context-manager

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.

Quality

19%

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-manager/SKILL.md

Quality

Content

10%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 capability catalog with no executable guidance, no code, and no validation checkpoints; its only external reference is broken (the file does not exist). It functions as a persona description rather than an actionable skill, leaving Claude without concrete steps to follow.

Suggestions

Replace the capability/behavioral/knowledge bullet walls with concise, actionable guidance: concrete commands, minimal code examples, or specific step sequences Claude can execute.

Add explicit validation checkpoints and feedback loops to the Response Approach (e.g., 'Validate retrieval results before proceeding; if relevance scores are low, re-chunk and retry'), which would lift workflow_clarity above the destructive/batch cap of 3.

Fix the broken reference: either create resources/implementation-playbook.md with the promised detailed examples or remove the pointer, and surface remaining references clearly under a dedicated 'References' section one level deep.

Dimension	Reasoning	Score
Conciseness	The ~180-line body is extensively verbose, restating concepts Claude already knows across ten 7-item capability sections and generic behavioral/knowledge lists with heavy padding, matching anchor 1 ('severely verbose; extensively explains concepts Claude already knows; heavily padded'). It is not 2 because there is no tighter, less-padded section to offset the bulk.	1 / 5
Actionability	The body provides no code, commands, or concrete executable guidance — only abstract capability descriptions and a generic 10-step 'Response Approach', matching anchor 1 ('entirely vague or abstract; only describes rather than instructs'). It is not 2 because not even minimal concrete steps or examples are given.	1 / 5
Workflow Clarity	A rough 10-step sequence ('Response Approach') exists but steps are abstract ('Analyze context requirements', 'Design context architecture') with no validation checkpoints or feedback loops for risky enterprise/batch operations, matching anchor 2 ('rough sequence present but many gaps; validation absent'). It is not 1 because a numbered sequence is present; it is not 3 because validation is entirely missing rather than just gappy.	2 / 5
Progressive Disclosure	Bulk capability content that belongs in separate files is inlined as a wall of bullets, and the one reference ('resources/implementation-playbook.md') is buried in the Instructions section and points to a non-existent file (no resources/ or bundle directory exists), matching anchor 2 ('content that clearly belongs in separate files is inlined; or references are buried'). It is not 3 because the sole reference is broken and unverified, not merely unclear.	2 / 5
	Total	6 / 20 Passed

Description

28%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 role-flavored domain listing rather than a trigger-oriented capability statement: it names areas of expertise but provides no concrete actions and no 'when to use' guidance. It reads as marketing copy, which weakens both trigger quality and completeness.

Suggestions

Rewrite in third-person action voice with concrete verbs, e.g. 'Designs and implements dynamic context management, vector retrieval, and memory systems for AI applications.'

Add an explicit trigger clause: 'Use when building RAG pipelines, vector search, knowledge graphs, or multi-agent context orchestration.'

Replace buzzwords ('Elite', 'mastering', 'intelligent') with specific, user-sayable terms like 'embeddings', 'RAG', and 'semantic retrieval' to improve trigger quality.

Dimension	Reasoning	Score
Specificity	The description names domains ('context management, vector databases, knowledge graphs, and intelligent memory systems') but uses role language ('specialist mastering') rather than concrete actions, matching anchor 2 where the domain is named but actions are minimal or generic. It is not 3 because no concrete actions like 'builds', 'retrieves', or 'extracts' are stated.	2 / 5
Completeness	It offers a vague 'what' (domains covered) and no 'when' trigger guidance at all, sitting between anchors 2 and 3; per the guideline a missing 'Use when...' clause caps completeness, and the 'what' itself is not concrete enough for 3.	2 / 5
Trigger Term Quality	Keywords are technical jargon ('dynamic context management', 'vector databases', 'knowledge graphs', 'intelligent memory systems') with few natural phrases a user would actually say, matching anchor 2 ('one or two generic keywords; missing the natural phrases users say'). It is not 3 because common user-facing terms like 'RAG', 'embeddings', or 'memory' are absent or buried.	2 / 5
Distinctiveness Conflict Risk	The AI context-engineering niche is somewhat specific but the broad terms ('context', 'memory', 'vector databases') could overlap with RAG, memory, or vector-DB skills, matching anchor 3 ('somewhat specific but could still overlap'). It is not 4 because the triggers are not narrowly differentiated from adjacent skills.	3 / 5
	Total	9 / 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-manager/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.