agentleFS
HeyEddi-comHeyEddi-com/heyeddi-skills/skills/heyeddi/SKILL.md

heyeddi

Skill0 starsChanged 3 months agoMITView on GitHub

ALWAYS-ON router named @heyeddi. Discovers skills, syncs .heyeddi/, and decides what to run. Design talk goes to @taste-penpot first (look, one pass) then @heyeddi-design (product, handoff). @heyeddi-orchestrator is a deprecated alias. Use at every session start, on ambiguous tasks, and when connecting product, UX, and design.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 3 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before a multi-step pipeline (intake → scaffold → design → handoff → QA)

    line 21
  2. Very specific:

    After @heyeddi-intake: confirm skill-routing.json before downstream work

    line 24
  3. Very specific:

    Prose anti-slop: when copy or .heyeddi docs change (verify_prose --check)

    line 32
  4. Very specific:

    Clarify-before-act: when product/design/stack intent is missing

    line 33
  5. Distinctive:

    You do not need a manual sync command: Every HeyEddi skill tool call runs auto-sync first:

    line 38
  6. Very specific:

    If .heyeddi/docs/intake/skill-routing.json exists, follow route order.

    line 64
  7. Distinctive:

    When you have finished the user's request for this skill (not after every tool call or subagent phase), suggest what to run next:

    line 82
  8. Very specific:

    Add --route /path if you worked a specific route.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

HeyEddi

The router. Invoke @heyeddi. @heyeddi-orchestrator is a deprecated alias for this skill.

Routes work to the right @skill, refreshes .heyeddi/, and keeps product, UX, and design pillars in sync.

Always on as the router bookend for every chat. See reference/always-on.md and hub docs/always-on-skills.md.

When to use

  • Every session start on a HeyEddi project (.heyeddi/ present or greenfield app request)
  • User asks "what skills do we have?" or "which skill should handle this?"
  • Before a multi-step pipeline (intake → scaffold → design → handoff → QA)
  • Design / look / polish: @taste-penpot first (one pass, tokens), then @heyeddi-design to record product context and hand off. Do not let @heyeddi-design invent a second look.
  • Any time one pillar runs: bookend with load_workflow_context / append_pillar_opinion
  • After @heyeddi-intake: confirm skill-routing.json before downstream work

Always-on siblings (every chat)

After routing, enforce:

  1. @heyeddi-setup prefs gate (verify_setup --check) before git/CI/commit/push or agent autonomy — incomplete prefs fail those actions; route setup until pass (reference/setup-always-on.md on that skill)
  2. @engineering-excellence plan gate before coding; change gate (audit_engineering --check) after edits — errors fail; warns advisory
  3. Prose anti-slop when copy or .heyeddi docs change (verify_prose --check)
  4. Clarify-before-act when product/design/stack intent is missing
  5. Host surfaces — prefer this session's native plan / data / visual tools when listed; degrade to .heyeddi / scripts otherwise (reference/host-surfaces.md)

Automatic .heyeddi/ upkeep

You do not need a manual sync command. Every HeyEddi skill tool call runs auto-sync first:

  1. Refreshes .heyeddi/skills-index.{json,md} when missing

Reinstall skills (npx skills add) and keep working: the next @heyeddi-intake, @heyeddi-product, or orchestrator tool updates .heyeddi/ automatically.

Optional explicit full sync (includes workflow scaffold): sync --project-root .

Cross-pillar sync (mandatory for product · UX · design)

Read reference/cross-pillar-workflow.md.

init_workflow_sync                    (once per project)
load_workflow_context --route /path   (start of pillar session)
… @heyeddi-product | @ux-flow-auditor | @heyeddi-design work …
append_pillar_opinion --pillar …      (end: triggers sibling opinions)

Skill discovery pipeline

load_catalog / suggest_skills   → auto-sync runs first
read one SKILL.md               → follow that skill's pipeline

If .heyeddi/docs/intake/skill-routing.json exists, follow route order.

Tools

ScriptPurpose
(auto)Every tool: refresh index when missing
sync.pyOptional full sync + workflow scaffold
write_skills_index.pyScan → .heyeddi/skills-index.*
load_catalog.pyRead cached index
suggest_skills.pyRank skills for a prompt
suggest_next_skill.pyNext @skill + command after any skill finishes
init_workflow_sync.pyScaffold .heyeddi/docs/workflow/
load_workflow_context.pySibling opinions + checklist for route
append_pillar_opinion.pyLog opinion; request UX/design/product response

When the task is complete: suggest next skills

When you have finished the user's request for this skill (not after every tool call or subagent phase), suggest what to run next:

  1. Run:

    python .agents/skills/heyeddi/scripts/suggest_next_skill.py --current-skill heyeddi --project-root .

    Add --route /path if you worked a specific route.

  2. Include the script's ### Next step block in your final reply. The user copies the Prompt line into chat (e.g. @heyeddi-design craft /settings).

Pass --mode shape (or craft, audit, etc.) when you know which sub-command just finished.

See @heyeddi → reference/next-skill-handoff.md.

Related

  • @heyeddi-product · @ux-flow-auditor · @heyeddi-design: three pillars
  • @heyeddi-setup: always-on prefs hard gate (verify_setup --check)
  • @engineering-excellence: always-on plan + change gates
  • @heyeddi-intake: upstream intake
  • reference/host-surfaces.md: prefer host plan/data/visual tools; portable degrade
  • reference/next-skill-handoff.md: next-skill block when a pipeline task completes
  • docs/cross-pillar-workflow.md: hub summary
  • docs/always-on-skills.md: hub always-on policy

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.