context-management-context-restore

Use when working with context management context restore

Quality

13%

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

Quality

Content

27%

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

The content is broad and well-structured but verbose, explanatory of concepts Claude already knows, and offers illustrative rather than executable code with no concrete validation checkpoints, leaving it mid-to-low across the rubric.

Suggestions

Cut conceptual primers (what cosine similarity or caching are) and the speculative 'Future Roadmap' to reduce tokens and respect Claude's competence.

Replace pseudocode-style helpers with concrete, runnable implementations or explicitly justify the abstraction, and document the real `context-restore` command interface.

Add explicit validation checkpoints with runnable commands in the workflows (e.g. a verification step after context merge) to support a clear validate→fix→retry loop.

Dimension	Reasoning	Score
Conciseness	The body explains general concepts Claude already knows (vector search, cosine similarity, temporal decay, caching) and pads the token budget with speculative material such as 'Quantum-inspired vector search algorithms', violating the lean-content anchor.	1 / 3
Actionability	It provides several Python snippets, but they rely on undefined helpers (VectorDatabase, calculate_composite_score, prioritize_components, load_component, estimate_tokens) and unimplemented CLI calls like `context-restore`, so the code is closer to illustrative pseudocode than copy-paste-ready execution.	2 / 3
Workflow Clarity	Reference workflows list sequenced steps, but validation is only mentioned as an abstract capability rather than an explicit checkpoint with a runnable command, and there is no validate→fix→retry feedback loop for the destructive merge operations described.	2 / 3
Progressive Disclosure	Sections are well-organized and no bundle files exist (so no nested references), but the SKILL.md is a single monolithic inline treatment of API details, strategies, and workflows that would benefit from being split into separate reference files rather than packed into one body.	2 / 3
	Total	7 / 12 Passed

Description

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 restatement of the skill name with no concrete capabilities, natural trigger terms, or clear niche, scoring at the bottom of the rubric across all dimensions.

Suggestions

State concrete actions the skill performs, e.g. 'Reconstructs and rehydrates project context from a vector database for resuming multi-agent workflows'.

Add natural user-facing triggers such as 'Use when resuming a long-running project, recovering lost context, or transferring knowledge between projects'.

Reword the title-derived phrase 'context management context restore' into distinct, human-language terms to reduce conflict with neighboring context/memory skills.

Dimension	Reasoning	Score
Specificity	The description "Use when working with context management context restore" names no concrete actions or capabilities — only restates the skill title in vague operational terms, closer to the 'Helps with documents' anchor than any action-listing example.	1 / 3
Completeness	It gives only a weak 'Use when' clause and never states what the skill does (no capability described), so both the 'what' and 'when' are missing or very weak — matching the score-1 anchor.	1 / 3
Trigger Term Quality	"context management context restore" is awkward, title-derived jargon rather than natural phrasing a user would actually say; it lacks common task variations and reads as a keyword-stuffed echo of the skill name.	1 / 3
Distinctiveness Conflict Risk	"context management context restore" is generic enough to overlap with many context/memory/multi-agent skills and provides no distinct niche trigger, so it would readily conflict with adjacent skills.	1 / 3
	Total	4 / 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/context-management-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.