context-management-context-save

Use when working with context management context save

Quality

21%

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-save/SKILL.md

Quality

Content

35%

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

The body is an elaborately structured but mostly conceptual overview: heavy on buzzwords and familiar concepts, light on executable guidance, with workflows that lack concrete commands or validation. It reads more like a product feature list than operational instructions Claude can follow.

Suggestions

Cut conceptual padding (Role/Purpose, Advanced Integration Capabilities, Future Roadmap) and assume Claude knows what vector databases and JSON Schema are, keeping only operationally useful detail.

Make code examples executable by either defining the referenced helper functions or replacing them with real library calls (e.g. actual embedding/vector-DB client code).

Add validation checkpoints to the workflows (e.g. verify the context fingerprint/round-trip before archiving, confirm no sensitive data leaked), and move the long schema and DB-integration reference material into separate referenced files.

Dimension	Reasoning	Score
Conciseness	The body is padded with buzzwords ('elite context engineering specialist', 'comprehensive, semantic, and dynamically adaptable') and explains concepts Claude already knows (vector databases, JSON Schema, knowledge graphs), plus non-actionable 'Future Roadmap' and 'Advanced Integration Capabilities' sections, matching the verbose anchor.	1 / 3
Actionability	Code examples are present but call undefined functions like extract_project_metadata, remove_redundant_tokens, semantic_compression, and advanced_vector_compression, making them illustrative pseudocode rather than copy-paste executable, and the generic 'Instructions' bullets give no concrete steps.	2 / 3
Workflow Clarity	The Reference Workflows are numbered and sequenced, but steps are vague ('Analyze project structure', 'Store in vector database') with no commands or validation checkpoints; per the batch/destructive guideline, missing validation caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The skill is a single ~160-line monolithic file with no bundle references, and reference-like material (vector DB integration, JSON schema, code examples, roadmap) sits inline rather than split out; sections are well-organized, but at this length the one-level-deep split expected for score 3 is absent.	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-placeholder that tells Claude when (circularly) but never what the skill does, and uses redundant jargon instead of natural trigger terms. It would rarely be selected appropriately because it lacks both capability specifics and recognizable user phrasing.

Suggestions

Replace the circular trigger with concrete capabilities, e.g. 'Capture project context, serialize state to JSON/markdown/vector stores, and restore it across sessions.'

Add natural trigger terms a user would actually say, such as 'save context', 'snapshot project state', or 'resume work across sessions'.

State both what and when explicitly: end with 'Use when the user wants to persist or restore project/session context across sessions or agents.'

Dimension	Reasoning	Score
Specificity	The description 'Use when working with context management context save' names no concrete actions (no 'extract', 'serialize', 'retrieve'), only a when-clause, matching the vague-language anchor rather than the score-2 'names domain and some actions'.	1 / 3
Completeness	It offers only a circular 'when' (use when working with the skill's own topic) and entirely omits what the skill does, so it misses the 'what' half required for completeness.	1 / 3
Trigger Term Quality	The phrase 'context management context save' is redundant jargon repeating the skill name rather than natural keywords a user would say, fitting the 'no natural keywords; technical jargon or overly generic' anchor.	1 / 3
Distinctiveness Conflict Risk	'context save' narrows to a niche beyond pure generality but still overlaps with adjacent context-management skills, matching 'somewhat specific but could still overlap' rather than the clearly-distinct score 3 or the score-1 'would conflict with many skills'.	2 / 3
	Total	5 / 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-save/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.