snippets

Create and manage prompt snippets — reusable text blocks referenced inside config variation prompts. Keeps common instructions, personas, and guardrails consistent across multiple configs.

Quality

51%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/agentcontrol/snippets/SKILL.md

Quality

Content

35%

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

The skill provides a reasonable structure for managing prompt snippets but is undermined by verbosity (explaining concepts Claude already knows), an incomplete workflow (missing the critical step of actually referencing snippets in config variations), and redundant sections. The JSON examples for creation and updates are helpful, but the most important action—wiring snippets into configs—is conspicuously absent despite being mentioned in the skill description.

Suggestions

Remove the 'What Are Prompt Snippets?', 'When to Use Snippets', 'When NOT to Use Snippets', and 'Core Principles' sections—condense to 2-3 bullet points of non-obvious guidance. Claude understands reusability and naming conventions.

Add a concrete example showing how to reference a snippet in a config variation using `update-ai-config-variation`, including the exact JSON payload—this is the skill's stated purpose but is never demonstrated.

Merge the 'What NOT to Do' section into the Edge Cases table to eliminate redundancy, and remove entries that restate obvious principles.

Add error handling guidance: what to do if `create-prompt-snippet` fails (e.g., key conflict), and how to verify that a config variation correctly picked up a snippet reference.

Dimension	Reasoning	Score
Conciseness	The skill is verbose and explains concepts Claude already understands. The 'What Are Prompt Snippets?' section, the 'When to Use Snippets' table, the 'When NOT to Use Snippets' list, and the 'Core Principles' section all explain things Claude can infer from the tool names and parameters. The 'What NOT to Do' section largely repeats the Core Principles. Significant token waste.	1 / 3
Actionability	The skill provides concrete JSON examples for create and update operations, and names specific MCP tools. However, it lacks executable examples for the full workflow of referencing snippets in config variations (Step 4 of the workflow is about updating snippets, not about actually wiring snippets into configs via `update-ai-config-variation`). The most critical action—how to reference a snippet in a config variation prompt—is never shown.	2 / 3
Workflow Clarity	Steps are listed in a clear sequence with a verification step (Step 3), which is good. However, the workflow is incomplete—it describes creating and verifying snippets but never shows the key step of actually referencing snippets in config variation prompts, despite listing `update-ai-config-variation` as an optional tool. The workflow also lacks error recovery for failed creation or update operations.	2 / 3
Progressive Disclosure	The content is reasonably structured with clear sections and headers, but it's monolithic—all content is inline in a single file with no references to external files. Given the length (~120 lines of substantive content), the edge cases table and anti-patterns could be separated or the document could be significantly trimmed. No bundle files exist to reference.	2 / 3
	Total	7 / 12 Passed

Description

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 reasonably strong in specificity and distinctiveness, clearly defining what prompt snippets are and their purpose within a config variation system. Its main weaknesses are the lack of an explicit 'Use when...' clause and somewhat niche trigger terms that may not match natural user language. Adding explicit trigger guidance and more natural keyword variations would improve selection accuracy.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to create, edit, or reference reusable prompt snippets, shared text blocks, or template content for config variations.'

Include more natural keyword variations users might say, such as 'shared prompts', 'prompt templates', 'reusable instructions', or 'snippet library'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'create and manage prompt snippets', 'reusable text blocks referenced inside config variation prompts', and specifies use cases like 'common instructions, personas, and guardrails'. These are specific, actionable capabilities.	3 / 3
Completeness	The 'what' is well-covered (create/manage prompt snippets, reusable text blocks). However, there is no explicit 'Use when...' clause or equivalent trigger guidance — the description only implies when it should be used through the explanation of what it does. Per rubric guidelines, missing 'Use when' caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant terms like 'prompt snippets', 'reusable text blocks', 'config variation prompts', 'personas', 'guardrails', but these are somewhat domain-specific. Missing more natural user phrases like 'shared prompts', 'template text', or 'prompt reuse'. A user might not naturally say 'prompt snippets' without prior knowledge of this system.	2 / 3
Distinctiveness Conflict Risk	The description carves out a clear niche: prompt snippets specifically for config variation prompts. The combination of 'snippets', 'config variation', and 'reusable text blocks' is distinctive enough to avoid conflicts with general prompt-writing or config-editing skills.	3 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: launchdarkly/ai-tooling
Commit: 913b745

Reviewed: 10 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.