Pre-write skill violation audit. Checks planned code against loaded skill anti-patterns before any file write. Use when writing Flutter/Dart code, editing SKILL.md files, or generating any code where project skills are active. Load as composite alongside other skills. When a violation is detected and Auto-fixed: YES, also load +common/common-learning-log to record the mistake.
63
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/common/common-feedback-reporter/SKILL.mdQuality
Discovery
75%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 functionally complete with clear 'what' and 'when' clauses, and occupies a distinct niche that minimizes conflict risk. However, the specificity of concrete actions could be improved (what exactly does the audit check or produce?), and the trigger terms lean technical rather than matching natural user language. The conditional loading instruction for the learning log is a nice operational detail.
Suggestions
Add more specific concrete actions, e.g., 'Scans planned code for banned patterns, flags violations with explanations, and auto-fixes correctable issues' to improve specificity.
Consider whether trigger terms like 'violation audit' and 'composite' match how users would naturally phrase requests — adding terms like 'check code quality', 'lint', or 'review before writing' could improve discoverability.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (pre-write skill violation audit) and some actions (checks planned code against anti-patterns, auto-fixes), but doesn't list multiple specific concrete actions beyond 'checks' and 'load as composite'. The actual audit actions are somewhat vague. | 2 / 3 |
Completeness | Clearly answers both 'what' (checks planned code against loaded skill anti-patterns before any file write) and 'when' (when writing Flutter/Dart code, editing SKILL.md files, or generating any code where project skills are active). Includes explicit trigger guidance and even conditional loading instructions. | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Flutter/Dart code', 'SKILL.md files', 'anti-patterns', 'code', and 'project skills', but the trigger terms are somewhat niche and technical. Terms like 'violation audit' and 'composite' are not things users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | This is a very specific niche — a pre-write audit against skill anti-patterns — that is unlikely to conflict with other skills. The description clearly distinguishes it as a meta-skill that operates before file writes, and the composite loading instruction further clarifies its role. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted meta-skill with strong actionability and workflow clarity. The decision tree, violation report template, and anti-patterns are concrete and immediately usable. Minor weaknesses include slight redundancy between the numbered steps and the ASCII flow diagram, and the referenced bundle file (`references/violation-examples.md`) cannot be verified since no bundle was provided.
Suggestions
Remove the ASCII detection flow diagram since it duplicates the numbered checkpoint steps — or consolidate them into one representation to improve conciseness.
Ensure the referenced `references/violation-examples.md` file exists in the bundle to support the progressive disclosure reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient and avoids explaining concepts Claude already knows. However, some sections are slightly verbose — the Root Cause table and Anti-Patterns list could be tightened, and the detection flow ASCII diagram partially duplicates the numbered checkpoint steps above it. | 2 / 3 |
Actionability | Provides a concrete, structured violation report format with exact field names, a clear decision tree for when to act, specific examples (Flutter hardcoded colors, React class components, SKILL.md line limits), and explicit anti-patterns. The guidance is immediately actionable without ambiguity. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: check extension → audit against rules → report if violation → fix immediately. Includes a pre-completion catch-all checkpoint ('Did I write code? Did I audit skills?') as a validation/feedback loop. Anti-patterns section explicitly addresses common workflow shortcuts that could be skipped. | 3 / 3 |
Progressive Disclosure | References `references/violation-examples.md` for more examples, which is good progressive disclosure. However, no bundle files are provided, so the reference is unverifiable. The main content is well-structured with clear sections but the violation report format and root cause guide are inline when they could potentially be extracted to a reference file to keep the overview leaner. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
556618c
Table of Contents
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.