CtrlK
BlogDocsLog inGet started
Tessl Logo

deepgram-incident-runbook

Execute Deepgram incident response procedures for production issues. Use when handling Deepgram outages, debugging production failures, or responding to service degradation. Trigger: "deepgram incident", "deepgram outage", "deepgram production issue", "deepgram down", "deepgram emergency", "deepgram 500 errors".

67

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

The body is highly actionable with executable code across all severity tiers and a clear sequence, but it is over-inlined: it duplicates content already in the references bundle without linking to it, and lacks explicit validation feedback loops for its risky fallback/replay operations.

Suggestions

Replace the inlined triage script and duplicated SEV/post-incident templates in the body with brief summaries and links to references/implementation.md to remove redundancy and improve progressive disclosure.

Add explicit validation checkpoints to the SEV1 fallback and replay workflow (e.g., verify queue integrity before replay, confirm service recovery before exiting fallback mode) with a fix→retry loop.

Trim redundant inline comments such as '// Disable to reduce processing' and '// Fallback to proven model' that restate the obvious intent of the config.

DimensionReasoningScore

Conciseness

Mostly efficient executable content with little concept-explanation padding, but the ~300-line body duplicates material already in references/implementation.md (triage script, SEV configs, post-incident template) and carries some redundant inline comments.

2 / 3

Actionability

Provides fully executable bash triage, TypeScript fallback/mitigation services, and concrete config objects — copy-paste ready with specific commands and examples.

3 / 3

Workflow Clarity

Steps are clearly sequenced by severity (Step 1–6) with an escalation matrix, but fragile operations like the fallback queue and replay lack explicit validate→fix→retry checkpoints, which caps the score at 2.

2 / 3

Progressive Disclosure

The body has structure but content that belongs in references (full triage script, templates) is inlined, and the existing references/implementation.md bundle is never linked from the body — references present but not clearly signaled.

2 / 3

Total

9

/

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.

The description cleanly answers what the skill does and when to use it, with concrete actions and natural trigger terms. It is well-distinguished from other skills by its Deepgram-specific framing.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Execute Deepgram incident response procedures', 'debugging production failures', 'responding to service degradation' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what ('Execute Deepgram incident response procedures for production issues') and when ('Use when handling Deepgram outages...') with explicit triggers.

3 / 3

Trigger Term Quality

Provides natural trigger phrases a user would say — 'deepgram incident', 'deepgram outage', 'deepgram down', 'deepgram 500 errors' — with good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

Narrowed to Deepgram-specific triggers, making it clearly distinguishable and 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.