new-project

Build a new AI agent with Olakai monitoring from scratch — project setup, SDK integration, KPI configuration, and end-to-end validation

Quality

61%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./content/olakai/skills/new-project/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 on specificity and distinctiveness, clearly outlining a concrete workflow for building AI agents with Olakai monitoring. However, it lacks an explicit 'Use when...' clause, which is critical for Claude to know when to select this skill, and could benefit from more natural trigger terms that users might actually say.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create a new AI agent project with Olakai observability, or asks about setting up monitoring for an agent from scratch.'

Include additional natural trigger terms users might say, such as 'observability', 'agent monitoring', 'instrument', 'tracking', 'new agent project', or 'Olakai setup'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: project setup, SDK integration, KPI configuration, and end-to-end validation. These are distinct, actionable steps in a clear workflow.	3 / 3
Completeness	Clearly answers 'what does this do' (build a new AI agent with Olakai monitoring, covering setup through validation), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric guidelines.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'AI agent', 'Olakai', 'SDK integration', 'KPI configuration', but misses common user variations like 'observability', 'monitoring setup', 'new project', 'tracking', or 'instrumentation'. The term 'Olakai' is a strong brand trigger but natural user phrasing variations are limited.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Olakai monitoring', 'AI agent', and the specific workflow (project setup through end-to-end validation) creates a clear niche that is unlikely to conflict with other skills. The brand name 'Olakai' is a strong distinguishing factor.	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 complete, executable code in multiple languages and a well-structured validation workflow with explicit error recovery steps. However, it is severely bloated — much of the content (formula references, task categories, motivational sections, duplicate implementations across languages) should be extracted into separate reference files or removed entirely. The monolithic structure and verbose explanations significantly undermine its effectiveness as a skill document.

Suggestions

Extract the KPI Formula Reference, Task Categories Reference, and language-specific implementation examples into separate referenced files (e.g., FORMULAS.md, EXAMPLES_TS.md, EXAMPLES_PY.md) to reduce the main skill to an overview with navigation links.

Remove the 'Why Custom KPIs Are Essential' section and the 'What NOT to Include in customData' table — these are explanatory/motivational content that Claude doesn't need; replace with a single-line constraint like 'Do not duplicate auto-tracked fields (session ID, tokens, model, timestamp, etc.) in customData.'

Cut the 'Understanding the customData to KPI Pipeline' section down to just the pipeline diagram and critical rules table — the prose explanations of each stage are unnecessary.

Remove the 'Built-in Context Variables' table from the main file and reference it from a separate doc, as it's reference material not needed for the core workflow.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~500+ lines. It explains concepts Claude already knows (what KPIs are, what business questions look like), includes extensive tables of built-in variables and task categories that belong in reference docs, and the 'Why Custom KPIs Are Essential' section is motivational fluff. The 'What NOT to Include' table and many explanatory paragraphs add significant token bloat.	1 / 3
Actionability	The skill provides fully executable CLI commands, complete TypeScript and Python code examples, REST API curl commands, and specific JSON output examples. Every step has concrete, copy-paste ready commands and code.	3 / 3
Workflow Clarity	The 5-step workflow is clearly sequenced with explicit validation in Step 4 including a visual validation flow diagram, specific checks for common failure modes (string vs numeric values, null values), and a feedback loop for fixing issues. The production checklist adds a final verification gate.	3 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. The KPI Formula Reference, Task Categories Reference, full Python/TypeScript implementations, and REST API examples should be split into separate reference documents. Everything is inlined in a single massive file with no navigation to supplementary materials.	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 (642 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: eeb895b

Reviewed: 5 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.