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

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

50%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.

Operationally rich and well-sequenced, with concrete checklists, action categories, and a copy-paste output schema, but noticeably verbose and missing a post-change verification step. The one signaled external reference points to a file absent from the bundle.

Suggestions

Trim or move 'Rationale and Philosophy', 'Design Decisions', 'Future Considerations', and the agent-compatibility roster into a separate references file (or delete) to cut the body substantially; the duplicated prompt-injection and configuration blocks should appear once.

Add an explicit validation step after the three passes — e.g. 'run the test suite / typecheck and only signal done if it passes' — so the code-modifying workflow has a real verification checkpoint.

Either create references/agent-context-snippets.md or remove the pointer to it, so the single signaled external reference actually resolves.

Dimension	Reasoning	Score
Conciseness	At ~519 lines the body has several padded sections — 'Rationale and Philosophy', 'Design Decisions', 'Future Considerations', and an 'Agent Compatibility' roster of ~12 tools — plus duplicated prompt-injection/configuration blocks, matching 'noticeably verbose; several unnecessary explanations or padded sections'; it is not a 3 because the excess is substantial rather than incidental.	2 / 5
Actionability	Concrete checklists, action categories (cosmetic vs refactor, patch vs security refactor), stop-hook example dialogs, a copy-paste YAML output schema, a config example, and an integration snippet give mostly executable guidance; it stays at 4 rather than 5 because some checklist items are directional ('Can any nested conditionals be flattened?') rather than literal commands.	4 / 5
Workflow Clarity	The three passes (simplify, harden, document) are clearly sequenced with checkpoints (mandatory fresh-eyes, refactor stop hook, budget_exceeded flag), but the skill modifies code yet never instructs running tests/verify after changes; per the destructive/batch-operation guidance, missing validation caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	Section structure is clear and one reference is explicitly signaled ('references/agent-context-snippets.md'), but that referenced file does not exist in the bundle and bulk content (full ~100-line YAML schema, full config, compatibility roster) is inlined, fitting 'some structure; references present; content that should be separate is inline'.	3 / 5
	Total	12 / 20 Passed

Description

83%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.

A strong, well-structured description that concretely names its three review passes, gives an explicit 'Use when' trigger, and disambiguates the CI variant. Its only weakness is mild overlap with general code-review/security-review skills and a few missing natural synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain ('coding agents', 'post-completion self-review') and several concrete actions ('runs simplify, harden, and micro-documentation passes on non-trivial code changes', 'bounded quality and security sweep'), matching the 'lists several specific actions; minor gaps' anchor rather than the comprehensive-coverage 5.	4 / 5
Completeness	It explicitly states what it does ('runs simplify, harden, and micro-documentation passes...') and when to use it ('Use when: a coding task is complete... before signaling done') with concrete trigger phrases, matching the anchor that answers both what AND when explicitly; it also disambiguates the CI variant.	5 / 5
Trigger Term Quality	The 'Use when' clause supplies natural phrases ('coding task is complete', 'quality and security sweep', 'before signaling done') plus keywords like simplify/harden; a few common synonyms are missing so it sits just below the comprehensive-coverage 5.	4 / 5
Distinctiveness Conflict Risk	The post-completion, simplify-first/harden posture is a clear niche and it explicitly steers CI usage to a sibling skill, but 'self-review' and 'quality and security sweep' overlap with general code-review/security-review skills, so it is 'mostly distinct; minor overlap risk' rather than minimal.	4 / 5
	Total	17 / 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
skill_md_line_count	SKILL.md is long (520 lines); consider splitting into references/ and linking	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: pskoett/pskoett-ai-skills
Path: .agents/skills/simplify-and-harden/SKILL.md
Commit: 8a71d70

Reviewed: 1 hour 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.