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.

Quality

62%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/simplify-and-harden/SKILL.md

Quality

Content

39%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill defines a thoughtful and well-structured three-pass review workflow with strong validation checkpoints and clear scope constraints. However, it is severely over-long for a SKILL.md, embedding extensive rationale, design philosophy, compatibility matrices, and configuration examples that should live in separate referenced files. The core actionable content (the three passes with their checklists and the refactor stop hook) is buried in verbose surrounding material that wastes context window tokens.

Suggestions

Extract Design Decisions, Future Considerations, Agent Compatibility, and Integration Notes into separate referenced files (e.g., DESIGN.md, INTEGRATION.md) and replace with one-line links in SKILL.md.

Move the full output schema example and configuration example into a REFERENCE.md file, keeping only a minimal schema summary inline.

Remove explanatory content Claude already knows (e.g., why budgets prevent unbounded refactoring, why documentation helps reviewers) — these are self-evident to an LLM agent.

Trim the install/metadata section significantly — the metadata table and multiple install variants add ~30 lines of low-value content for the agent's actual task execution.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Includes extensive philosophical rationale ('Design Decisions'), agent compatibility lists, future considerations, and explanations of concepts Claude already understands (why post-completion review matters, why budgets exist). The metadata table, install instructions, and agent compatibility sections add significant token overhead without actionable value for the skill's core purpose.	1 / 3
Actionability	The review checklists for simplify and harden passes are concrete and useful, and the prompt-based integration snippet is copy-paste ready. However, the programmatic integration code is pseudocode for a hypothetical API, the output schema is an example rather than a validated spec, and much of the content describes philosophy rather than providing executable steps.	2 / 3
Workflow Clarity	The three-pass workflow (Simplify → Harden → Document) is clearly sequenced with explicit validation checkpoints: the Refactor Stop Hook requires human approval before structural changes, budget limits enforce stopping conditions, and the output schema captures applied/flagged/skipped states. The feedback loop for refactor proposals (approve/reject/show diff/skip all) is well-defined.	3 / 3
Progressive Disclosure	The skill is a monolithic wall of text with no bundle files to offload content to. The design decisions, future considerations, agent compatibility matrix, full output schema example, configuration example, and integration notes could all be in separate referenced files. The reference to 'references/agent-context-snippets.md' and 'simplify-and-harden-ci' suggests supporting files should exist but no bundle is provided, and the SKILL.md itself doesn't split content appropriately.	1 / 3
	Total	7 / 12 Passed

Description

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 well-structured description that clearly defines what the skill does (simplify, harden, micro-documentation passes), when to use it (post-completion of coding tasks in general agent sessions), and even disambiguates from a related CI-specific skill. Its main weakness is that trigger terms lean toward internal/technical vocabulary rather than natural user language, which could reduce discoverability when users phrase requests more casually.

Suggestions

Add more natural trigger terms users might say, such as 'review my code', 'clean up code', 'security review', 'code quality check', or 'refactor before merging'.

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 in a general agent session and you want a bounded quality/security sweep). It even distinguishes from a related skill (simplify-and-harden-ci) for CI contexts.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'coding agents', 'quality and security sweep', 'self-review', and 'code changes', but these are somewhat specialized. Common user phrases like 'review my code', 'clean up', 'refactor', or 'security check' are missing. The language leans more toward internal/technical jargon than natural user phrasing.	2 / 3
Distinctiveness Conflict Risk	Highly distinctive: it explicitly scopes itself to post-completion self-review in general agent sessions and differentiates from the CI pipeline variant by name. The combination of 'post-completion', 'coding agents', and the three named passes creates a clear niche unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

90%

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 — 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: 20e64ce

Reviewed: 15 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.