cycosoft/Eyas / .agents/skills/efficiency-tiers
efficiency-tiers
VerifiedDefinitions of development efficiency tiers and work streams, detailing mandatory verification gates and test bypass rules for diagnostic exploration vs production commits.
Reusable Skill: Efficiency Tiers & Work Streams
Overview
This skill defines the four operational efficiency tiers, outlining specific verification requirements and bypass rules for diagnostic probes, cosmetic adjustments, targeted bug fixes, and final integration check-ins.
When to Use
- Trigger when determining the level of verification required for a current development task.
- Trigger when applying zero-gate diagnostic logging during debugging sessions.
Instructions
Tier 0: Diagnostic / Temporary Logging (Zero-Gate Stream)
- Definition: Adding temporary
console.logstatements, print traces, or debug probes requested by the user to diagnose problems. - Workflow: Rapid Direct Edit -> Direct Run/Manual Verification.
- Verification/Bypass Rules: Completely bypass test writing (no BDD required), linter rules, formatting checks, and file quality-gate rules (e.g. ignore maximum line counts or style enforcement). Never perform secondary cleanups, file refactoring, or split logic when adding temporary debug logging.
Tier 1: Visual/Cosmetic Iteration
- Definition: Changes to CSS, labels, or UI layout that do not touch application logic or IPC.
- Workflow: Rapid Edit -> Manual/User Verification.
- Verification: Skip full test suites. Run only
npx eslint <file> --fixlocally. Batch full verification at the end of the task.
Tier 2: Targeted Functional Fixes
- Definition: Logic changes in a single module or component.
- Workflow: BDD (Targeted Test) -> Code -> Targeted Verification.
- Verification: Run
npx vitest <file>ornpx playwright test <file>. Skip project-wide checks until the feature is stable.
Tier 3: Final Integration (The "Check-In" Gate)
- Definition: Completion of a feature branch or complex refactor.
- Workflow: Full project validation.
- Verification: Mandatory
npm run checkbefore concluding the session or task.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |