code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

31%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/code-refactoring-context-restore/SKILL.md

The canonical home for this skill is context-management-context-restore in sickn33/agentic-awesome-skills

Quality

Content

38%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.

The content is broad and padded with conceptual filler and a speculative roadmap rather than lean, executable guidance. Code examples are non-runnable pseudocode, workflows lack validation checkpoints, and the single file reference points to a file that does not exist in the bundle.

Suggestions

Trim conceptual explanations and remove the 'Future Roadmap' section; assume Claude knows what embeddings, caching, and vector search are.

Make code examples executable by defining or importing the helper functions they call, or explicitly mark them as illustrative patterns with concrete implementation pointers.

Add validation checkpoints to the context-merge/rehydration workflows (e.g. verify signature, check version compatibility, retry on conflict) and either create the referenced implementation-playbook.md or remove the dangling reference.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, padding sections with generic explanations of concepts Claude already knows (e.g. 'Utilize multi-dimensional embedding models', 'Implement efficient caching mechanisms') and listing speculative roadmap items that add no actionable value.	2 / 5
Actionability	It includes several Python snippets, but they reference undefined functions and classes (VectorDatabase, calculate_composite_score, prioritize_components, estimate_tokens, load_component) and an unverifiable CLI 'context-restore', making them illustrative pseudocode rather than executable guidance.	3 / 5
Workflow Clarity	The two reference workflows are numbered but lack validation checkpoints, and operations that modify/merge context are destructive/batch in nature without any verify-then-retry feedback loop, capping clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	The body is a ~170-line monolith with sections (strategies, workflows, integration patterns, roadmap) that clearly belong in separate files; it references a non-existent 'resources/implementation-playbook.md' and no references/ directory is present, so navigation is broken and structure is inlined.	2 / 5
	Total	10 / 20 Passed

Description

25%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.

The description is essentially a restatement of the skill name with a single generic trigger clause and no statement of capabilities. It fails to answer what the skill does and uses an unnatural trigger phrase, making it both vague and hard to distinguish.

Suggestions

Rewrite as a concrete capability statement, e.g. 'Rehydrates and reconstructs project context (decisions, architecture, recent work) across multi-agent workflows using semantic vector retrieval.'

Replace the unnatural 'code refactoring context restore' trigger with phrases users would actually say, such as 'context restoration', 'memory rehydration', or 'recovering project context after a context reset'.

Keep the explicit 'Use when...' clause but pair it with the what-it-does sentence so both 'what' and 'when' are clearly answered.

Dimension	Reasoning	Score
Specificity	The description only restates the skill name ('Use when working with code refactoring context restore') with no concrete actions enumerated; it names the domain but offers minimal, generic action language.	2 / 5
Completeness	It provides a weak 'when' clause ('Use when working with...') but entirely lacks a 'what' describing what the skill actually does, so the what/when pair is incomplete.	2 / 5
Trigger Term Quality	'code refactoring context restore' is awkward jargon unlikely to be a phrase a user would naturally say, and no synonyms or natural variations are present.	2 / 5
Distinctiveness Conflict Risk	'code refactoring' is a very broad domain that overlaps heavily with general coding and refactoring skills, giving high conflict risk with little to distinguish it.	2 / 5
	Total	8 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/code-refactoring-context-restore/SKILL.md
Commit: 57c135b

Reviewed: 2 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.