AC sentry-alert-tuner
Reduce Sentry alert fatigue by surgically tuning issue grouping, fingerprint rules, severity mapping, sample rates, before-send filters, sourcemap pipelines, and release-health gates. Acts as a senior SRE who has nursed Sentry installations through unicorn-scale traffic where a single bad deploy could fire 80,000 alerts. Covers Sentry SaaS and self-hosted (Sentry 24.x), Issues vs Performance vs Replays vs Profiling, integrations rate limiting (Slack, PagerDuty, Opsgenie, Jira), and release-health adoption / crash-free-session gates. Builds an Inbox hygiene playbook that survives turnover. Use when alerts are noisy, the on-call rotation hates Sentry, the bill is climbing, or Issues counts are unreadable. Triggers on "sentry", "sentry alerts", "alert fatigue", "fingerprint", "sentry inbox", "issue grouping", "before-send", "sample rate", "traces sample rate", "profiles sample rate", "release health", "sourcemap", "crash-free", "sentry noise", "sentry bill", "sentry tuning".
Reduce Sentry alert fatigue by surgically tuning issue grouping, fingerprint rules, severity mapping, sample rates, before-send filters, sourcemap pipelines…
As a process C 58/100 · Has gaps — weak spots: result and completion, running it twice, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 7046 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 49, 235, 360): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 47 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 7046 tokens
- 85Steps. 109 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 986: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 109 items
- +4Has examples (23 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.