context-management-context-save
Use when working with context management context save
40
11%
Does it follow best practices?
Impact
91%
1.31xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-management-context-save/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is extremely weak across all dimensions. It lacks any concrete actions, provides no meaningful explanation of what the skill does, and its trigger terms are circular and vague. It would be nearly impossible for Claude to reliably select this skill from a pool of alternatives.
Suggestions
Add specific concrete actions the skill performs, e.g., 'Saves and restores conversation context, persists key variables across sessions, and manages memory state.'
Expand the 'Use when' clause with natural trigger terms users would actually say, e.g., 'Use when the user asks to save context, remember something, persist session data, or manage conversation memory.'
Clarify the skill's distinct niche to reduce conflict risk—specify what kind of context (conversation, application state, user preferences) and what format or mechanism is used.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. 'Working with context management context save' is vague and abstract—it doesn't describe what the skill actually does (e.g., save conversation state, persist variables, manage memory). | 1 / 3 |
Completeness | The 'what does this do' is entirely missing—there is no description of capabilities. While it has a 'Use when' clause, the trigger condition is circular and uninformative ('working with context management context save'), so both what and when are very weak. | 1 / 3 |
Trigger Term Quality | It includes some potentially relevant keywords like 'context management' and 'context save,' but these are somewhat redundant and lack natural variations a user might say (e.g., 'save session,' 'remember context,' 'persist state,' 'store conversation'). | 2 / 3 |
Distinctiveness Conflict Risk | 'Context management' is extremely generic and could overlap with many skills involving memory, state, sessions, or data persistence. There is nothing to clearly distinguish this skill's niche. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
7%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads like a marketing document or architectural overview rather than actionable instructions. It is extremely verbose, explains concepts Claude already understands, provides non-executable pseudocode, and lacks concrete workflows with validation steps. The content would need a near-complete rewrite to be useful as a skill file.
Suggestions
Replace all pseudocode with executable, copy-paste-ready code examples that use real libraries and produce real output.
Remove conceptual explanations (what context management is, what vector databases are, future roadmap) and focus only on specific steps Claude should take.
Add concrete, numbered workflows with explicit validation checkpoints (e.g., 'verify the context file was written by reading it back and checking the schema').
Move detailed sections like vector DB integration and knowledge graph construction into separate referenced files, keeping SKILL.md as a concise overview with clear navigation links.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive conceptual explanations Claude already knows (what context management is, what vector databases are, what compression is). Includes a 'Future Roadmap' section and 'Role and Purpose' preamble that waste tokens. Much of the content describes rather than instructs. | 1 / 3 |
Actionability | Code examples are pseudocode calling undefined functions (extract_project_metadata, analyze_architecture, semantic_compression, etc.) — none are executable. The workflows are vague step lists without concrete commands. The JSON schema is the only concrete artifact but isn't tied to actionable usage. | 1 / 3 |
Workflow Clarity | The two 'Reference Workflows' are high-level bullet lists with no concrete commands, no validation checkpoints, and no error recovery steps. There is no clear sequence a user or Claude could actually follow to accomplish context saving. | 1 / 3 |
Progressive Disclosure | There is a reference to 'resources/implementation-playbook.md' for detailed examples, which is good. However, the main file is a monolithic wall of text with sections that should be split out (vector DB integration, knowledge graph construction, storage formats) rather than inlined at length. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
93c57b2
- Reviewed
Table of Contents
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.