project-memory

Name: project-memory
Author: jamditis

336stars57forks

How to install project-memory?

jamditis/claude-skills-journalism/project-memory

$npx -y skills add jamditis/claude-skills-journalism --skill project-memory

Installs into the current project.

Summary

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, publicati

Files · 1

View on GitHub

SKILL.md

1	# Project memory generator
2
3	Create CLAUDE.md files that transfer institutional 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.
4
5	## CLAUDE.md is advisory, not enforced
6
7	Anthropic is explicit on this point: CLAUDE.md content is delivered as a user message after the system prompt. Claude reads it and tries to follow it, but there's no guarantee of strict compliance — especially with vague or conflicting instructions. Source: https://code.claude.com/docs/en/memory
8
9	This affects how you write a CLAUDE.md and what you put elsewhere:
10
11	\| Mechanism \| Use for \| Source-of-truth \|
12	\|---\|---\|---\|
13	\| CLAUDE.md \| Standing facts, conventions, "always do X" rules \| Advisory \|
14	\| Skills \| Multi-step procedures, on-demand workflows \| Loaded when invoked \|
15	\| Hooks \| Actions that must happen every time, no exceptions \| Deterministic — runs as a shell command (e.g., `hooks/one-way-door-check.md`) or as a prompt the harness enforces (e.g., `hooks/enforce-test-first.md`) \|
16
17	If an instruction is "block writes to `published/`" or "run accessibility check before commit," that belongs in a hook, not CLAUDE.md. If it's "fact-check workflow" or "FOIA-letter drafting," that's a skill. CLAUDE.md is the place for things Claude must hold in every session.
18
19	## What belongs in CLAUDE.md
20
21	Anthropic publishes an explicit include/exclude table for what makes an effective CLAUDE.md. Source: https://code.claude.com/docs/en/best-practices
22
23	\| ✅ Include \| ❌ Exclude \|
24	\|---\|---\|
25	\| Bash commands Claude can't guess \| Anything Claude can figure out by reading code \|
26	\| Code style rules that differ from defaults \| Standard language conventions Claude already knows \|
27	\| Testing instructions and preferred test runners \| Detailed API documentation (link to docs instead) \|
28	\| Repository etiquette (branch naming, PR conventions) \| Information that changes frequently \|
29	\| Architectural decisions specific to your project \| Long explanations or tutorials \|
30	\| Developer environment quirks (required env vars) \| File-by-file descriptions of the codebase \|
31	\| Common gotchas or non-obvious behaviors \| Self-evident practices like "write clean code" \|
32
33	For journalism projects, translate to:
34
35	- Include: AP-style preferences that override defaults, "always cite source URLs," byline policy, embargo handling, source-protection invariants, CMS quirks (e.g., "story slugs must be unique across ALL desks, not just metro").
36	- Exclude: "We verify facts before publishing" (every journalist knows this), "use AP Style" without specifics (every journalism stack does this), framework documentation, generic git commands.
37
38	## The deletion test
39
40	For every line you write, ask: "Would removing this cause Claude to make mistakes?" If not, cut it.
41
42	## Size guidance: target under 200 lines
43
44	Anthropic's explicit guidance as of 2026: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence. Bloated CLAUDE.md files cause Claude to ignore the actual rules. Source: https://code.claude.com/docs/en/best-practices
45
46	Going over 200 lines is a signal to use one of these instead:
47
48	- `.claude/rules/` with `paths:` frontmatter — file-pattern-scoped rules that load only when Claude works with matching files. Replaces `@import` chains as the size-management mechanism. (Note: `@imports` no longer help with context size — Anthropic explicitly notes that imports load fully at launch.)
49	- Skills — for multi-step procedures that don't need to be in every session.
50	- Hooks — for deterministic enforcement.
51
52	## Where to put CLAUDE.md files
53
54	CLAUDE.md location precedence (more specific wins). Source: https://code.claude.com/docs/en/memory
55
56	\| Scope \| Location \| Use case \|
57	\|---\|---\|---\|
58	\| Managed policy \| Linux/WSL: `/etc/claude-code/CLAUDE.md`<br/>macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md`<br/>Windows: `C:\Program Files\ClaudeCode\CLAUDE.md` \| Org-wide standards (IT/DevOps managed; cannot be excluded by individual settings) \|
59	\| Project \| `./CLAUDE.md` OR `./.claude/CLAUDE.md` \| Team-shared instructions (check into git) \|
60	\| User \| `~/.claude/CLAUDE.md` \| Personal preferences across all projects \|
61	\| Local \| `./CLAUDE.local.md` \| Personal project-specific notes (add to `.gitignore`) \|
62
63	The `./.claude/CLAUDE.md` location and managed-policy tier are 2026 additions to Anthropic's documented locations. Templates that say "put this at project root" should mention `./.claude/CLAUDE.md` as an equally valid location.
64
65	## AGENTS.md

People who liked this also viewed

6 picks

Type

project-memory

336stars57forks

View on GitHub

How to install project-memory?

jamditis/claude-skills-journalism/project-memory

$npx -y skills add jamditis/claude-skills-journalism --skill project-memory

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Project memory generator
2
3	Create CLAUDE.md files that transfer institutional 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.
4
5	## CLAUDE.md is advisory, not enforced
6
7	Anthropic is explicit on this point: CLAUDE.md content is delivered as a user message after the system prompt. Claude reads it and tries to follow it, but there's no guarantee of strict compliance — especially with vague or conflicting instructions. Source: https://code.claude.com/docs/en/memory
8
9	This affects how you write a CLAUDE.md and what you put elsewhere:
10
11	\| Mechanism \| Use for \| Source-of-truth \|
12	\|---\|---\|---\|
13	\| CLAUDE.md \| Standing facts, conventions, "always do X" rules \| Advisory \|
14	\| Skills \| Multi-step procedures, on-demand workflows \| Loaded when invoked \|
15	\| Hooks \| Actions that must happen every time, no exceptions \| Deterministic — runs as a shell command (e.g., `hooks/one-way-door-check.md`) or as a prompt the harness enforces (e.g., `hooks/enforce-test-first.md`) \|
16
17	If an instruction is "block writes to `published/`" or "run accessibility check before commit," that belongs in a hook, not CLAUDE.md. If it's "fact-check workflow" or "FOIA-letter drafting," that's a skill. CLAUDE.md is the place for things Claude must hold in every session.
18
19	## What belongs in CLAUDE.md
20
21	Anthropic publishes an explicit include/exclude table for what makes an effective CLAUDE.md. Source: https://code.claude.com/docs/en/best-practices
22
23	\| ✅ Include \| ❌ Exclude \|
24	\|---\|---\|
25	\| Bash commands Claude can't guess \| Anything Claude can figure out by reading code \|
26	\| Code style rules that differ from defaults \| Standard language conventions Claude already knows \|
27	\| Testing instructions and preferred test runners \| Detailed API documentation (link to docs instead) \|
28	\| Repository etiquette (branch naming, PR conventions) \| Information that changes frequently \|
29	\| Architectural decisions specific to your project \| Long explanations or tutorials \|
30	\| Developer environment quirks (required env vars) \| File-by-file descriptions of the codebase \|
31	\| Common gotchas or non-obvious behaviors \| Self-evident practices like "write clean code" \|
32
33	For journalism projects, translate to:
34
35	- Include: AP-style preferences that override defaults, "always cite source URLs," byline policy, embargo handling, source-protection invariants, CMS quirks (e.g., "story slugs must be unique across ALL desks, not just metro").
36	- Exclude: "We verify facts before publishing" (every journalist knows this), "use AP Style" without specifics (every journalism stack does this), framework documentation, generic git commands.
37
38	## The deletion test
39
40	For every line you write, ask: "Would removing this cause Claude to make mistakes?" If not, cut it.
41
42	## Size guidance: target under 200 lines
43
44	Anthropic's explicit guidance as of 2026: target under 200 lines per CLAUDE.md file. Longer files consume more context and reduce adherence. Bloated CLAUDE.md files cause Claude to ignore the actual rules. Source: https://code.claude.com/docs/en/best-practices
45
46	Going over 200 lines is a signal to use one of these instead:
47
48	- `.claude/rules/` with `paths:` frontmatter — file-pattern-scoped rules that load only when Claude works with matching files. Replaces `@import` chains as the size-management mechanism. (Note: `@imports` no longer help with context size — Anthropic explicitly notes that imports load fully at launch.)
49	- Skills — for multi-step procedures that don't need to be in every session.
50	- Hooks — for deterministic enforcement.
51
52	## Where to put CLAUDE.md files
53
54	CLAUDE.md location precedence (more specific wins). Source: https://code.claude.com/docs/en/memory
55
56	\| Scope \| Location \| Use case \|
57	\|---\|---\|---\|
58	\| Managed policy \| Linux/WSL: `/etc/claude-code/CLAUDE.md`<br/>macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md`<br/>Windows: `C:\Program Files\ClaudeCode\CLAUDE.md` \| Org-wide standards (IT/DevOps managed; cannot be excluded by individual settings) \|
59	\| Project \| `./CLAUDE.md` OR `./.claude/CLAUDE.md` \| Team-shared instructions (check into git) \|
60	\| User \| `~/.claude/CLAUDE.md` \| Personal preferences across all projects \|
61	\| Local \| `./CLAUDE.local.md` \| Personal project-specific notes (add to `.gitignore`) \|
62
63	The `./.claude/CLAUDE.md` location and managed-policy tier are 2026 additions to Anthropic's documented locations. Templates that say "put this at project root" should mention `./.claude/CLAUDE.md` as an equally valid location.
64
65	## AGENTS.md

People who liked this also viewed

6 picks

Type