slos-and-triggers

Decision heuristics for interpreting Honeycomb SLO compliance, budget burn rates, and trigger status — what the numbers mean and what action to take, including detecting misconfigured SLIs, deciding when to freeze deploys vs page on-call, and designing burn alert thresholds. Load this skill before calling get_slos or get_triggers. Trigger phrases: "check our SLOs", "are we meeting our SLOs", "which SLOs are healthy", "is the error budget OK", "are any alerts firing", "what's the burn rate", "set up an SLO", "create a trigger", "configure alerts", "set up burn alerts", "check trigger status", "starting on-call", "reliability picture", "should we freeze deploys", "is this SLO misconfigured", "are we within budget", "SLO is broken", "budget is negative", or any request about service level objectives, error budgets, burn rates, or alerting in Honeycomb.

1.42x

Quality

96%

Does it follow best practices?

Impact

100%

1.42x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Quality

Content

93%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, actionable body that offloads depth to real reference files and gives concrete formulas and thresholds throughout. The only gap is the absence of an explicit post-create validation/feedback loop for SLO and trigger configuration.

Suggestions

Add an explicit validation step after creating an SLO or trigger (e.g., re-query with get_slos/get_triggers to confirm the object exists with expected settings, and fix-and-retry if it does not), turning the create flow into a true validate→fix→retry loop.

Surface a short concrete 'verify SLI is populated' check (e.g., confirm the calculated field returns 1/0 rather than undefined on a sample) to catch the misconfigured-SLI case the skill already flags.

Dimension	Reasoning	Score
Conciseness	Lean throughout — it assumes Claude knows what SLOs/triggers are and spends tokens only on Honeycomb-specific design rules, formulas, and thresholds, with no padding or elementary concept explanation.	5 / 5
Actionability	Provides copy-paste-ready specifics: SLI formula syntax ('IF(<qualifying-condition>, <success-condition>)', 'LTE(duration_ms, 500)'), concrete alert thresholds (4h exhaustion, 1h burn > 10x), trigger query patterns ('COUNT WHERE duration_ms > 2000'), and explicit status-to-action mappings.	5 / 5
Workflow Clarity	The SLO design flow is sequenced (define SLI → set target → exhaustion alerts → burn alerts) and includes a 'Check in with the user' confirmation gate before the create tool, but there is no explicit validate-then-retry feedback loop for the create/configure operations the skill drives.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview that signals three one-level-deep, real reference files (slo-design-guide.md, trigger-examples.md, alerting-strategy.md) plus targeted cross-references to the query-patterns and production-investigation skills, with detail appropriately offloaded.	5 / 5
	Total	19 / 20 Passed

Description

100%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.

An exemplary description: it concisely states concrete capabilities, supplies a rich set of natural trigger phrases, and is tightly scoped to the Honeycomb SLO/trigger domain with minimal conflict risk. No changes needed.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'interpreting Honeycomb SLO compliance, budget burn rates, and trigger status', 'detecting misconfigured SLIs', 'deciding when to freeze deploys vs page on-call', and 'designing burn alert thresholds' — giving comprehensive, specific coverage rather than vague verbs.	5 / 5
Completeness	Explicitly answers both 'what' (decision heuristics for interpreting SLO/budget/trigger numbers and the actions to take) and 'when' (a long list of concrete trigger phrases), with the 'Load this skill before calling get_slos or get_triggers' directive closing the loop.	5 / 5
Trigger Term Quality	Comprehensive natural phrases users would actually say, including synonyms and variants ('check our SLOs', 'is the error budget OK', 'what's the burn rate', 'should we freeze deploys', 'budget is negative'), plus a broad catch-all clause for related requests.	5 / 5
Distinctiveness Conflict Risk	A clearly bounded Honeycomb-specific niche (SLOs, error budgets, burn rates, triggers) with distinctive trigger phrases and a load directive tied to specific tools, leaving minimal overlap with unrelated skills.	5 / 5
	Total	20 / 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: honeycombio/agent-skill
Path: honeycomb/skills/slos-and-triggers/SKILL.md
Commit: 41214b7

Reviewed: 5 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.