skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
heyeddi-com/heyeddi-skills100 installs

engineering-excellence

ALWAYS-ON: audits plans and code for KISS, YAGNI, DRY, SOLID, and testability; maintains .heyeddi/docs/engineering/. Use on every chat that plans or changes code, before merge, refactor, ADRs, or reuse-catalog work. Not for visual UX (ux-flow-auditor) or full CI (pre-merge-gate includes this audit).

How do I install this agent skill?

npx skills add https://github.com/heyeddi-com/heyeddi-skills --skill engineering-excellence
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill is a software engineering audit utility that manages project documentation and performs static analysis on codebase files. It includes a hardened command execution utility and processes local source code, which introduces a minor surface for indirect prompt injection from audited content.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Engineering Excellence

Simple solutions that scale: documented so the next agent does not over-build or repeat work.

Always on for every chat that plans or changes code. See reference/engineering-always-on.md and hub docs/always-on-skills.md.

All artifacts go under .heyeddi/docs/: never repo root.

When to use

  • Every chat that proposes an implementation plan or edits code
  • After a feature ships: capture how it works
  • Before adding abstractions: check reuse catalog
  • Refactor / architecture review: KISS, YAGNI, SOLID
  • User asks: "don't over-engineer", "document the system", "engineering notes"

Subagents (default)

See reference/subagents.md. Delegate audit_engineering.py, check_engineering_plan.py, and doc init to Task shell. Main chat interprets findings and updates living docs.

Pipeline

check_engineering_plan  → plan gate (docs + optional plan smells)
init_engineering_docs   → .heyeddi/docs/engineering/{architecture,reuse-catalog,decisions}.md
implement / refactor
audit_engineering       → .heyeddi/docs/engineering-audit-<date>.md (--check = errors fail)
append_decision         → ADR when trade-off is non-obvious

Instructions

  1. Plan gate (every chat before coding): python scripts/check_engineering_plan.py --project-root <root> --check (add --plan-file when a written plan exists).
  2. First time in project: python scripts/init_engineering_docs.py --project-root <root>
  3. While coding: read reuse-catalog.md before new components/composables/services
  4. After meaningful change: update architecture.md module map and add reuse rows
  5. Non-obvious trade-off: append_decision.py --title … --context … --decision …
  6. Change gate (every chat after edits): audit_engineering.py --check (errors fail; warns advisory). Use --strict only when the user asks for warn-blocking.

Principles (how we enforce)

PrincipleSkill behavior
KISSWarn on oversized files; error when extreme; prefer flat modules
YAGNIFlag abstraction names without clear reuse; plan gate errors on new Factory/Manager without reuse cite
DRYMaintain reuse-catalog.md; chain @no-duplicate-ui for UI
SOLIDWarn on fat routers; views thin, services fat
TestableNote views missing smoke specs

.heyeddi/ outputs

PathPurpose
.heyeddi/docs/engineering/architecture.mdSystem map, data flow, boundaries
.heyeddi/docs/engineering/reuse-catalog.mdWhat exists: do not rebuild
.heyeddi/docs/engineering/decisions.mdEngineering ADRs (not design log)
.heyeddi/docs/engineering-audit-<date>.mdPoint-in-time audit report

Design decisions stay in .heyeddi/design.md Decision log: do not mix.

Chain

  • @heyeddi: always-on router before this skill when the task is ambiguous
  • @project-engineering: scaffold first
  • @composable-patterns / @backend-type-bridger: after architecture notes exist
  • @pre-merge-gate: final CI; includes audit_engineering --check

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 engineering-excellence --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. @visual-auditor review and fix /settings).

Pass --mode audit when the change-gate audit just finished.

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

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/heyeddi-com/heyeddi-skills/engineering-excellence">View engineering-excellence on skillZs</a>