agentleFS
naman10parikhnaman10parikh/pixel/.claude/skills/integrate-resources/SKILL.md

integrate-resources

Skill0 starsChanged 27 days agoMITView on GitHub

Process new resources dropped into resources/unread/. Extracts Claude Code tips, tools, patterns and updates the setup guide, skills, hooks, and knowledge catalog.

  • Installs packages

4 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

12 rules. About 0 are common, 10 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈10

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Add MCP servers to .mcp.json

    line 32
  2. Distinctive:

    Add wikilinks in existing vault notes to connect new knowledge

    line 36
  3. Distinctive:

    Update frontmatter tags on relevant notes

    line 37
  4. Very specific:

    NO new random documents: Do not create resources/research/, content/intelligence/reports/, or any other new standalone files for daily …

    line 43
  5. Distinctive:

    Dedup before writing: Check if an insight is already present.

    line 44
  6. Distinctive:

    Only add high-value touchpoints not already covered.

    line 45
  7. Distinctive:

    Never remove existing content — only enhance

    line 46
  8. Distinctive:

    If a tip contradicts existing guidance, flag it for human review

    line 47
  9. Distinctive:

    Prefer concrete, actionable configurations over vague advice

    line 48
  10. Distinctive:

    Always include source attribution inline (not in a separate catalog)

    line 49
  11. Distinctive:

    Test any new hook or setting configurations for correctness

    line 50
  12. Distinctive:

    This pipeline builds the NEXT thing: Every run should make the harness smarter, the content engine sharper, the vault more connected.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Trigger

User says something like "new resources to integrate" or "process unread resources"

Process

  1. List all files in resources/unread/
  2. Triage: batch-read all files, assign relevance 1-5 and category (HARNESS/AGENT/PRODUCT/CONTENT/CRYPTO/TECH/DESIGN/IRRELEVANT)
  3. For each file with relevance >= 3: a. Read the full content b. Check: is this insight ALREADY covered in our docs? If yes, skip or enhance existing text only. c. Extract actionable items:
    • Tools/packages to install (npm install, MCP servers, CLI tools)
    • Skills/hooks patterns to adopt
    • Strategic insights that shift our architecture or content
    • Competitor moves that require response d. For mentioned projects/tools: WebSearch to get current state, repo URL, install instructions
  4. WEAVE into EXISTING documents — route by CATEGORY per .claude/rules/resource-integration.md:
    • Tier 1 (ALL categories): the_complete_story.md, LEARNINGS.md, x-content-engine skill, vault notes
    • Tier 2 (CONTENT): content/distribution/ playbooks (MASTER-PLAYBOOK.md, PUBLISHING-WORKFLOW.md, PLATFORM-SPECIFIC-HOOKS.md), vault Ops - Content Engine / Distribution Playbook
    • Tier 3 (CRYPTO/EARNING): agents/earning/strategies/, vault Ops - Earning Strategy, CHAIRMAN-CHECKLIST.md
    • Tier 4 (HARNESS/AGENT): .claude/skills/, .claude/rules/, CLAUDE.md, .mcp.json, install tools
    • Tier 5 (DESIGN): .claude/rules/design.md, .claude/skills/design-systems/knowledge/
    • See .claude/rules/resource-integration.md for the COMPLETE routing table with 5 tiers and quick-reference chart
  5. INSTALL actionable tools immediately:
    • npm install -g <tool> for CLI tools
    • Add MCP servers to .mcp.json
    • Download skills/hooks from discovered repos
  6. Update Obsidian vault relationships:
    • Trace through vault/MOC - Energy Platform.md for where new knowledge connects
    • Add wikilinks in existing vault notes to connect new knowledge
    • Update frontmatter tags on relevant notes
  7. Move processed files to resources/read/ with date prefix: YYYY-MM-DD_originalname
  8. Summarize: what was integrated, WHERE it was integrated, what was installed

Rules (HARD — Chairman Directive)

  • NO new random documents. Do not create resources/research/, content/intelligence/reports/, or any other new standalone files for daily intake. Weave into existing docs.
  • Dedup before writing. Check if an insight is already present. If yes, enhance the existing text — don't duplicate.
  • Only add high-value touchpoints not already covered. Most articles will be "interesting but already addressed."
  • Never remove existing content — only enhance
  • If a tip contradicts existing guidance, flag it for human review
  • Prefer concrete, actionable configurations over vague advice
  • Always include source attribution inline (not in a separate catalog)
  • Test any new hook or setting configurations for correctness
  • This pipeline builds the NEXT thing. Every run should make the harness smarter, the content engine sharper, the vault more connected. It's a compounding intelligence loop sourced from the community and the digital AI town square.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.