context-management-context-save

Use when working with context management context save

Quality

23%

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

28%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 reads like product documentation — conceptual feature lists and stub code rather than executable guidance for Claude. Workflows lack concrete steps and validation, and verbosity is high relative to actionable content.

Suggestions

Replace stub functions with real, runnable code (or named helper scripts in ./scripts/) so examples are copy-paste executable.

Strip marketing prose and remove non-actionable sections ('Future Roadmap', 'Advanced Integration Capabilities') to cut tokens.

Add validation checkpoints to the capture workflows, e.g. verify no secrets are included and confirm the serialized artifact round-trips before storing.

Dimension	Reasoning	Score
Conciseness	Marketing-fluff paragraphs ('elite context engineering specialist', 'orchestrates advanced context capture') and padding sections like 'Future Roadmap' and 'Advanced Integration Capabilities' add tokens Claude does not need.	2 / 5
Actionability	The Python examples call only undefined stubs (extract_project_metadata, semantic_compression, advanced_vector_compression); the only genuinely executable artifact is the JSON Schema, leaving mostly high-level hints.	2 / 5
Workflow Clarity	Workflows are abstract numbered steps ('Analyze project structure', 'Store in vector database') with no concrete commands and no validation checkpoints, despite the skill noting sensitive-info exclusion and batch capture risk.	2 / 5
Progressive Disclosure	The body is a single inlined file with clear section headers but no external references, and content such as the schema and feature lists could be split out; structure exists but no one-level-deep navigation.	3 / 5
	Total	9 / 20 Passed

Description

17%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, tautological trigger phrase that states when to invoke the skill but never says what it does. It reads as auto-generated filler rather than a useful capability statement.

Suggestions

Rewrite the description to lead with concrete actions, e.g. 'Captures, serializes, and retrieves project context across sessions for multi-agent workflows.'

Add a real 'when' trigger using natural user language such as 'Use when the user wants to save or restore conversation/project context across sessions.'

Avoid the repetitive 'context management context save' phrasing; use plain terms a user would actually say.

Dimension	Reasoning	Score
Specificity	The phrase 'working with context management context save' names a domain but lists no concrete actions — 'working with' is not a capability verb, so it sits just above entirely-vague.	2 / 5
Completeness	Only a 'when' clause is present ('Use when working with...'); there is no 'what' describing what the skill actually does, matching the anchor for only-'when'-without-'what'.	2 / 5
Trigger Term Quality	'context management context save' is tautological jargon a user would never naturally say; it lacks any natural trigger phrases, synonyms, or file extensions.	1 / 5
Distinctiveness Conflict Risk	The generic 'context management' framing is very broad and would overlap with many context-handling or memory skills, with no niche trigger to disambiguate.	2 / 5
	Total	7 / 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-save/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.