loopx-change-quality

Qualify the exact final diff for a LoopX-managed goal. Use when goal policy enables change_quality_qualification, before a non-trivial delivery or merge, and when producing or repairing an exact-scope quality receipt. The workflow is language-neutral, permits at most one policy-authorized safe-fix pass, and never grants merge or repository authority.

Quality

80%

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

73%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.

The content is a tightly sequenced, validation-rich review workflow with concrete CLI commands and clear feedback loops. Its weaknesses are some philosophical/meta narration that pads the token budget and an opportunity to externalize the long guardrail catalog into a reference file.

Suggestions

Trim or relocate the model shadow-matrix paragraph and the 'guardrail catalog is review guidance, not an output checklist' meta commentary; they describe maintainer behavior rather than reviewer action.

Move the 10-lens guardrail catalog and the Simplify-First rules into a references file (e.g. guardrails.md) referenced one level deep, leaving SKILL.md as a lean overview.

Replace the placeholder '<ignored-or-temporary-result.json>' in the record command with a concrete note on where the result file should live so the command is fully executable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and information-dense, but includes non-actionable framing and meta commentary such as the model shadow-matrix paragraph and 'The guardrail catalog is review guidance, not an Agent output checklist' that could be trimmed, fitting anchor 3 more than anchor 4.	3 / 5
Actionability	Provides concrete, copy-pasteable CLI commands with flags (prepare, record, verify, canary premerge) and explicit stop conditions, giving mostly executable guidance with only minor gaps such as the placeholder result-json path, sitting below the fully comprehensive anchor 5.	4 / 5
Workflow Clarity	Sequences Prepare -> Simplify First -> Safe Fix -> Record -> Premerge -> Completion with explicit validation checkpoints and feedback loops ('After any edit, rerun prepare. The old fingerprint is invalid'; 'Stop before delivery when ... the receipt is missing, invalid, stale'), matching anchor 5 even for this destructive/batch workflow.	5 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-organized with clear section headers and no nested references, but the 10-lens guardrail catalog and simplify rules are long enough that they could be split into a one-level reference file, keeping it below anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is well-constructed: third-person voice, explicit what-and-when with concrete policy-gated triggers, and a distinct niche with low conflict risk. Its main limitation is jargon-heavy trigger terms that could use a few more natural synonyms.

Suggestions

Add a couple of plain-language synonyms (e.g. 'review the final diff before merge') alongside the LoopX-specific terms so users outside the policy vocabulary can still trigger it naturally.

Consider listing one or two more concrete review actions (e.g. 'emit sparse risks and a validation receipt') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names concrete actions such as 'Qualify the exact final diff' and 'producing or repairing an exact-scope quality receipt' plus the bounded safe-fix pass, listing several specific actions with only minor coverage gaps, so it sits above anchor 3 but lacks the exhaustive action list of anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Qualify the exact final diff for a LoopX-managed goal ... permits at most one policy-authorized safe-fix pass ... never grants merge or repository authority') and when ('Use when goal policy enables change_quality_qualification, before a non-trivial delivery or merge, and when producing or repairing an exact-scope quality receipt') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural domain triggers like 'before a non-trivial delivery or merge' and 'producing or repairing an exact-scope quality receipt' with good keyword coverage, though the terms are fairly LoopX-specific jargon and lack synonyms, keeping it below anchor 5.	4 / 5
Distinctiveness Conflict Risk	The LoopX-managed goal and change_quality_qualification policy gating carve a clear niche with distinct triggers and minimal conflict risk against other skills, matching anchor 5.	5 / 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: huangruiteng/CS-Notes
Path: .agents/skills/loopx-change-quality/SKILL.md
Commit: 5d012c4

Reviewed: 3 days 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.