context-management-context-save

Use when working with context management context save

Quality

31%

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

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 verbose, buzzword-heavy monolith with stub code that is not directly executable and workflows lacking validation checkpoints. Its only external reference points to a file that does not exist, and no bundle files are provided, leaving detailed content inlined rather than progressively disclosed.

Suggestions

Cut the 'Role and Purpose', 'Advanced Integration Capabilities', and 'Future Roadmap' sections, which are buzzword filler that assumes Claude lacks knowledge it already has.

Make code examples executable by defining the referenced helper functions or replacing them with real library calls, so the examples are copy-paste ready.

Add validation/verification checkpoints to the workflows (e.g. 'verify the context fingerprint is unique before storing', 're-validate schema after serialization') and either create the referenced 'resources/implementation-playbook.md' or remove the broken reference.

Move the vector-database, storage-format, and schema reference material into separate files under references/ and link to them from a lean SKILL.md overview.

Dimension	Reasoning	Score
Conciseness	The body is padded with buzzword sections ('elite context engineering specialist', 'Future Roadmap', 'Advanced Integration Capabilities') and concept-list filler, matching 'Noticeably verbose; several unnecessary explanations or padded sections'; not score 1 because real code examples are present alongside the padding.	2 / 5
Actionability	Code examples are structurally concrete but call undefined helpers (extract_project_metadata, semantic_compression, advanced_vector_compression), making them effectively stubs/pseudocode, matching 'Some concrete guidance but incomplete; pseudocode instead of executable code'; not score 4 because the examples are not copy-paste executable.	3 / 5
Workflow Clarity	Two numbered workflows are present but neither includes validation, verification, or error-recovery checkpoints for a batch context-capture operation, matching 'Steps listed but validation gaps'; the rubric's destructive/batch cap also prevents scoring above 3.	3 / 5
Progressive Disclosure	Detailed material (vector DB integration, storage formats, code, roadmap) is inlined monolithically and the single reference to 'resources/implementation-playbook.md' points at a non-existent file with no bundle directories present, matching 'content that clearly belongs in separate files is inlined; or references are buried'; not score 3 because the one reference is broken and bulk content is not split out.	2 / 5
	Total	10 / 20 Passed

Description

25%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 weak trigger-only string that names a domain but never states what the skill does, using redundant jargon ('context management context save') that users would not naturally say. It fails to answer the 'what' half of a complete description and carries high overlap risk with other context skills.

Suggestions

Add a concrete 'what' clause before the trigger, e.g. 'Captures, serializes, and retrieves project context across sessions. Use when the user wants to save or restore conversation/project context.'

Replace the redundant 'context management context save' phrasing with natural trigger terms like 'save context', 'preserve session state', or 'restore project context'.

Add file-format or tool-specific triggers (e.g. 'context snapshots', '.json context files') to improve distinctiveness and reduce conflict with other context skills.

Dimension	Reasoning	Score
Specificity	The description only states 'Use when working with context management context save' and names the domain but lists no concrete actions the skill performs, fitting 'Names the domain but actions are minimal or generic' rather than the entirely-vague anchor 1 because a domain is named.	2 / 5
Completeness	It provides a 'when' trigger ('Use when working with...') but no 'what' describing the skill's function, exactly matching the anchor 'only when is present without what'; not score 3 because no clear statement of what it does exists.	2 / 5
Trigger Term Quality	The phrase 'context management context save' is repetitive jargon rather than a natural user utterance, offering only generic keywords and missing the natural phrasings users would say, matching 'One or two generic keywords; missing the natural phrases users say'.	2 / 5
Distinctiveness Conflict Risk	'context management' is broad and would overlap with many context-related skills, matching 'Very broad; high overlap risk with many similar skills'; not score 3 because 'context save' alone does not carve out a clearly distinct niche.	2 / 5
	Total	8 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/context-management-context-save/SKILL.md
Commit: b1aebac

Reviewed: ~17 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.