agentsclimarketplace

Lint microtask

Skill exchanet/method_enterprise_builder_planning/agents/antigravity/.agent/skills/lint-microtask

πŸ—οΈ Universal 8-phase methodology for planning and building enterprise-grade, mission-critical software with AI coding agents. Supports Cursor AI, Claude Code, Kimi Code, Windsurf & Google Antigravity. Includes ADR validator, microtask linter & CI/CD templates. β‰₯99% test coverage. MIT.

Install
npx -y skills add exchanet/method_enterprise_builder_planning --skill lint-microtask

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Validate that a code file complies with the ≀50 effective lines micro-task rule

SKILL.md

2.2 KB, as published. Nobody here has run it

Skill: Lint Microtask

Purpose

Validate that a source code file complies with the ≀50 effective lines micro-task constraint. "Effective lines" excludes blank lines, comment-only lines, and import/using lines.

When to use

  • After implementing any micro-task in Phase 4
  • During the Check step of the PDCA-T cycle (Plan β†’ Do β†’ Check β†’ Act β†’ Test)
  • Before marking a micro-task as complete
  • When a file appears to exceed the 50-line budget

How to run

# Single file
node packs/enterprise-microtask-planner-pack/validators/microtask-linter/src/index.ts \
  --task=src/payments/domain/money.ts

# All files in a directory
node packs/enterprise-microtask-planner-pack/validators/microtask-linter/src/index.ts \
  --dir=src/payments/ --recursive

# Custom line limit
node packs/enterprise-microtask-planner-pack/validators/microtask-linter/src/index.ts \
  --task=src/file.ts --max-lines=40

Supported languages

  • TypeScript (.ts, .tsx)
  • JavaScript (.js, .mjs, .cjs)
  • Python (.py)

Output interpretation

PASS:

βœ“ src/payments/domain/money.ts β€” PASS (38 effective lines)

FAIL with split suggestions:

βœ— src/payments/application/authorize-payment.ts β€” FAIL (67 effective lines > 50)
  Breakdown: 89 total | 67 code | 12 comments | 8 imports | 2 blank

  Suggested split (3 units):
    β”œβ”€β”€ extract: unit-1()  [lines 1–28]    ~22 effective lines
    β”œβ”€β”€ extract: unit-2()  [lines 29–55]   ~24 effective lines
    └── extract: unit-3()  [lines 56–89]   ~21 effective lines

  Result: 3 micro-tasks of ~22 lines each

Action on FAIL

  1. Review the split suggestions
  2. Extract each suggested unit into its own file
  3. Re-run the linter on each new file to confirm all pass
  4. Update the micro-task backlog to reflect the split
  5. Continue with the Act step of PDCA-T

Gate rule

A micro-task that exceeds 50 effective lines cannot be marked as complete until it is split.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.