ipollowork-maintainable-code

Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation and clean repository ownership. Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI, or generated-file workflows. Reuse existing code before creating files, keep one source of truth, prevent parallel implementations and junk directories, justify every new file or dependency, and audit the current change before completion.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a high-quality instruction skill: fully actionable with exact paths, commands, and a decision table, and a well-sequenced workflow with explicit validation and error-resolution loops. Its only flaws are minor cross-section rule duplication and some placement detail inlined in SKILL.md that duplicates the boundaries reference.

Suggestions

Deduplicate the abstraction rule (Creation Gate bullet 7 vs. the Reuse Decision closing paragraph) into a single statement so the Creation Gate stays a pure checklist.

Trim the Frontend Rules and Server And Generated Files sections to the rules only and let references/repository-boundaries.md carry the placement map, since both currently state the same owner paths.

Consider moving the Verification By Risk matrix into a reference file so the SKILL.md body stays a lean overview of outcomes, workflow, and gates.

Dimension	Reasoning	Score
Conciseness	The body is dense, declarative, and assumes Claude's competence with zero concept explanation, but rules repeat across sections — 'Do not create a generic abstraction for one caller' (line 47) reappears at line 59, and the junk-path list in Creation Gate overlaps the Required Workflow — so minor trimming is possible.	4 / 5
Actionability	Guidance is fully executable: a runnable audit command ('node .codex/skills/ipollowork-maintainable-code/scripts/audit-changes.mjs'), exact search targets and paths ('apps/server/src/paths.ts', 'apps/app/src/components/ui'), concrete session layouts, and a decision table mapping each situation to a specific action.	5 / 5
Workflow Clarity	The 9-step Required Workflow is clearly sequenced with an explicit validation checkpoint (run the audit script) and an error-recovery feedback loop ('Resolve every error. Fix warnings or give a concrete ownership/performance reason'), reinforced by risk-tiered verification steps and a completion checklist.	5 / 5
Progressive Disclosure	The single reference (references/repository-boundaries.md, verified to exist and one level deep) is clearly signaled with a read-before trigger, and the audit script is properly externalized; however, the Frontend Rules and Server sections inline placement detail that also lives in the reference, a minor duplication of structure.	4 / 5
	Total	18 / 20 Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it is specific, concrete, third-person, and answers what and when explicitly with a broad but actionable trigger set. Its only weaknesses are the absence of a few natural synonym phrases and a trigger scope so wide it could contend with general-purpose coding skills.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'Reuse existing code before creating files', 'keep one source of truth', 'prevent parallel implementations and junk directories', 'justify every new file or dependency', and 'audit the current change before completion' — giving comprehensive, not just minor-gap, coverage.	5 / 5
Completeness	It explicitly answers both 'what' (a code-change gate enforcing modern, minimal, performant, reuse-first implementation and clean ownership) and 'when' ('Use whenever AI creates, edits, deletes, or refactors application code, server code, packages, scripts, tests...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural keyword coverage via 'creates, edits, deletes, or refactors' plus concrete nouns (dependencies, routes, UI, tests, schemas), but common synonym phrasings a user might say — 'code quality', 'maintainable', 'cleanup', 'tech debt' — are absent.	4 / 5
Distinctiveness Conflict Risk	The iPolloWork branding and specific gate framing make it mostly distinct, but 'whenever AI creates, edits, deletes, or refactors' code fires on nearly every code change, creating minor overlap risk with general coding and refactoring skills.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Devin-AXIS/iPolloWork
Path: .codex/skills/ipollowork-maintainable-code/SKILL.md
Commit: dada31d

Reviewed: 13 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.