Project memory
Skill pinkpixel-dev/skills-collection-2/SKILLS/project-memory
Part 2 of the AI and agent skills collection, with 650+ skill folders focused on reusable workflows, security playbooks, cloud implementation guides, scripts, references, and assets for builders and operators.
npx -y skills add pinkpixel-dev/skills-collection-2 --skill project-memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 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.
What its author says it does
Copied from the file, not written here
Generate CLAUDE.md project memory files that transfer institutional knowledge, not obvious information. Use when setting up new journalism projects, onboarding collaborators, or documenting project-specific quirks. Includes templates for editorial tools, event websites, publications, research projects, content pipelines, and digital archives.
SKILL.md
5.2 KB, as published. Nobody here has run it
Project memory generator
Create CLAUDE.md files that transfer tribal knowledge, not obvious information. Think like a senior journalist onboarding a competent colleague—you don't explain how journalism works, you explain YOUR project's quirks.
What belongs in CLAUDE.md
| Include | Don't include |
|---|---|
| Project-specific quirks | How journalism works generally |
| YOUR naming conventions | Standard file organization |
| Commands with YOUR flags | Generic commands like "npm install" |
| Non-obvious architecture | Framework documentation |
| Common mistakes in THIS project | General best practices |
| External service configurations | Information already in comments |
| Source handling requirements | Basic ethics everyone knows |
The deletion test
For every line you write, ask: "Would an experienced journalist already know this?"
- If yes → Delete it
- If no → Keep it
Basic template structure
# CLAUDE.md
## Project overview
[1-2 sentences maximum. What this does + who uses it.]
## Commands
[Only project-specific commands. Not generic ones.]
## Architecture
[Only non-obvious decisions. Where does X live? Why?]
## Patterns
[Only patterns unique to this project]
## Things to avoid
[Project-specific anti-patterns and gotchas]
## External dependencies
[APIs, services, credential locations]
What to cut ruthlessly
Generic commands everyone knows:
<!-- DELETE THIS -->
git add . # Stage changes
npm install # Install dependencies
Obvious journalism patterns:
<!-- DELETE THIS -->
We verify facts before publishing. All quotes must be
attributed. Follow AP Style...
Framework explanations:
<!-- DELETE THIS -->
React components live in /components. We use hooks
for state management...
What to keep
Project-specific quirks:
<!-- KEEP THIS -->
Source names in the spreadsheet use LAST, FIRST format
but the CMS expects FIRST LAST. The import script handles
this, but manual entries need flipping.
Non-obvious architecture:
<!-- KEEP THIS -->
Embargo dates are stored in the CMS as NYC time but
displayed in the reader's local time. Server-side renders
use UTC. Check timezone handling before changing date code.
Gotchas that burned you:
<!-- KEEP THIS -->
The AP feed disconnects silently after 4 hours. Cron job
at :00 checks connection and restarts if stale.
Voice guidelines
- Direct and terse
- Like notes you'd leave for yourself
- No marketing language
- No "Welcome to..." introductions
- No "This project is..." padding
Example: Good vs bad
Bad (too verbose, obvious):
# CLAUDE.md
## Overview
Welcome to our newsroom's story tracking system! This is a
web application built with React and Node.js that helps
editors and reporters collaborate on stories.
## Getting started
First, make sure you have Node.js installed. Then:
npm install
npm start
Good (tribal knowledge only):
# CLAUDE.md
## Overview
Story tracker for metro desk. React + Supabase.
## Gotchas
- Story slugs must be unique across ALL desks, not just metro
- "Hold" status doesn't stop the autopublish cron—use "Kill"
- Reporter dropdown caches for 1 hour; new hires won't appear
## Commands
npm run sync-ap # Pull latest from AP, runs automatically at :15
## Credentials
Supabase key in 1Password "Metro Desk" vault, not .env
Length guideline
A good CLAUDE.md is 50-150 lines. If it's longer, you're explaining too much. If it's shorter, you might be missing critical quirks.
Journalism-specific templates
Templates are in the templates/ directory:
| Template | Use for |
|---|---|
editorial-tool.md | Newsroom tools, fact-checkers, AI assistants |
event-website.md | Conferences, workshops, campaign sites |
publication.md | Newsletters, podcasts, ongoing content series |
research-project.md | Investigations, data journalism with defined scope |
content-pipeline.md | CMS workflows, publishing automation |
digital-archive.md | Historical collections, document repositories |
Template selection guide
What are you building?
├── Tool for the newsroom → editorial-tool.md
├── Site for an event → event-website.md
├── Recurring content series → publication.md
├── One-time investigation → research-project.md
├── Publishing automation → content-pipeline.md
└── Archive/preservation → digital-archive.md
How to use templates
- Copy the appropriate template to your project root as
CLAUDE.md - Fill in the bracketed placeholders with YOUR specifics
- Delete any sections that don't apply
- Add project-specific gotchas as you discover them
- Keep it updated—stale CLAUDE.md files cause confusion
The best CLAUDE.md files are written by people who've been burned by the quirks they're documenting.
Gives 0 of the 12 instructions most memory context skills give
Counted across 674 of the 847 authors here whose files we hold, read 2026-08-06
- inform the user when setup is completein 21 of 674, across 6 files
- confirm the draft with the user before writingin 21 of 674, across 6 files
- update the agent skills block in place if it existsin 21 of 674, across 6 files
- present findings to the userin 20 of 674, across 5 files
- write the three docs files from seed templatesin 20 of 674, across 5 files
- ask the user about each decision one at a timein 19 of 674, across 4 files
- edit CLAUDE.md if it existsin 18 of 674, across 3 files
- explore current repo statein 18 of 674, across 3 files
- do not overwrite user edits to surrounding sectionsin 18 of 674, across 3 files
- back up the original file before overwritingin 16 of 674, across 8 files
- keep the memory index under 200 linesin 15 of 674
- Provide actionable steps and verificationin 13 of 674, across 2 files
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.