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.

A highly actionable, well-structured code-quality skill with explicit workflow sequencing and strong validation feedback loops, backed by real bundle files. Minor redundancy across sections is the only thing keeping conciseness from the top anchor.

Dimension	Reasoning	Score
Conciseness	Dense, rule-based prose that assumes competence and avoids explaining basic concepts, but the no-new/old/v2-junk-paths rule recurs across Non-Negotiable Outcomes, Required Workflow, Creation Gate, and Reuse Decision, creating minor redundancy.	4 / 5
Actionability	Provides concrete executable commands and paths: `rg` searches over named directories, the exact audit invocation `node .codex/skills/ipollowork-maintainable-code/scripts/audit-changes.mjs`, and specific path-guard and owner locations.	5 / 5
Workflow Clarity	The nine-step Required Workflow is explicitly sequenced with validation checkpoints (tests at step 7, the audit script at step 8, "Resolve every error" at step 9) plus a per-risk Verification section providing feedback loops for a batch/destructive-relevant code-change skill.	5 / 5
Progressive Disclosure	Body is well-sectioned and points to real one-level-deep resources (references/repository-boundaries.md and scripts/audit-changes.mjs, both present) clearly signaled in the workflow; some inlined rule tables are appropriately kept inline, with only minor organization gaps.	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, concrete description that clearly states both the skill's purpose and its triggers, anchored to a specific product gate. Trigger phrasing leans on action enumeration rather than natural user language, leaving minor room for improvement.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and objects ("creates, edits, deletes, or refactors application code, server code, packages, scripts, tests, dependencies, schemas, routes, UI"; "Reuse existing code before creating files"; "audit the current change before completion") with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ("Mandatory iPolloWork code-change gate for modern, minimal, performant, reuse-first implementation") and when ("Use whenever AI creates, edits, deletes, or refactors...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	"Use whenever AI creates, edits, deletes, or refactors ... code, packages, scripts, tests, dependencies, schemas, routes, UI" gives good keyword coverage of action verbs and object types, but enumerates actions rather than mirroring the natural phrases a user would say.	4 / 5
Distinctiveness Conflict Risk	The "Mandatory iPolloWork code-change gate" framing carves a distinct niche, but the broad code-quality category could overlap with other general maintainability 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: 52934c1

Reviewed: about 14 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.