code-refactoring-context-restore

Use when working with code refactoring context restore

Quality

26%

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

Quality

Content

17%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 skill body is a templated shell filled with generic instructions and buzzwords, an empty requirements section, and references to a dozen sub-skill files that do not exist in the bundle. It provides almost no executable guidance and cannot stand on its own.

Suggestions

Replace the abstract Instruction bullets with concrete, executable steps (specific commands, code snippets, or a real recovery procedure) and fill the empty 'Core Requirements and Arguments' section.

Either create the referenced sub-skills and resources files or remove the dangling links so progressive disclosure points to real content.

Trim the buzzword-heavy Role Statement and Context Overview, which restate concepts Claude already knows and restate the skill title verbatim.

Dimension	Reasoning	Score
Conciseness	The body restates the title verbatim in the 'Use this skill when' section and pads with buzzword-laden boilerplate ('intelligent, semantic-aware context retrieval and reconstruction') plus a Context Overview explaining what such a system is, matching 'Noticeably verbose; several unnecessary explanations or padded sections'; not a 3 because the padding is pervasive rather than minor.	2 / 5
Actionability	The Instructions are pure abstraction ('Clarify goals... Apply relevant best practices... Provide actionable steps and verification') with no code, commands, or specifics, and the 'Core Requirements and Arguments' section is empty, matching 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'.	1 / 5
Workflow Clarity	The four instruction bullets are a rough but generic sequence with no validation checkpoints and an empty requirements section, matching 'Rough sequence present but many gaps; steps poorly defined; validation absent'; not a 1 because some sequence is discernible.	2 / 5
Progressive Disclosure	The body is a hollow skeleton whose entire detail lives in 11 referenced ./sub-skills/*.md files and resources/implementation-playbook.md, none of which exist in the bundle, so the promised navigation leads nowhere and the inline content is effectively empty, matching 'Minimal structure; content that clearly belongs in separate files is inlined; or references are buried'; not a 3 because the references are dead rather than merely unclear.	2 / 5
	Total	7 / 20 Passed

Description

36%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 single trigger clause that names its niche but fails to state what the skill actually does, leaving it vague and one-dimensional. It is identifiable but thin on capability detail and natural trigger phrasing.

Suggestions

Add a 'what' clause stating concrete capabilities, e.g. 'Recovers and rehydrates project context across multi-agent workflows. Use when resuming paused projects or restoring lost session state.'

Replace the awkward 'context restore' with natural user phrasing and synonyms such as 'restore context', 'session recovery', or 'resume project'.

List one or two concrete actions so the skill is distinguishable from generic refactoring skills.

Dimension	Reasoning	Score
Specificity	The description names the domain ('code refactoring context restore') but lists no concrete actions, matching the anchor 'Names the domain but actions are minimal or generic' and falling above score 1 which requires entirely vague language with no domain named.	2 / 5
Completeness	Only a 'when' clause ('Use when working with code refactoring context restore') is present with no 'what' describing capabilities, exactly matching the anchor 'only when is present without what'; not a 3 because there is no clear statement of what the skill does.	2 / 5
Trigger Term Quality	'code refactoring' is a natural term a user would say, but 'context restore' is awkward jargon with no synonyms or variations, fitting 'Some relevant keywords but missing common variations or synonyms'; it is not a 2 because a genuine natural trigger phrase is present.	3 / 5
Distinctiveness Conflict Risk	The 'context restore' niche is somewhat specific but the phrase overlaps with general code-refactoring skills, matching 'Somewhat specific but could still overlap with similar skills'; not a 4 because the trigger is not crisp enough to minimize overlap.	3 / 5
	Total	10 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 11 missing	Warning

	Total	14 / 16 Passed

Repository: Dokhacgiakhoa/Agent-Skills-4-Vibe-Coding-CLI
Path: .agent/skills/code-refactoring-context-restore/SKILL.md
Commit: c4a059b

Reviewed: ~16 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.