iii-observability

OpenTelemetry-backed tracing, structured logs, metrics with rollups, alerts, sampling, and baggage for the engine — emit and query telemetry through `engine::*` functions and react to logs with a `log` trigger.

Quality

75%

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 ./engine/src/workers/observability/skills/SKILL.md

Quality

Content

75%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 content is well-organized, lean, and actionable with a concrete trigger-binding example, performing solidly across all dimensions. The main uplift is adding executable call examples for the emit/query functions and an explicit validation note for the destructive clear operations.

Suggestions

Add one or two executable `engine::log::*` / `engine::logs::list` call examples so the common emit/query path is copy-paste ready, not just listed.

Note the destructive nature of `engine::logs::clear` / `engine::traces::clear` with a brief confirm-before-clear guidance to add a validation checkpoint.

Consider extracting the full Functions list into a `references/functions.md` to keep SKILL.md a tighter overview.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's familiarity with OTel, spending tokens on genuinely engine-specific details (OTEL_* env vars, exporter protocols); a few framing sentences could still be trimmed.	4 / 5
Actionability	Concrete `engine::*` function names and a copy-paste-ready TypeScript trigger-binding example are provided, but the emit/query functions are only listed rather than shown with executable call examples.	4 / 5
Workflow Clarity	The "How to bind" section gives a clear two-step sequence with surrounding behavior notes; the workflow is non-destructive so the missing-validation cap does not apply, though no explicit validation checkpoint is given.	4 / 5
Progressive Disclosure	No bundle files exist and the single file is well-sectioned (When to Use, Boundaries, Functions, Reactive triggers, How to bind); the fairly long Functions list could arguably move to a reference file, leaving a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

75%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 is specific, distinct, and rich in natural trigger terms, but it omits an explicit "when to use" clause, which caps completeness. Adding a Use-when sentence would lift it to the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use when instrumenting the iii engine for telemetry or reacting to log entries in real time."

Add a couple of natural synonyms ("monitoring", "observability") so users phrase-matching those terms land on this skill.

Keep the concrete action list as-is — it already anchors specificity and distinctiveness well.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "tracing, structured logs, metrics with rollups, alerts, sampling, and baggage" plus "emit and query telemetry" and "react to logs with a `log` trigger" — giving comprehensive coverage of the observability domain.	5 / 5
Completeness	The "what" is clearly stated, but there is no explicit "Use when…" clause or equivalent trigger guidance, so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural keywords like "tracing", "logs", "metrics", "alerts", "sampling", "telemetry", and "OpenTelemetry" are present, but common synonyms such as "monitoring" or "observability" are absent.	4 / 5
Distinctiveness Conflict Risk	It carves a clear OpenTelemetry-for-the-engine niche with distinct `engine::*` and `log` trigger surfaces, minimizing overlap with unrelated skills.	5 / 5
	Total	17 / 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: iii-hq/iii
Path: engine/src/workers/observability/skills/SKILL.md
Commit: 2c8976b

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.