integrate

Add Olakai monitoring to existing AI code — wrap your LLM client, configure custom KPIs, and validate the integration end-to-end

Quality

61%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./content/olakai/skills/integrate/SKILL.md

Quality

Discovery

67%

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 strong in specificity and distinctiveness, clearly naming the Olakai product and listing concrete integration steps. However, it lacks an explicit 'Use when...' clause which hurts completeness, and could benefit from more natural trigger terms users might use when seeking this functionality. The use of second person 'your' violates the third-person voice guideline.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to add Olakai monitoring, observability, or tracing to their AI/LLM application.'

Include additional natural trigger terms like 'observability', 'tracing', 'LLM logging', 'AI analytics', or 'model monitoring' to improve keyword coverage.

Rewrite in third person voice: 'Adds Olakai monitoring to existing AI code — wraps the LLM client, configures custom KPIs, and validates the integration end-to-end.'

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'wrap your LLM client', 'configure custom KPIs', and 'validate the integration end-to-end'. These are clear, actionable steps.	3 / 3
Completeness	Clearly answers 'what' (add Olakai monitoring by wrapping LLM client, configuring KPIs, validating integration), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant terms like 'Olakai', 'monitoring', 'LLM client', 'KPIs', and 'integration', but misses common variations users might say such as 'observability', 'tracing', 'logging', 'AI monitoring', or 'LLM analytics'. Also uses second person 'your' which is noted but scored under specificity per rubric.	2 / 3
Distinctiveness Conflict Risk	The description is highly specific to Olakai as a product and its monitoring integration workflow. The brand name 'Olakai' combined with specific actions like wrapping LLM clients makes it very unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Implementation

55%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill excels at actionability with concrete, executable code examples and CLI commands for every step, and has strong workflow clarity with explicit validation checkpoints and error recovery flows. However, it is severely bloated — the content could easily be split across multiple files and trimmed of explanatory prose that doesn't add value for Claude. The monolithic structure with ~400+ lines of inline content undermines token efficiency and discoverability.

Suggestions

Cut the 'Why Custom KPIs Are Essential' and 'Understanding the customData to KPI Pipeline' sections down to 2-3 bullet points each — Claude doesn't need motivational framing or conceptual pipeline diagrams.

Extract framework-specific integrations (Next.js, FastAPI), edge cases (streaming, error handling, non-OpenAI providers), and KPI formula reference into separate referenced files to reduce the main skill to a focused overview.

Remove redundant code examples — the Quick Start already shows TypeScript and Python patterns; the 'Adding User Information' and 'Adding Custom Data' subsections repeat nearly identical code with minor additions that could be shown as diffs or bullet points.

Consolidate the Quick Reference section with the Quick Start — they serve the same purpose and having both is wasteful.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It includes unnecessary explanatory sections like 'Why Custom KPIs Are Essential' with bullet-point comparisons Claude doesn't need, explains the customData pipeline conceptually before showing code, and repeats similar code patterns across TypeScript/Python/frameworks multiple times. The 'Understanding the customData to KPI Pipeline' section explains concepts that could be a single sentence. Much content could be cut in half while preserving all actionable information.	1 / 3
Actionability	The skill provides fully executable, copy-paste ready code examples for TypeScript and Python, concrete CLI commands for every configuration step, specific before/after code comparisons, and framework-specific integrations (Next.js, FastAPI). Every step has concrete commands or code rather than abstract descriptions.	3 / 3
Workflow Clarity	The multi-step integration process is clearly sequenced (Steps 1-5), and the Test-Validate-Iterate Cycle section provides an explicit validation flow with a decision tree for debugging. The validation flow diagram with specific CLI commands for checking each component and clear fix instructions for common failure modes (string instead of number, null values) demonstrates strong feedback loops.	3 / 3
Progressive Disclosure	Everything is in a single monolithic file with no bundle files to offload content to. The framework-specific integrations, KPI formula reference, edge cases, and detailed agentic workflow examples could all be separate referenced files. The single external reference (https://app.olakai.ai/llms.txt) doesn't compensate for the massive inline content that makes the skill overwhelming to parse.	1 / 3
	Total	8 / 12 Passed

Validation

72%

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 — 8 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (661 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	8 / 11 Passed

Repository: andrewyng/context-hub
Commit: 04c149c

Reviewed: 20 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.