context-manager

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

1.00x

Quality

26%

Does it follow best practices?

Impact

99%

1.00x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/context-manager/SKILL.md

The canonical home for this skill is context-manager in sickn33/agentic-awesome-skills

Quality

Content

25%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 an abstract persona-and-capability catalogue: long lists of capabilities, traits, and knowledge with no executable code, commands, or validation steps, and a single inline reference to a non-existent resources file. It reads as marketing material rather than actionable skill guidance.

Suggestions

Replace the capability/trait/knowledge enumerations with concrete, executable guidance — example architecture sketches, library calls (e.g., Pinecone/Weaviate/Qdrant snippets), chunking strategies, and retrieval-evaluation commands.

Add validation/verification checkpoints to the workflow (e.g., measure retrieval recall@k, validate context-window budget, re-rank and check for hallucination) instead of the abstract 10-step 'Response Approach'.

Either create the referenced resources/implementation-playbook.md with the detailed material and link to it one level deep, or remove the broken reference and inline only the essential quick-start content.

Dimension	Reasoning	Score
Conciseness	The body runs ~170 lines of abstract capability, behavioral-trait, and knowledge-base enumerations (e.g., 'Dynamic context assembly and intelligent information retrieval', 'Systems thinking approach') that restate concepts Claude already knows, matching the noticeably-verbose / padded anchor.	2 / 5
Actionability	Guidance is high-level hints only ('Clarify goals, constraints, and required inputs', 'Apply relevant best practices and validate outcomes') with no concrete code, commands, or specific steps, matching the minimal-concrete-guidance anchor.	2 / 5
Workflow Clarity	The 10-step 'Response Approach' is a rough abstract sequence ('Analyze… Design… Implement… Optimize…') with no executable commands and no validation checkpoints, matching the rough-sequence-with-gaps-and-absent-validation anchor.	2 / 5
Progressive Disclosure	Capability lists that belong in separate reference files are inlined as a monolithic wall, and the single reference — 'open resources/implementation-playbook.md' — is buried and broken (no resources/ directory exists), matching the minimal-structure / buried-reference anchor.	2 / 5
	Total	8 / 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 persona statement ('Elite AI context engineering specialist mastering…') rather than a trigger-oriented capability summary: it names the domain but lists no concrete actions and omits any 'Use when' guidance. It reads as marketing fluff, which the rubric explicitly penalizes.

Suggestions

Rewrite the description in third person around concrete actions (e.g., 'Designs dynamic context assembly systems, vector/keyword retrieval pipelines, and multi-agent context handoff protocols').

Add an explicit 'Use when…' clause listing natural trigger phrases users would actually say (e.g., 'Use when designing RAG pipelines, building context orchestration for multi-agent systems, or optimizing context windows and token budgets').

Drop buzzword padding ('Elite', 'intelligent', 'mastering') and replace with specific, scannable capability verbs.

Dimension	Reasoning	Score
Specificity	The description 'Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems' names the domain but uses persona adjectives ('mastering', 'specialist') rather than concrete actions, matching the anchor for naming the domain with minimal/generic actions.	2 / 5
Completeness	It gives a vague 'what' (a persona description) but provides no 'when' / 'Use when' trigger clause at all, matching the anchor for a vague what with no when.	2 / 5
Trigger Term Quality	The keywords ('dynamic context management, vector databases, knowledge graphs, intelligent memory systems') are technical jargon rather than the natural phrases a user would say when needing this skill, fitting the one-or-two generic/technical keywords anchor.	2 / 5
Distinctiveness Conflict Risk	'Context engineering' is a recognizable niche but the description is broad enough to overlap with adjacent RAG, vector-DB, and memory skills, matching the somewhat-specific-but-could-overlap anchor.	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: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/context-manager/SKILL.md
Commit: 57c135b

Reviewed: 3 days 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.