harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
73
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/harden/SKILL.mdQuality
Discovery
92%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a well-crafted skill description that clearly communicates its purpose and includes explicit trigger guidance. It lists concrete capabilities and provides a strong 'Use when...' clause with natural user language. The only minor weakness is potential overlap with general code quality or testing skills due to broad terms like 'production-ready' and 'edge cases'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: error handling, i18n support, text overflow handling, and edge case management. Also mentions making interfaces 'production-ready' and 'robust', which are concrete goals. | 3 / 3 |
Completeness | Clearly answers both 'what' (improve resilience through error handling, i18n, text overflow, edge cases) and 'when' with an explicit 'Use when...' clause listing specific trigger scenarios like hardening, production-readiness, error states, overflow, and i18n issues. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would say: 'harden', 'production-ready', 'handle edge cases', 'error states', 'overflow', 'i18n issues'. These cover a good range of how users would naturally phrase requests for this type of work. | 3 / 3 |
Distinctiveness Conflict Risk | While the combination of error handling + i18n + overflow + edge cases is somewhat distinctive, individual terms like 'error handling' or 'edge cases' could overlap with general code quality or testing skills. The focus on UI/interface resilience helps narrow it, but 'production-ready' is broad enough to potentially conflict with other skills. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is comprehensive and provides genuinely useful, executable code examples across many hardening dimensions, earning high actionability marks. However, it is far too verbose — much of the content covers standard web development practices Claude already knows, and the monolithic structure with no progressive disclosure wastes significant context window space. The workflow is loosely structured without proper validation checkpoints between hardening steps.
Suggestions
Split the 8+ hardening dimensions into separate referenced files (e.g., I18N.md, ERROR_HANDLING.md, ACCESSIBILITY.md) and keep SKILL.md as a concise overview with navigation links.
Remove explanations of concepts Claude already knows (e.g., what UTF-8 is, that server-side validation is needed, basic CSS overflow properties) and focus only on project-specific patterns or non-obvious techniques.
Add explicit validation checkpoints in the workflow, such as 'After applying text overflow fixes, verify by testing with 100+ character strings before moving to i18n hardening.'
Reduce the NEVER list and general advice sections — these are common knowledge for Claude and consume tokens without adding unique value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~300+ lines, covering many topics Claude already understands well (CSS overflow, basic form validation, accessibility fundamentals, debouncing). Much of this is general web development knowledge that doesn't need to be spelled out in such detail. The NEVER list and many bullet-point lists restate common sense for an LLM. | 1 / 3 |
Actionability | The skill provides concrete, executable code examples throughout — CSS snippets for truncation, JSX for error states, JavaScript for Intl API usage, HTML for input constraints, and CSS for reduced motion. These are copy-paste ready and specific. | 3 / 3 |
Workflow Clarity | The skill has a loose workflow (Assess → Harden across dimensions → Verify), but lacks explicit validation checkpoints between steps. The 'Verify Hardening' section is a checklist but doesn't include feedback loops for fixing issues found during verification. For a skill involving potentially destructive UI changes, this is insufficient. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no references to external files. The content covers at least 8 major sub-topics (text overflow, i18n, error handling, edge cases, input validation, accessibility, performance, testing) that could each be their own referenced document. Everything is inlined, making it overwhelming and token-expensive. | 1 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- pbakaus/impeccable
- Commit
3a4fc70
- Reviewed
Table of Contents
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.