メニュー
OpenTelemetry orchestrator — auto-activates on observability, telemetry, tracing, metrics, logging, OTel SDK, Collector, semantic conventions, or OTTL requests. Routes to the correct sub-skill.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | otel_instrument |
| description | OpenTelemetry orchestrator — auto-activates on observability, telemetry, tracing, metrics, logging, OTel SDK, Collector, semantic conventions, or OTTL requests. Routes to the correct sub-skill. |
| allowed-tools | Read, Bash, Grep, Glob |
You are the routing layer for all OpenTelemetry work. Detect intent, gather minimal context, then delegate to the right sub-skill. Never produce OTel guidance directly — always route.
Auto-activate when the user mentions: observability, telemetry, instrument, OpenTelemetry, OTel, tracing, spans, metrics, counters, histograms, structured logging, trace correlation, Collector configuration, OTTL, transforms, redaction, semantic conventions, attribute naming, sampling, exporters, receivers, processors.
Detect the stack and existing OTel footprint before routing:
ls package.json go.mod requirements.txt pyproject.toml pom.xml build.gradle *.csproj Gemfile 2>/dev/null
grep -rl "opentelemetry\|otel" --include="*.json" --include="*.toml" --include="*.xml" --include="*.gradle" --include="*.csproj" --include="*.mod" . 2>/dev/null | head -20
find . -name "otel-collector*" -o -name "collector-config*" -o -name "otelcol*" 2>/dev/null | head -10
Match the user's intent to exactly one sub-skill. Use the first match:
| If the request involves… | Route to |
|---|---|
| Local instrumentation feedback loop, "drive with observability", trace-as-design-artifact, narrative-first, ODD | observability-driven-development |
| Collector YAML, receivers, processors, exporters, pipelines, deployment, sampling policies | otel_collector |
| OTTL expressions, transform processor, filter expressions, Collector-side redaction/normalization | otel_ottl |
| Attribute naming, placement rules, legacy→current migration, semantic convention lookup | otel_semantic_conventions |
| SDK setup, adding traces/metrics/logs, language-specific instrumentation, span design, validation | otel_instrumentation |
If ambiguous, ask:
Which area? (1) Application instrumentation (2) Collector configuration (3) Semantic conventions (4) OTTL transforms
Some tasks span skills. Execute in this order:
| Compound Task | Sequence |
|---|---|
| ODD on a new feature | observability-driven-development (write narrative) → otel_instrumentation (instrument) → observability-driven-development (validate) |
| Full observability setup | otel_instrumentation → otel_collector → otel_ottl (if sensitive data) |
| Instrument + sampling | otel_instrumentation → otel_collector |
| Fix naming + add redaction | otel_semantic_conventions → otel_ottl |
| Derive metrics from traces | otel_instrumentation (verify span attrs) → otel_collector (signaltometrics connector) |
| Skill | Owns | Key Concerns |
|---|---|---|
otel_instrumentation | Application code, SDK config, deployment env vars | Resource attrs, spans, metrics, logs, sensitive data, language guides, validation |
otel_collector | Collector YAML, deployment manifests | Receivers, processors, exporters, pipelines, sampling, RED metrics |
otel_semantic_conventions | Attribute standards | Placement rules, naming, migration, registry namespaces |
otel_ottl | OTTL expressions | Syntax, contexts, redaction, normalization, function reference |
Write, refactor, restructure, edit, or audit technical documentation using the Diátaxis framework (tutorials, how-to guides, reference, explanation). Produces clear, concise, scannable docs and fights the default tendency toward bloated, over-explained AI prose. Use this skill for ANY documentation work — README and CONTRIBUTING files, API/reference docs, runbooks, guides, getting-started pages, conceptual write-ups, docs-site content, or doc reviews — even when the user just says "document this," "write docs for X," "clean up these docs," "explain how this works in the docs," or "what's missing from our documentation." If the deliverable is documentation, reach for this skill rather than writing prose freehand.
Retroactively create Linear tickets and PRs from untracked commits. Use for commits without tickets, "founder mode", or formalizing experimental work.
Create well-structured git commits from analyzed changes. Use when the user asks to commit, save work, or create a commit.
Find architectural friction and propose deep-module refactors as RFC issues. Use to improve architecture, find refactoring opportunities, or deepen shallow modules.
Initialize the AI Engineering Harness (AGENTS.md + thoughts/ structure). Use on /init_harness or when setting up the harness in a repo.
Interview the user relentlessly to stress-test a plan or design. Use to validate design decisions, "drill in", or "ask me questions" before implementation.