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

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%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.

A well-structured, largely actionable body with concrete tool usage, verification steps, and thoughtful edge-case and anti-pattern coverage. The main improvement opportunities are demonstrating the snippet-reference syntax in variation prompts, adding a validation loop after updates, and trimming the small duplications between sections.

Suggestions

Add a short example of referencing a snippet inside a config variation prompt (e.g., the `update-ai-config-variation` call showing the snippet reference syntax), since wiring snippets into variations is a stated core task but never shown.

Add a verification step after Step 4 (e.g., use `get-prompt-snippet` to confirm the new version and check that referencing configs picked it up), and cover it in the edge-case table for propagation.

Trim the redundant guidance where Core Principle 1 ("Only create a snippet if the text will be used in 2+ places") repeats the first "What NOT to Do" bullet.

Dimension	Reasoning	Score
Conciseness	The body is efficient overall — tight tables for when-to-use/edge cases and copy-paste JSON examples — with only minor over-explanation: the intro paragraph ("Your job is to identify reusable text, create snippets, reference them...") narrates the workflow re-presented later, and Core Principle 1 duplicates the first "What NOT to Do" bullet.	4 / 5
Actionability	Concrete MCP tool names, per-tool parameter lists, and complete JSON payloads for create and update make the guidance mostly executable; the notable gap is that referencing a snippet inside a variation via `update-ai-config-variation` is named as a tool but never demonstrated with syntax or an example.	4 / 5
Workflow Clarity	Steps 1–4 are clearly sequenced with an explicit verify step (get-prompt-snippet, list, check version) and edge-case recovery (duplicate key → check then update or re-key; delete → warn + `confirm: true`); minor gaps remain, such as no validation loop after Step 4 snippet updates or after wiring references into variations.	4 / 5
Progressive Disclosure	A single well-organized file with clear section headers and one external docs link; at ~125 lines it exceeds the under-50-line simple-skill exception, and content such as the edge-case table or JSON examples could arguably live in reference files, but the current structure is easy to navigate.	4 / 5
	Total	16 / 20 Passed

Description

61%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.

A clear, specific third-person description of what the skill does, but it lacks any explicit "when to use" trigger clause, which limits both completeness and discoverability. Adding a use-when clause with concrete trigger phrases would lift it into the top tier.

Suggestions

Append an explicit trigger clause, e.g. "Use when creating or updating AI config variations that share repeated prompt text, or when the user mentions snippets, personas, guardrails, or reusable prompt blocks."

Enumerate the concrete operations (create, list, update, delete snippets and reference them in variation prompts) to strengthen the specificity of capabilities.

Include common user synonyms such as "reusable prompt text", "shared prompt blocks", or "AI config prompts" to broaden natural trigger coverage.

Dimension	Reasoning	Score
Specificity	"Create and manage prompt snippets" names the domain with two concrete actions, but does not enumerate the fuller set of operations (list, update, delete, reference in variations), matching anchor 3 rather than the several-action coverage of anchor 4.	3 / 5
Completeness	The "what" is clear (create and manage prompt snippets for config variation prompts), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	Natural terms like "prompt snippets", "personas", "guardrails", "instructions", and "config variation prompts" give good keyword coverage a LaunchDarkly user would plausibly say, though common synonyms such as "reusable prompt text" or "AI configs" are missing.	4 / 5
Distinctiveness Conflict Risk	"Prompt snippets — reusable text blocks referenced inside config variation prompts" carves a clear niche that is unlikely to fire for unrelated skills; minor overlap risk remains with generic snippet-management skills.	4 / 5
	Total	14 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: launchdarkly/ai-tooling
Path: skills/agentcontrol/snippets/SKILL.md
Commit: ef54971

Reviewed: 6 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.