Diagnose gateway failures by reading daemon logs, session transcripts, Redis state, and OTEL telemetry. Full Telegram path triage: daemon process → Redis channel → command queue → pi session → model API → Telegram delivery. Use when: 'gateway broken', 'telegram not working', 'why is gateway down', 'gateway not responding', 'check gateway logs', 'what happened to gateway', 'gateway diagnose', 'gateway errors', 'review gateway logs', 'fallback activated', 'gateway stuck', or any request to understand why the gateway failed. Distinct from the gateway skill (operations) — this skill is diagnostic.
84
81%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
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.
This is an excellent skill description that hits all the marks. It provides highly specific capabilities (reading daemon logs, Redis state, OTEL telemetry), includes a comprehensive set of natural trigger terms, explicitly addresses both what and when, and proactively distinguishes itself from a related gateway operations skill. The description is thorough without being padded, and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: reading daemon logs, session transcripts, Redis state, OTEL telemetry, and describes the full triage path (daemon process → Redis channel → command queue → pi session → model API → Telegram delivery). | 3 / 3 |
Completeness | Clearly answers both 'what' (diagnose gateway failures by reading logs, Redis state, telemetry, full Telegram path triage) and 'when' (explicit 'Use when:' clause with extensive trigger phrases). Also distinguishes itself from a related skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'gateway broken', 'telegram not working', 'why is gateway down', 'gateway not responding', 'check gateway logs', 'fallback activated', 'gateway stuck', etc. These are realistic phrases a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Explicitly distinguishes itself from the gateway operations skill by stating 'Distinct from the gateway skill (operations) — this skill is diagnostic.' The focus on diagnosis, logs, and telemetry creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an extremely thorough and actionable diagnostic skill with excellent workflow structure and concrete commands at every step. However, it suffers significantly from verbosity — the sheer volume of inline content (known failure scenarios, architecture details, OTEL event catalogs) makes it a poor fit for context window efficiency. The content would benefit greatly from splitting detailed failure scenarios and reference material into separate files while keeping the core diagnostic workflow lean.
Suggestions
Extract the Known Failure Scenarios section (scenarios 0-7 with sub-variants) into a separate FAILURES.md reference file, keeping only a brief summary table in the main skill
Move Architecture Reference, Key Code, ADR anchors, and Fallback Controller State into a separate REFERENCE.md file linked from the main skill
Trim the Layer 1 CLI Status interpretation section — the detailed explanations of each status field (interruptibility, operator-tracing, channel-health, channel-healing) are excessively verbose and could be a linked reference
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~400+ lines with extensive detail on every failure scenario, internal architecture, OTEL event names, and implementation specifics. Much of this (e.g., explaining what each OTEL event name means, detailed architecture diagrams, code file listings) could be in referenced files. The sheer volume of known failure scenarios with their sub-variants (2a, 2b, 2c, 4a, 4b, 4c) makes this a wall of operational knowledge that competes heavily with context window. | 1 / 3 |
Actionability | Every diagnostic layer has concrete, copy-paste-ready bash commands. Error patterns are mapped to specific meanings and fixes. The CLI commands, kubectl commands, curl tests, and log inspection commands are all fully executable and specific. | 3 / 3 |
Workflow Clarity | The diagnostic procedure is clearly sequenced as numbered layers (Layer -1 through Layer 8) with explicit 'stop at the first failure' instruction. Each layer has validation criteria and failure patterns. The workflow includes feedback loops (e.g., watchdog auto-aborts then self-restarts, validate → fix → re-validate patterns). | 3 / 3 |
Progressive Disclosure | The skill references related skills at the bottom and starts with CLI commands before manual steps, which is good progressive disclosure. However, the massive Known Failure Scenarios section, Fallback Controller State, Architecture Reference, and Key Code sections are all inline when they could be split into referenced files. The monolithic nature of the content undermines discoverability. | 2 / 3 |
Total | 9 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
ce9ca8e
Table of Contents
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.