common-feedback-reporter

Pre-write audit for skill violations: checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart/TS code or editing SKILL.md files with active project skills. Load as composite; on auto-fixed violation, also load +common/common-learning-log.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

82%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 tight, executable contract with a concrete report template, root-cause taxonomy, and a checkpoint-gated workflow, well-supported by real bundle files. Its weak spots are a missing explicit validate/retry feedback loop for batch/destructive writes and references that are signaled conceptually rather than by explicit links.

Suggestions

Add an explicit validate-then-retry feedback loop step for batch/destructive write cases, since workflow_clarity is currently capped by the absence of a concrete re-validation cycle.

Replace the conceptual 'move large examples to references/' pointer with explicit markdown links to references/test-scenarios.md and references/violation-examples.md so navigation is clearly signaled.

Deduplicate the restated report-label sentence that appears in both 'Mandatory execution contract' and 'Anti-Patterns' to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, repeating only the required block labels and root-cause codes without padding concepts; minor redundancy comes from restating the exact report-label sentence twice (sections 'Mandatory execution contract' and 'Anti-Patterns').	4 / 5
Actionability	It provides a fully copy-paste-ready violation block template with exact field labels, a concrete Root Cause code table, and a worked decision tree, giving executable guidance that covers the common cases.	5 / 5
Workflow Clarity	A clear checkpoint sequence (Check -> Audit -> Output violation block -> Fix immediately) with an explicit pre-completion validation checkpoint is present, but it lacks a concrete validate-then-retry feedback loop for the destructive/batch write cases the skill governs.	4 / 5
Progressive Disclosure	The body is a concise overview that points large examples to references/ (test-scenarios.md, violation-examples.md exist and are referenced conceptually), keeping the main file tight; however the references are not linked by explicit markdown paths, so navigation is implied rather than clearly signaled.	4 / 5
	Total	17 / 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 concise, concrete, and explicitly states both what it does and when to use it, with strong trigger terms and a distinct niche. Its main weakness is mild abstraction around 'skill violations' and 'anti-patterns' rather than listing the exact audit behaviors.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'checks planned code against loaded skill anti-patterns', 'before any file write', 'auto-fixed violation' — but 'skill violations' and 'anti-patterns' are somewhat abstract and the exact audit action is implied rather than enumerated.	4 / 5
Completeness	Explicitly answers 'what' (pre-write audit that checks planned code against loaded skill anti-patterns) and 'when' (writing Flutter/Dart/TS code or editing SKILL.md files with active project skills), with a concrete 'Use when...' clause.	5 / 5
Trigger Term Quality	Covers natural trigger phrases ('writing Flutter/Dart/TS code', 'editing SKILL.md files', 'skill violation', 'pre-write audit') plus file extensions, but is missing common user phrasings like 'check my code' or 'review before saving'.	4 / 5
Distinctiveness Conflict Risk	The narrow niche (pre-write violation auditing for Flutter/Dart/TS/SKILL.md against loaded skills) with composite-loading and co-skill coupling is highly distinct and unlikely to trigger for the wrong skill.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: HoangNguyen0403/agent-skills-standard
Path: .github/skills/common/common-feedback-reporter/SKILL.md
Commit: 3bdb7b5

Reviewed: 2 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.