CtrlK
BlogDocsLog inGet started
Tessl Logo

o11y-logging

Implement and verify joelclaw observability on every change so failures cannot stay silent. Use when adding/updating Inngest functions, gateway channels, webhook providers, APIs, workers, or any pipeline step. Enforces canonical OTEL contract, storage path, and verification gates. Triggers on: 'o11y', 'observability', 'logging', 'otel', 'instrument this', 'silent failure', 'add telemetry', 'log this function'.

73

Quality

91%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a strong, well-crafted skill that provides concrete, executable guidance for implementing observability in the JoelClaw system. It efficiently communicates project-specific conventions, patterns, and verification steps without wasting tokens on concepts Claude already knows. The main weakness is that the Inngest triage section adds length that could be offloaded to a reference file, and the referenced `implementation-checklist.md` cannot be verified.

DimensionReasoningScore

Conciseness

The content is lean and efficient. It avoids explaining what observability is or how OTEL works conceptually—it jumps straight into project-specific rules, conventions, and patterns. Every section earns its place with actionable, domain-specific information Claude wouldn't already know.

3 / 3

Actionability

Provides fully executable TypeScript code examples for worker, gateway, and CLI emission patterns. Commands are copy-paste ready (e.g., `joelclaw otel emit`, `./scripts/otel-smoke.sh`), and the triage section gives specific CLI commands with what to look for in output.

3 / 3

Workflow Clarity

The implementation workflow is clearly sequenced (identify boundary → add envelopes → include context → set severity → verify). The Definition of Done section serves as an explicit validation checklist. The Inngest triage section has a clear numbered diagnostic sequence with verification at each step. The smoke probe acts as a feedback loop.

3 / 3

Progressive Disclosure

References `references/implementation-checklist.md` for detailed checklists, which is good progressive disclosure. However, no bundle files were provided to verify this reference exists, and the Key Files section is a flat list without navigation guidance. The content is moderately long but mostly justified; the Inngest triage section could arguably be in a separate reference file.

2 / 3

Total

11

/

12

Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong skill description that excels in completeness and distinctiveness, with clear 'what' and 'when' clauses and project-specific terminology that minimizes conflict risk. The trigger terms are comprehensive and natural. The main weakness is that the core capabilities could be more concretely specified—listing specific actions like 'add span instrumentation, configure metric exporters, set up structured logging' would strengthen specificity.

Suggestions

Replace abstract phrases like 'implement and verify observability' with more concrete actions such as 'add OTEL spans, configure metric exporters, set up structured log pipelines, validate trace propagation'.

DimensionReasoningScore

Specificity

Names the domain (observability/telemetry) and some actions ('implement and verify', 'enforces canonical OTEL contract, storage path, and verification gates'), but the core actions are somewhat abstract—'implement observability' is broad, and 'verification gates' is vague without specifying what those gates entail concretely.

2 / 3

Completeness

Clearly answers both 'what' (implement/verify observability, enforce OTEL contract, storage path, verification gates) and 'when' (adding/updating Inngest functions, gateway channels, webhook providers, APIs, workers, pipeline steps) with explicit trigger terms listed.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms including both technical ('o11y', 'otel', 'telemetry') and conversational ('instrument this', 'silent failure', 'log this function', 'logging') variations that users would naturally say.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive—targets a specific observability stack (joelclaw, OTEL) for specific infrastructure components (Inngest functions, gateway channels, webhook providers). The project-specific terminology ('joelclaw') and explicit trigger terms make conflicts with other skills very unlikely.

3 / 3

Total

11

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
joelhooks/joelclaw
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.