Skip to content
cccskills
FreePublished on GitHub

spark-find-simplifications

Use when a working Spark implementation should be simplified without changing its observed behavior, ownership, compatibility, or public contract.

The English summary is being prepared. Showing the original description.

See how to install

Files included (1)

  • SKILL.md1.7 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Spark simplification search

Simplify only after the behavior and validation baseline are known.

Procedure

  1. Identify the owner, public behavior, compatibility constraints, and tests that establish the current contract.
  2. Start from code-review findings or inspect for duplicate branches, overlapping adapters, zero-semantic wrappers, unused metadata, unnecessary abstractions, dead compatibility paths with explicit exit criteria, and state derived in more than one place.
  3. For each candidate, state its semantic payload. If deleting or inlining it loses no policy, conversion, owner boundary, invariant, or supported compatibility, prefer removal.
  4. Trace polling and opportunistic reconciliation back to the authoritative mutation path. Prefer keeping the owner correct at write time over another cache, scan, or repair loop.
  5. Check collection limits before downstream filtering or skipping for fairness and starvation errors.
  6. Prefer deleting indirection or moving semantics into the existing owner over introducing another framework, package, schema, facade, budget, or exception.
  7. Compare each candidate against production callers and focused validation. Require live call-path evidence before declaring code unreachable.
  8. Recommend the smallest independent simplification and the evidence needed to prove equivalence.

Stop when a simplification would alter serialization, authority, lifecycle, or user-visible behavior without explicit acceptance criteria. Return candidates, evidence, recommendedSlice, validation, and rejectedIdeas.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Use when Spark engineering knowledge must be placed, deduplicated, migrated, or validated across AGENTS, Notes, Roles, Skills, and Workflows.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

Use when adding or updating Spark AI provider models or their compact and preflight metrics, especially baidu-oneapi, Grok, Claude, GPT, DeepSeek, OneAPI, context windows, output budgets, prices, thinking maps, or transports.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

Use when a Spark change needs its authoritative owner, affected boundaries, risks, acceptance criteria, and smallest verifiable slice established before implementation or review.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

Use when a Spark implementation needs an evidence-based review for correctness, ownership, compatibility, failure handling, maintainability, and unnecessary complexity.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

Use when designing a Spark feature or writing or materially revising a design proposal that needs repository-first research, user input on unresolved key choices, and an owner-aligned implementation plan before code changes.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

Use when a running Spark or DSH web service needs real-browser verification — page load, client-plugin boot errors, console errors, failed requests, or onboarding/dialog rendering — with the repository's own Playwright chromium.

The English summary is being prepared. Showing the original description.

zendev-lab/spark2Updated Oct 19, 2026

See all skills by zendev-lab

Report a problem with this skill