CtrlK
BlogDocsLog inGet started
Tessl Logo

documenso-observability

Implement monitoring, logging, and tracing for Documenso integrations. Use when setting up observability, implementing metrics collection, or debugging production issues. Trigger with phrases like "documenso monitoring", "documenso metrics", "documenso logging", "documenso tracing", "documenso observability".

72

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

SKILL.md
Quality
Evals
Security

Quality

Content

80%

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

Strong actionability and conciseness with complete executable code, but the multi-step build sequence lacks explicit validation checkpoints and progressive disclosure is mishandled: a real reference file goes unlinked while a non-existent runbook is cited.

Suggestions

Add explicit validation steps between the build steps (e.g. after Step 4, 'curl /metrics/documenso and confirm documenso_requests_total increments') to create feedback loops and lift workflow clarity.

Link the existing `references/implementation-guide.md` from the body (e.g. an '## Implementation details' section) and either create or remove the dangling `documenso-incident-runbook` reference in Next Steps.

Consider moving the longer code blocks (e.g. the full instrumented client and alerting rules) into the reference guide, keeping SKILL.md as an overview pointing one level deep.

DimensionReasoningScore

Conciseness

The body is lean: a concise Overview that adds a non-obvious fact (Documenso exposes no rate-limit/usage headers), minimal prerequisites, and executable code throughout. It assumes Claude's competence and avoids explaining basic concepts, so each token earns its place.

3 / 3

Actionability

Each of the six steps provides complete, executable TypeScript/YAML with imports and realistic values (e.g. the Proxy-based instrumented client, winston logger, Express endpoints, Prometheus alerting rules), copy-paste ready rather than pseudocode.

3 / 3

Workflow Clarity

Steps 1–6 are clearly numbered and sequenced (instrument → log → health check → metrics → webhooks → alerting), but there are no explicit validation checkpoints or feedback loops confirming each piece works before moving on. The Error Handling table is reference material, not a workflow checkpoint.

2 / 3

Progressive Disclosure

The body is a single monolithic file with six full inline code sections, and its one Next Steps pointer (`documenso-incident-runbook`) does not exist in the bundle, while the actual `references/implementation-guide.md` is never linked from the body — references are present but poorly signaled and one is dangling.

2 / 3

Total

10

/

12

Passed

Description

100%

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

A well-constructed description: concrete actions, explicit "Use when" guidance, and natural documenso-scoped trigger phrases. Third-person imperative voice is used throughout with no first/second-person. No changes needed.

DimensionReasoningScore

Specificity

"Implement monitoring, logging, and tracing" plus "implementing metrics collection" lists multiple concrete, distinct actions (monitoring, logging, tracing, metrics) rather than vague language.

3 / 3

Completeness

It states what ("Implement monitoring, logging, and tracing") and an explicit "Use when setting up observability, implementing metrics collection, or debugging production issues" clause, covering both what and when.

3 / 3

Trigger Term Quality

Explicit natural trigger phrases are given — "documenso monitoring", "documenso metrics", "documenso logging", "documenso tracing", "documenso observability" — terms a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

The domain is narrowed to Documenso with documenso-prefixed trigger phrases, giving it a clear niche unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.