code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

28%

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 ./skills/code-refactoring-context-restore/SKILL.md

Quality

Content

35%

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

The content is an over-padded, buzzword-heavy overview whose code examples are non-executable pseudocode and whose workflows lack validation. It functions more as a concept brief than actionable guidance.

Suggestions

Strip explanatory prose and buzzwords (Role Statement, Context Overview, Future Roadmap) and keep only instructions Claude would not already know.

Replace pseudocode with executable, self-contained examples or reference a real, available tool/library instead of undefined helpers and a hypothetical 'context-restore' CLI.

Add explicit validation/checkpoint steps to the restore and merge workflows (e.g. verify context signatures, confirm token budget, re-validate on failure before proceeding).

Dimension	Reasoning	Score
Conciseness	The body is padded with concept explanations and buzzwords ('sophisticated memory management system designed to...', 'Expert Context Restoration Specialist', 'quantum-inspired vector search algorithms') that add no actionable value and restate things Claude already knows.	1 / 3
Actionability	The Python blocks are pseudocode calling undefined helpers (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components, load_component, estimate_tokens) and the bash examples invoke an unverified 'context-restore' CLI, so guidance is present but not executable or copy-paste ready.	2 / 3
Workflow Clarity	Workflows 1 and 2 list sequenced steps, but neither includes validation checkpoints or feedback loops despite restore/merge being risky state-changing operations, which caps clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	The 175-line body is a single monolithic file with no bundle files or external references, and content that would benefit from being split (advanced strategies, integration patterns, roadmap) is all inline, though sections are reasonably headed.	2 / 3
	Total	7 / 12 Passed

Description

22%

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 little more than a restated skill name wrapped in a 'Use when' clause: it gives a trigger but no concrete capabilities. It reads as auto-generated filler rather than a clear, action-oriented statement.

Suggestions

Add concrete actions the skill performs, e.g. 'Recovers, ranks, and rehydrates project context from a vector store within a token budget.'

Replace the awkward 'context restore' phrasing with natural terms a user would say, such as 'restore context', 'resume a project', or 'reload conversation history'.

State both what the skill does and when to use it in one sentence, e.g. 'Rehydrates prior project context from semantic memory for long-running multi-agent workflows. Use when resuming a paused project or reconstructing lost conversation state.'

Dimension	Reasoning	Score
Specificity	The description 'Use when working with code refactoring context restore' names a domain but lists no concrete actions or capabilities; it is effectively a trigger phrase with the skill's name restated.	1 / 3
Completeness	It provides a 'when' trigger but no statement of what the skill does, matching the anchor for missing 'what'; the explicit Use-when clause prevents going below 1 but the absent 'what' caps it at 1.	1 / 3
Trigger Term Quality	'code refactoring' is a natural user term, but 'context restore' is awkward jargon (vs. 'restore context') and common variations are missing, so it sits at the middle anchor.	2 / 3
Distinctiveness Conflict Risk	The phrase points at a narrow niche, but the generic wording and absence of distinct triggers mean it could still overlap with general refactoring or memory skills.	2 / 3
	Total	6 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/code-refactoring-context-restore/SKILL.md
Commit: e63f7dd

Reviewed: about 5 hours 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.