simplify-and-harden
Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding task is complete in a general agent session and you want a bounded quality and security sweep before signaling done. For CI pipeline execution, use simplify-and-harden-ci.
55
62%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugin/skills/simplify-and-harden/SKILL.mdQuality
Discovery
85%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 strong description that clearly defines its niche as a post-completion code review skill for general agent sessions. It effectively communicates what it does (simplify, harden, micro-documentation passes) and when to use it, and even disambiguates from a related CI-focused skill. The main weakness is that trigger terms lean toward internal/technical vocabulary rather than natural user language.
Suggestions
Add more natural user-facing trigger terms such as 'code review', 'clean up code', 'refactor', or 'security check' to improve discoverability when users phrase requests informally.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists three specific concrete actions: 'simplify', 'harden', and 'micro-documentation passes on non-trivial code changes'. These are distinct, named operations that describe what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (simplify, harden, and micro-documentation passes on non-trivial code changes) and 'when' (when a coding task is complete and you want a bounded quality/security sweep before signaling done). Also includes a disambiguation clause pointing to the CI variant. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'self-review', 'coding agents', 'quality and security sweep', 'code changes', but misses common natural user phrases like 'review my code', 'clean up', 'refactor', or 'code review'. The terms lean more toward internal/technical jargon than what users would naturally say. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: post-completion self-review for coding agents in general agent sessions. The explicit disambiguation from 'simplify-and-harden-ci' for CI pipelines further reduces conflict risk with related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
39%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has a well-thought-out workflow with clear sequencing and validation checkpoints, but it is severely undermined by extreme verbosity. At 500+ lines, it includes extensive philosophical rationale, design decisions, future considerations, agent compatibility lists, and a massive output schema that should either be in separate files or omitted entirely. The content explains far more than it instructs, violating the principle that skills should assume Claude's intelligence and add only what Claude doesn't already know.
Suggestions
Cut the content by 60-70%: remove 'Rationale and Philosophy', 'Design Decisions', 'Future Considerations', 'Agent Compatibility', and the metadata table. These explain concepts Claude doesn't need explained.
Move the full YAML output schema and configuration example to separate bundle files (e.g., OUTPUT_SCHEMA.md and CONFIG.md) and reference them with one-line links.
Replace the pseudocode integration example with either a real executable hook or remove it entirely — the prompt-based integration snippet is the actionable part.
Consolidate the Simplify and Harden checklists into tighter bullet points with direct imperatives rather than rhetorical questions (e.g., 'Remove unused imports' instead of 'Did I leave behind unused imports?').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~500+ lines. Extensive sections explain rationale, philosophy, design decisions, and agent compatibility that Claude already understands or doesn't need. The 'Rationale and Philosophy' section, 'Design Decisions' section, 'Agent Compatibility' list, and 'Future Considerations' are all unnecessary padding. The full YAML output schema example alone is ~80 lines. Much of this content describes concepts rather than instructs. | 1 / 3 |
Actionability | The skill provides concrete checklists for simplify/harden passes and a clear prompt-based integration snippet, but the core integration code is pseudocode (not executable), the configuration example is hypothetical ('adapt path to your agent's config format'), and there are no real executable scripts or commands. The review checklists are actionable but expressed as questions rather than direct instructions. | 2 / 3 |
Workflow Clarity | The three-pass workflow (Simplify → Harden → Document) is clearly sequenced with explicit validation checkpoints. The Refactor Stop Hook provides a concrete feedback loop with approve/reject/skip options. Budget limits serve as explicit constraints. The trigger conditions and scope constraints are well-defined with clear non-trivial change definitions. | 3 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no bundle files to support it. References to 'references/agent-context-snippets.md' and 'simplify-and-harden-ci' exist but no bundle files are provided. The massive YAML output schema, full configuration example, design decisions, and agent compatibility sections should be in separate reference files. Everything is inlined into one enormous document. | 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (527 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- pskoett/pskoett-ai-skills
- Commit
f6c5d7b
- 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.