code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

33%

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-claude/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 body is broad and structured but speculative and non-executable: code is pseudocode against undefined helpers, the one referenced file is missing, and substantial sections are conceptual padding or roadmap fluff. It reads like a domain overview rather than a runnable procedure.

Suggestions

Replace pseudocode with executable code or define the helper functions it calls, so examples can actually run.

Remove the "Role Statement", "Context Overview", and "Future Roadmap" sections — they explain concepts Claude already knows or speculate rather than instruct.

Add an explicit validation feedback loop (validate restored context -> on mismatch, re-retrieve) to the workflows, and either create `resources/implementation-playbook.md` or drop the dangling reference.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded — the "Role Statement", "Context Overview", abstract capability bullets, and a buzzword-heavy "Future Roadmap" ("Quantum-inspired vector search", "Self-healing context reconstruction") do not earn their tokens.	2 / 5
Actionability	Code blocks are present but are pseudocode calling undefined functions (VectorDatabase, rank_and_filter_contexts, calculate_composite_score, prioritize_components, estimate_tokens), so they are not executable; the bash CLI examples are more concrete.	3 / 5
Workflow Clarity	The numbered Reference Workflows are sequenced and mention a validation step, but they lack explicit feedback loops or error-recovery checkpoints; for a batch context-restoration operation this caps clarity at 3.	3 / 5
Progressive Disclosure	The single reference to `resources/implementation-playbook.md` is dangling (no such file or directory exists), and the eight detailed strategy sections are inlined in the SKILL.md rather than split into separate files.	2 / 5
	Total	10 / 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 near-tautological trigger phrase that names a domain but tells Claude neither what the skill does nor how it is distinct. It reads as auto-generated from the skill title rather than written to guide invocation.

Suggestions

State concrete actions the skill performs, e.g. "Recovers and reconstructs project context across multi-agent workflows, rehydrating memory from a vector store within a token budget."

Replace the awkward "context restore" with natural trigger phrasing users would actually say, e.g. "restore context", "context restoration", "recover project memory".

Add an explicit "Use when..." clause tied to concrete situations (resuming a long-running project, rehydrating memory after a context compaction).

Dimension	Reasoning	Score
Specificity	The description "Use when working with code refactoring context restore" names a domain but describes no concrete actions at all — there is not even a generic action verb, only a "working with" framing.	2 / 5
Completeness	It provides a "when" clause ("Use when working with...") but no "what" — it never states what the skill does, matching the anchor where only "when" is present without "what".	2 / 5
Trigger Term Quality	"code refactoring" is a genuine natural keyword, but "context restore" is grammatically broken rather than a phrase users would say, and synonyms like "restore context" or "context restoration" are missing.	2 / 5
Distinctiveness Conflict Risk	The niche of context restoration during refactoring is somewhat specific, but the bare phrasing could still overlap with general refactoring or context-management skills.	3 / 5
	Total	9 / 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-claude/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.