmp/jev_project_context
mkdir -p ~/.claude/skills
cp -r /tmp/jev_project_context/. ~/.claude/skills/project-context-v2

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Project Context V2

Maintain research memory as a traceable chain from question to evidence to claim. Preserve measurements and provenance before interpretation so a later correction can replace the analysis without destroying the record.

## Non-negotiable rules

1. Treat evidence as more durable than interpretation. When space is limited, remove repetitive prose before removing key tables, sample counts, protocols, baselines, uncertainty, failure cases, or artifact paths.
2. Never silently rewrite history. Mark a result or claim `superseded` or `invalidated`, state why, and link its replacement.
3. Separate four epistemic classes:
   - **Evidence**: observed values and artifacts.
   - **Observation**: description directly supported by evidence.
   - **Interpretation**: causal or mechanistic explanation that may be wrong.
   - **Decision**: action chosen under stated evidence, constraints, and risk.
4. Never convert missing, incomparable, or failed measurements into conclusions. Use `—`, `not measured`, `failed`, or `incomparable` explicitly.
5. Keep raw or per-sample data in machine-readable artifacts when available. Preserve the decisive subset as Markdown tables so the project remains understandable if outputs are unavailable.
6. Record negative results, bugs, leakage, protocol changes, and counterexamples with the same care as improvements.
7. Do not claim causality from correlation, ablation-free comparisons, changed protocols, or cherry-picked samples.

Read the full skill on GitHub

Details

Skill name: project-context-v2
Repository: poiuyjie/jev_project_context
License: MIT
Repo updated: 22 September 2026

FAQ

What does the Project Context V2 skill do?

How do I install the Project Context V2 skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add poiuyjie/jev_project_context --skill project-context-v2. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Project Context V2 popular?

It lives in poiuyjie/jev_project_context, which has 10 GitHub stars and 0 forks.

Related skills

Research Cockpit

sanngotall/research-cockpit

Generate and dynamically maintain a visual project cockpit for any research or development project — a zero-dependency HTML dashboard with a research-trajectory flowchart, a hypothesis-space force graph, a status header, a pending-decisions list, and a hidden-premises panel. Use it when the user asks to "build / update / refresh the project cockpit", or whenever the project reaches a milestone closure, a major decision point, or a moment when the human needs to re-orient and steer the pace after long agent-run campaigns. The skill is project-agnostic and reusable.

Research & Science

Paper Reading

xiaofengShi/paper-reading-skill

Read a research paper from a PDF, arXiv link, URL, or local source and build one offline visual HTML atlas with a Markdown audit copy. Use when the user wants to understand or explain a paper's argument, mechanisms, equations or proofs, figures, and evidence. Two reading modes: Brief Reading for a focused explanation by default, and Deep Reading for full technical reconstruction on request. Reviewer critique and research comparisons are optional lenses.

Research & Science

Zotero

ketthub/zotero-skill

Query your local Zotero library. Supports keyword, fulltext, author, collection, tag, DOI, and recent-additions search. Trigger: /zotero, "my papers", "Zotero", "find paper", "references", "citations". After installation, verify DEFAULT_DB path in scripts/zotero-search.py points to your zotero.sqlite.

Research & Science

Sci Introduction

stephenlzc/sci-introduction

写"国内外研究现状"（文献综述 / Related Work）。当用户提到研究现状、文献综述、国内外研究对比、Literature Review、述评、研究背景、国内外研究现状时使用。即使用户没有明确说"写研究现状"，只要涉及对某一主题的国内外学术研究现状进行结构化梳理，就应该触发此技能。

Research & Science

Academic Research

orhoncan/oneshot-academic-research-skill

Create comprehensive academic research notes with deep literature coverage. Auto-detects language (EN prompt→EN output, TR prompt→TR output). Supports Obsidian markdown and PDF. Performs 8-15 iterative search cycles with 25-50+ sources for comprehensive coverage. Uses footnote citations and visual overviews.

Research & Science

Paperless Ngx

ColCh/paperless-ngx-skill

Use for Paperless-NGX API work: search, upload, download, metadata, tags, status, logs, bulk ops. Triggers: paperless.

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.