alert-investigation

Investigates a triggered observability alert and returns a structured diagnosis with likely cause, scope, and next steps.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/observability/alert-investigation/SKILL.md

Quality

Content

82%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 body is a lean, well-structured overview that points cleanly to per-product companions and gives a concrete output template and strong guidelines. It is held back slightly by implicit (rather than explicit) workflow checkpoints, an external cross-reference to another skill, and companion files that are referenced but not bundled.

Suggestions

Inline or summarize the key steps of the 'investigate skill' methodology referenced in workflow step 3 so the skill is self-contained rather than deferring to another skill.

Add an explicit validation/checklist step to the workflow (e.g. 'Confirm every claim cites a specific identifier before producing the diagnosis') to reach the explicit-checkpoint anchor.

Bundle the referenced companion files (logs.md, traces.md, errors.md, sessions.md, metrics.md) under references/ so the signaled navigation resolves to real files.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: no concept-padding, no over-explanation, and each section (prerequisites, workflow, output template, companion map, guidelines) earns its place.	5 / 5
Actionability	Provides a concrete output template and specific guidance (cite identifiers, noise handling, per-product companions), but workflow step 3 defers to 'the methodology from the investigate skill' without inlining it and lists MCP tools without concrete invocation arguments, leaving minor gaps.	4 / 5
Workflow Clarity	A clear four-step sequence scoped to the alert's time range and filter; checkpoints are only implicit rather than explicitly stated, so it sits just below the explicit-validation anchor.	4 / 5
Progressive Disclosure	Well-signaled one-level-deep references to per-product companions (logs.md, traces.md, etc.) with a clear overview; held below 5 because those referenced companion files are not present in the references/ bundle, so navigation is signaled but not fully realized.	4 / 5
	Total	17 / 20 Passed

Description

58%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 clearly conveys what the skill does in third person with concrete capabilities, but omits any explicit 'Use when...' trigger guidance, which limits completeness and trigger-term quality. Distinctiveness is good for its niche.

Suggestions

Add an explicit 'Use when...' clause naming the natural trigger phrases users say (e.g. 'Use when an observability alert fires, a page comes in, or the user asks to investigate a triggered alert').

Expand trigger-term coverage with user-natural synonyms like 'alert fired', 'page', 'on-call investigation', and 'alert triage' alongside the existing 'observability alert' phrasing.

Consider listing one or two more concrete diagnostic actions (e.g. 'correlates traces, logs, and error groups') to push specificity toward a 5.

Dimension	Reasoning	Score
Specificity	Third-person voice ('Investigates ... and returns a structured diagnosis') names the domain and several concrete actions (diagnosis with likely cause, scope, next steps); not a full 5 because action coverage is broad rather than enumerating multiple distinct concrete operations.	4 / 5
Completeness	The 'what' is clearly stated, but there is no 'Use when...' or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant terms ('triggered observability alert', 'structured diagnosis') but lacks common natural synonyms a user would actually say (e.g. 'alert fired', 'alert triggered', 'page', 'on-call'), so keyword coverage is partial.	3 / 5
Distinctiveness Conflict Risk	The observability-alert-investigation niche is fairly specific with distinct triggers and only minor overlap risk with general debugging or monitoring 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/observability/alert-investigation/SKILL.md
Commit: 0aef88f

Reviewed: 3 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.