Name: context-management-context-restore
Rating: 37.6 (1 reviews)
Author: rmyndharis

Blog Docs Log in Get started

context-management-context-restore

Use when working with context management 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 ./skills/context-management-context-restore/SKILL.md

The canonical home for this skill is code-refactoring-context-restore in rmyndharis/antigravity-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 a long, padded overview of context-restoration concepts illustrated with non-executable pseudocode and workflows that lack validation checkpoints. It reads as a domain primer rather than focused, actionable guidance, with no progressive disclosure to supporting files.

Suggestions

Trim explanatory bullets that restate concepts Claude already knows (cosine similarity, embeddings, caching) and keep only skill-specific decisions and parameters.

Replace pseudocode helpers with executable code or explicitly justify the abstraction, so examples are copy-paste runnable.

Add validation/verification checkpoints to the Reference Workflows (e.g. verify restored context against the current codebase before proceeding) and split the eight strategy sections into separate reference files linked from a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose, padding sections with concepts Claude already knows (cosine similarity, multi-modal embeddings, caching, probabilistic data structures) across 8 strategy sections and a role statement; it is above 1 only because the content is structured rather than a single unbroken wall of text.	2 / 5
Actionability	Python examples are pseudocode relying on 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, matching the 'pseudocode instead of executable code' anchor; it is not 4 because none of the code is copy-paste runnable.	3 / 5
Workflow Clarity	The 'Reference Workflows' list numbered steps but include no validation or verification checkpoints for batch context operations, hitting the rubric's cap of 3 for missing validation; it is not 2 because sequences are present and roughly ordered.	3 / 5
Progressive Disclosure	No bundle files exist and the body is a monolithic document with eight strategy sections, input parameters, and workflows all inlined that clearly belong in separate reference files, matching the 'content that belongs in separate files is inlined' anchor; it is not 3 because there are no external references or navigation at all.	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 bare 'Use when...' restatement of the skill name with no concrete capabilities, no natural trigger terms, and no 'what' clause. It functions as a placeholder rather than actionable trigger guidance.

Suggestions

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

Replace the redundant 'context management context restore' with natural user phrases such as 'restore project context', 'resume a long-running project', or 'rehydrate agent memory'.

Add an explicit 'what' clause before the 'Use when' clause so both capability and trigger conditions are present.

Dimension	Reasoning	Score
Specificity	The description 'Use when working with context management context restore' names the domain but states no concrete actions or capabilities, matching the 'names domain but actions are minimal or generic' anchor; it does not reach 3 because no specific action is enumerated.	2 / 5
Completeness	Only a vague 'when' clause is present (restating the skill name) with no 'what' describing what the skill does, matching the 'only when is present without what' anchor; it is not 3 because the 'what' is entirely absent rather than clear.	2 / 5
Trigger Term Quality	The only trigger phrase is 'context management context restore', a redundant restatement of the skill name rather than natural user language, missing the common phrases a user would actually say; it is above 1 only because the domain term itself appears.	2 / 5
Distinctiveness Conflict Risk	The 'context restore' niche is somewhat specific but the generic, redundant phrasing could overlap with broader context-management skills, matching the 'somewhat specific but could still overlap' anchor; it is not 4 because the trigger is not clearly distinctive.	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/context-management-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.