code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

35%

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

42%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 presents an elaborate imagined system with pseudocode and conceptual prose rather than executable, token-efficient guidance. Workflows lack validation checkpoints and the single monolithic file should be split into references for the longer sections.

Suggestions

Replace pseudocode with runnable code or remove undefined helper functions, and either verify the 'context-restore' CLI or drop the unverified usage examples.

Add explicit validation/verification steps to the workflows (e.g., verify restored context against the current codebase before proceeding) to support the destructive merge operations described.

Trim the conceptual overview and 'Future Roadmap' padding, and move the eight retrieval strategies and parameter reference into separate files under references/ with one-level-deep links from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, with padded conceptual descriptions ('sophisticated memory management system designed to...'), imagined capability lists, and a buzzword-heavy 'Future Roadmap' ('Quantum-inspired vector search') that add tokens without actionable value.	2 / 5
Actionability	Code blocks look concrete but are pseudocode relying on undefined functions (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components, load_component, estimate_tokens), and the 'context-restore' CLI is unverified, leaving key execution details missing.	3 / 5
Workflow Clarity	Workflows 1 and 2 list sequenced steps but include no validation checkpoints or feedback loops, and operations like context merging and conflict resolution are risky enough to require them, capping the score per the rubric.	3 / 5
Progressive Disclosure	No bundle files exist and the ~175-line body inlines everything (eight retrieval strategies, parameter specs, workflows, roadmap) under section headers; the length exceeds the simple-skill exception and content that belongs in separate reference files is all in SKILL.md.	3 / 5
	Total	11 / 20 Passed

Description

28%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 a minimal trigger-only statement that names a domain but states no capabilities, leaving 'what does this skill do' unanswered. Trigger phrasing is unnatural and would not reliably surface in user requests.

Suggestions

Add a concrete 'what' clause naming specific actions, e.g. 'Recovers and reconstructs project context across multi-agent workflows using semantic vector search and token-budgeted rehydration.'

Rewrite the trigger in natural user language, e.g. 'Use when resuming a long-running project, rehydrating prior agent context, or merging context across sessions.'

Combine what and when into a single sentence so both are explicit and distinct from generic refactoring skills.

Dimension	Reasoning	Score
Specificity	The phrase 'Use when working with code refactoring context restore' names a domain but describes no concrete actions at all, only a usage trigger.	2 / 5
Completeness	It provides only a 'when' clause ('Use when working with...') and no 'what' describing what the skill actually does, matching the anchor for only-when-present-without-what.	2 / 5
Trigger Term Quality	'code refactoring context restore' is awkward technical phrasing rather than natural language a user would say; it offers one or two generic keywords and misses common variations.	2 / 5
Distinctiveness Conflict Risk	'context restore' is a somewhat specific niche phrase, but 'code refactoring' is broad and could overlap with general refactoring skills.	3 / 5
	Total	9 / 20 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: 3eff4af

Reviewed: 1 day 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.