agentleFS
IgorGanapolskyIgorGanapolsky/mac-yolo-safeguards/.agents/skills/context-six-block/SKILL.md

context-six-block

Skill3 starsChanged 4 days agoMITView on GitHub

Everyday AI Ep 710 FORMAT steal: six context blocks (goal, constraints, reference, examples, procedures, rubric) across personal/team/company/market layers. Show-don't-tell few-shot gold and rubric-first grading. Not Everyday AI, not ChatGPT connectors. Complementary to context-vault (Allie 8 prompts). Slash: /context-six-block.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use before drafting agent/public copy when the user cites Everyday AI, six key blocks, show don't tell, rubric-first, or reusable context …

    line 11
  2. Very specific:

    Add ChatGPT/Claude/Gemini connector SKUs

    line 30

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Context six-block pack

Use before drafting agent/public copy when the user cites Everyday AI, six key blocks, show don't tell, rubric-first, or reusable context vaults.

Steal (FORMAT only)

BlockMeaning here
GoalWhat to produce and for whom
ConstraintsChief lock, no Continuity hero, no invented traction
ReferenceAGENTS.md, CHIEF.md, SKILLS.md
ExamplesConcrete gold + bad (not "write well")
ProceduresLoad pack → example → rubric → capped repair
RubricmustInclude / mustNot, graded before ship

Layers: personal (this agent/worktree), team (AGENTS.md), company (Chief), market ($10 fenced VPS).

Do not

  • Clone Everyday AI / Prime Prompt Polish
  • Add ChatGPT/Claude/Gemini connector SKUs
  • Dual-edit tools/context-vault.js
  • Claim LIVE from this pack (liveClaim is always false)

Proof

node tests/test-context-six-block.js
node tools/context-six-block.js --json
node tools/context-six-block.js --grade "Hosted Hermes is $10/mo chat on a fenced VPS."

Business-data "connectors" map to coding-context-pack, recall, and SKILLS.md.

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.