CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

71%

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/agentcontrol/snippets/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The content is a well-structured, actionable single-file skill: concrete tool calls, JSON examples, explicit verification, and destructive-operation safeguards. Its main gaps are the missing workflow step for wiring snippets into config variations (the skill's stated goal) and light redundant padding.

Suggestions

Add a workflow step (with an update-agent-config example payload) showing how to reference a snippet inside a config variation prompt, since the intro lists it as a core job but no step covers it.

Add a post-update verification step (re-fetch the snippet and confirm the new version number) to close the feedback loop, and merge the redundant get-prompt-snippets bullets in Step 3.

DimensionReasoningScore

Conciseness

The body is efficient — tables for when-to-use/edge cases, no re-teaching of concepts Claude already knows (prompt snippets are a LaunchDarkly-specific feature) — with only minor trimmable padding such as the "You're using a skill that will guide you through..." opener and slight overlap between the Edge Cases table and "What NOT to Do".

4 / 5

Actionability

Concrete MCP tool names with parameter explanations and copy-paste-ready JSON examples for create and update make the guidance mostly executable; the gap is that referencing snippets in config variations — a stated job of the skill — has no workflow step or example (update-agent-config appears only as an optional tool).

4 / 5

Workflow Clarity

Steps 1–4 are clearly sequenced with an explicit verification step ("Use get-prompt-snippets to confirm the snippet was created... Check that version is 1") and destructive-op safeguards ("Warn the user... use delete-prompt-snippet with confirm: true"), but there is no re-verify loop after updates and Step 3's two nearly identical get-prompt-snippets bullets add redundancy rather than checkpoints.

4 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the ~124-line single-file body is well organized into scannable sections with one clearly signaled one-level-deep external link under "More resources"; content is appropriately placed, with only minor opportunity to split detail (e.g., edge-case handling) out.

4 / 5

Total

16

/

20

Passed

Description

53%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 communicates a clear purpose and niche, but lacks any explicit "when to use" trigger guidance and leans on product jargon ("prompt snippets") without natural synonyms a user would say. Actions are named but only at a coarse create/manage level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user mentions prompt snippets, reusable prompt text, shared personas or guardrails, or wants consistency across LaunchDarkly AI config variations."

Enumerate the concrete operations instead of the generic "manage": "Create, update, and delete prompt snippets; browse existing ones; reference them in config variation prompts."

Include natural synonyms and user phrasings ("reusable prompt text", "shared instructions", "persona block") so the skill triggers on how users actually describe the task.

DimensionReasoningScore

Specificity

"Create and manage prompt snippets" names the domain with two actions, but "manage" is generic and no finer-grained operations (update, delete, browse, reference in configs) are listed, matching the anchor for 1-2 concrete actions rather than several specific ones.

3 / 5

Completeness

The "what" is clear ("Create and manage prompt snippets — reusable text blocks referenced inside 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

Relevant keywords are present ("prompt snippets", "reusable text blocks", "personas", "guardrails") but "prompt snippets" is product jargon and natural user phrasings or synonyms users would actually say are missing, matching the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Prompt snippets" tied to "config variation prompts" carves a mostly distinct niche with only minor overlap risk against a closely related LaunchDarkly config/prompt-authoring skill; it is not a fully clear niche since no distinct trigger phrases set it apart.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

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.