context-manager
Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
31
14%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/context-manager/SKILL.mdQuality
Discovery
22%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 reads like a résumé headline rather than a functional skill description. It is heavy on buzzwords ('elite', 'mastering', 'intelligent') and light on concrete actions or trigger guidance. It fails to tell Claude what specific tasks this skill performs or when to select it.
Suggestions
Replace buzzwords with concrete actions, e.g., 'Builds and queries vector databases, constructs knowledge graphs, manages context windows for LLM applications.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about RAG pipelines, embedding storage, context window optimization, or knowledge graph construction.'
Remove self-promotional language like 'Elite' and 'mastering' — use third-person functional descriptions of what the skill does, not what it claims to be.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, buzzword-heavy language like 'elite AI context engineering specialist' and 'mastering dynamic context management' without listing any concrete actions. No specific operations (e.g., 'build knowledge graphs', 'query vector databases') are described. | 1 / 3 |
Completeness | The description vaguely addresses 'what' through buzzwords but provides no 'when' guidance whatsoever. There is no 'Use when...' clause or any explicit trigger guidance, and even the 'what' is too abstract to be useful. | 1 / 3 |
Trigger Term Quality | It includes some relevant technical keywords like 'vector databases', 'knowledge graphs', and 'memory systems' that a user might mention, but these are buried in fluff and missing common natural variations or user-facing terms. | 2 / 3 |
Distinctiveness Conflict Risk | Terms like 'vector databases' and 'knowledge graphs' provide some distinctiveness, but the broad framing ('context engineering', 'intelligent memory systems') could overlap with many AI-related skills. | 2 / 3 |
Total | 6 / 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 is essentially a persona/role description rather than an actionable skill. It consists almost entirely of abstract capability lists, behavioral traits, and knowledge areas that provide no concrete guidance on how to perform any specific task. There are no code examples, no specific commands, no concrete workflows, and no executable instructions—just extensive taxonomies of topics Claude likely already understands.
Suggestions
Replace the extensive capability/trait/knowledge lists with 2-3 concrete, executable workflows for the most common tasks (e.g., implementing a RAG pipeline, setting up a vector database, designing a context management system) with actual code examples.
Remove the persona-style sections (Expert Purpose, Behavioral Traits, Knowledge Base, Example Interactions) which waste tokens describing what Claude should be rather than teaching it what to do.
Add specific validation steps and feedback loops to workflows, such as how to test context retrieval quality, measure RAG performance, or validate knowledge graph integrity.
Move detailed reference material (e.g., vector database comparison, chunking strategy details) into the referenced 'resources/implementation-playbook.md' and keep SKILL.md as a concise quick-start guide.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and padded with extensive lists of capabilities, behavioral traits, and knowledge areas that Claude already knows or that provide no actionable guidance. The content reads like a persona description rather than a skill, with massive bullet-point lists that waste tokens without teaching Claude anything new. | 1 / 3 |
Actionability | No concrete code, commands, or executable examples anywhere. The entire skill is abstract descriptions and vague bullet points like 'Dynamic context assembly and intelligent information retrieval' with zero specifics on how to actually do anything. The 'Response Approach' section lists generic steps like 'Analyze context requirements' without any concrete guidance. | 1 / 3 |
Workflow Clarity | The 'Response Approach' lists 10 high-level steps but they are vague and lack any validation checkpoints, concrete commands, or feedback loops. There is no clear workflow for any specific task—just abstract process descriptions that could apply to almost anything. | 1 / 3 |
Progressive Disclosure | There is one reference to 'resources/implementation-playbook.md' for detailed examples, which shows some awareness of progressive disclosure. However, the main content is a monolithic wall of bullet-point lists that should either be drastically condensed or split into referenced files. The single external reference is insufficient given the volume of inline content. | 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.