CtrlK
BlogDocsLog inGet started
Tessl Logo

context-manager

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

29

Quality

23%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-manager/SKILL.md
SKILL.md
Quality
Evals
Security

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 résumé-style persona specification: ten sections of capability bullets, behavioral traits, and knowledge areas that describe an ideal expert without ever telling Claude what to actually do. Its only pointer to concrete material references a nonexistent file, so the skill delivers zero executable guidance despite consuming a large token budget.

Suggestions

Replace the Capabilities/Behavioral Traits/Knowledge Base catalogs with 3–5 concrete procedures (e.g., a context-assembly decision checklist, a chunking-strategy selection table, a RAG evaluation recipe) — or move the catalogs into a reference file and keep a 10-line overview in SKILL.md.

Fix or remove the dangling reference: resources/implementation-playbook.md does not exist in the bundle; either ship the file (and use the correct bundle directory) or delete the pointer.

Add validation checkpoints to the Response Approach (e.g., 'verify retrieval relevance with a held-out query set before scaling', 'confirm context fits token budget before deployment') so the workflow has testable gates instead of generic steps.

DimensionReasoningScore

Conciseness

The body is ~150 lines of abstract capability bullets ('Dynamic context assembly and intelligent information retrieval', 'Ontology development and semantic schema design', etc.) that enumerate domain knowledge Claude already has and add no instruction. This matches anchor 1 ('severely verbose… heavily padded'); it does not merit anchor 2 because there is essentially no section that earns its tokens beyond the generic 'Use this skill when' header.

1 / 5

Actionability

The only procedural guidance is 'Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes' — entirely abstract direction with no code, commands, schemas, decision criteria, or worked examples. This matches anchor 1 ('entirely vague or abstract; only describes rather than instructs'); anchor 2 would require at least high-level but specific steps, which even the 10-step 'Response Approach' lacks ('Analyze context requirements', 'Design context architecture').

1 / 5

Workflow Clarity

The 'Response Approach' section lists a 10-step sequence, so a rough order exists, but the steps are generic one-liners with no validation checkpoints or error-recovery loops ('Monitor and measure context quality' is not a checkable gate). This matches anchor 2 ('rough sequence present but many gaps; validation absent'); it falls short of anchor 3, whose steps are concretely defined, and this is not a destructive/batch skill so no additional cap applies.

2 / 5

Progressive Disclosure

The body is a monolithic persona spec — capability catalogs, behavioral traits, and a knowledge-base list that belong in separate reference files are all inlined — and its single reference, 'If detailed examples are required, open resources/implementation-playbook.md', is buried in a bullet and points to a file that does not exist in the bundle (no resources/, references/, scripts/, or assets/ directories are present). This matches anchor 2 ('minimal structure; content that clearly belongs in separate files is inlined'); it is below anchor 3 because the one reference present is broken rather than merely unclearly signaled.

2 / 5

Total

6

/

20

Passed

Description

36%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 buzzword-heavy persona statement: it names four technical domains but never states what the skill actually does or when to invoke it. It reads like a LinkedIn headline rather than a capability+trigger description, and would likely fail to surface for many relevant user phrasings (e.g., 'RAG', 'embeddings', 'retrieval').

Suggestions

Rewrite as a third-person action list, e.g. 'Designs dynamic context assembly, vector-database retrieval pipelines (Pinecone, Qdrant, Weaviate), knowledge graphs, and memory systems for AI agents.'

Add an explicit trigger clause: 'Use when the user mentions context engineering, context windows, RAG, embeddings, vector databases, knowledge graphs, or agent memory.'

Drop evaluative filler ('Elite', 'mastering', 'intelligent') — it adds tokens without adding capability or trigger information.

DimensionReasoningScore

Specificity

The description names the domain ('dynamic context management, vector databases, knowledge graphs, and intelligent memory systems') but contains no concrete actions — 'Elite AI context engineering specialist mastering' is a persona claim, not a capability. It fits anchor 2 ('names the domain but actions are minimal or generic'), not anchor 3, which requires 1–2 concrete actions; it is above anchor 1 because four specific technical domains are named rather than pure abstraction.

2 / 5

Completeness

There is no 'Use when…' clause or equivalent trigger guidance anywhere in the description (capping completeness at 3), and the 'what' is vague — 'Elite AI context engineering specialist mastering…' states a persona and topic areas, not what the skill does. This matches anchor 2 ('has a vague what and no when'); it does not reach anchor 3 because that anchor's 'clear what' implies stated capabilities, which are absent.

2 / 5

Trigger Term Quality

Phrases like 'context management', 'vector databases', 'knowledge graphs', and 'memory systems' are terms a user in this space would plausibly say, but common variations such as RAG, embeddings, retrieval, Pinecone/Qdrant, or 'context window' are missing. This matches anchor 3 ('some relevant keywords but missing common variations or synonyms'), below anchor 4's 'good keyword coverage' and above anchor 2's generic-only language.

3 / 5

Distinctiveness Conflict Risk

'Context engineering… vector databases, knowledge graphs, and intelligent memory systems' carves out a recognizable niche, but the scope overlaps heavily with adjacent skills (RAG/retrieval, agent orchestration, prompt engineering, memory tools). It fits anchor 3 ('somewhat specific but could still overlap with similar skills'), below anchor 4 because multiple sibling skills in the AI-engineering space would trigger on the same terms.

3 / 5

Total

10

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
sickn33/agentic-awesome-skills
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.