CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

alert-investigation

Investigates a firing or recently fired observability alert: finds the firing and replays the value it evaluated, decides whether the alert is chronic noise or a new problem, reuses any automatic investigation, then finds the cause (what changed, which host, version or route is over-represented) and returns a structured diagnosis with cause, scope and next steps.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

An exemplary operational skill body: every step is driven by named MCP tools with exact arguments, explicit decision gates, failure branches, and a concrete output template for on-call handoffs. The only real critiques are minor — inlined API-return enumerations that could live in a reference file, and companion-file references that lack resolvable paths.

DimensionReasoningScore

Conciseness

The body is lean and operational, assumes Claude's competence (e.g. "A P99 over about 600 spans per window is the sixth-slowest span"), and explains nothing the model already knows — but the field-by-field enumerations of `evaluation`, `firings` and `summary` return values in steps 1 and 3 read as inlined API reference that could be trimmed or offloaded. This places it at level 4 (efficient with minor trims possible) rather than level 5 (every token earns its place).

4 / 5

Actionability

Guidance is fully executable: exact tool calls with exact arguments ("call `get-alert-firing-history` with the `alertId` and `lookbackDays: 7`", "Add `compareTo: \"1w\"`", "run the replay over 3 to 7 days with `bucketCount` 24 to 48"), concrete decision rules ("> 4 of the last 7 days"), a copy-paste output template, and concrete retune examples ("P95 > 1 s with a minimum of 200 spans"). Per the rubric's scoring note, an instruction-only skill without code is not penalized when guidance is this actionable, and there are no gaps — common cases (no alert ID, NoData, unshared investigation, config drift) are each handled.

5 / 5

Workflow Clarity

A clear five-step sequence (find alert → replay value → chronic/new verdict → reuse investigation → investigate cause) with explicit gates and error-recovery branches: "Decide this before you look for a cause", "If it is chronic, say so… If it is new… carry on", "If it says the investigation is not shared with you, do not retry", and "set `exact: true` if the result says `estimated: true`". The work is read-only investigation, so the destructive/batch validation cap does not apply; checkpoints are explicit at every step, matching level 5 rather than the most-checkpoints level 4.

5 / 5

Progressive Disclosure

Good structure: a dedicated "When to load which companion" section cleanly signals which per-product file to load (logs.md, traces.md, errors.md, sessions.md, metrics.md), and the sibling investigate skill is linked with its purpose stated. However the companion filenames carry no resolvable paths or links in the bundle, and API-return detail is inlined, which fits level 4 (good structure, minor organization gaps) rather than level 5 (fully well-signaled, easy navigation).

4 / 5

Total

18

/

20

Passed

Description

71%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 highly specific, action-dense description that clearly communicates what the skill does and carves out a distinct alert-diagnosis niche. Its main weakness is the absence of an explicit "Use when…" trigger clause, leaving the activation condition implied rather than stated, and slightly thin synonym coverage for natural trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks why an alert is firing, whether an alert is real or noise, or what caused a pager/incident."

Include common user-side synonyms such as "incident", "pager", and "on-call" so the description matches the phrasing users naturally use when an alert fires.

Clarify the boundary with sibling skills (e.g. "for the alert-specific steps around a general investigation") so it is distinguishable from the broader 'investigate' skill at the description level, not just in the body.

DimensionReasoningScore

Specificity

The description lists multiple distinct concrete actions — "finds the firing and replays the value it evaluated", "decides whether the alert is chronic noise or a new problem", "reuses any automatic investigation", "returns a structured diagnosis with cause, scope and next steps" — covering the full investigation arc comprehensively, which matches the level-5 anchor rather than the minor-gaps level-4 anchor.

5 / 5

Completeness

The "what" is explicit and detailed, but there is no "Use when…" clause or equivalent explicit trigger guidance — the "when" is only implied through the object "a firing or recently fired observability alert", which per the judging guidelines caps completeness at 3. It is not 4 because no explicit trigger clause exists that could be made more specific.

3 / 5

Trigger Term Quality

Natural terms like "firing", "observability alert", "chronic noise" and "diagnosis" are exactly what a user would say, but common variations such as "incident", "pager", "on-call" or "why did this alert fire" are absent, so coverage is good-but-incomplete (level 4) rather than comprehensive with synonyms (level 5).

4 / 5

Distinctiveness Conflict Risk

The niche (diagnosing a firing observability alert, with a chronic-vs-new verdict) is clear and specific, but the skill family includes closely related siblings (a general "investigate" skill and "observability/alert-management" guides), giving minor overlap risk — matching level 4 rather than the minimal-conflict level 5 or the broader-overlap level 3.

4 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 4 suspicious

Warning

Total

15

/

16

Passed

Repository

launchdarkly/ai-tooling

Path

skills/observability/alert-investigation/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.