Content
22%Weight 40%Scale 1-5Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The body is a marketing landing page rather than an operational skill document: it promotes the skill's benefits and purchase terms but provides no executable diagnostic commands, no ordered workflow, and no bundle files — the diagnostic engine itself is explicitly not included. As a result, an agent reading this file could not actually perform the advertised diagnosis.
Suggestions
Add a concrete diagnostic workflow with the actual commands to run (e.g., `ss -tulpn | grep :80` for port conflicts, `nginx -t` for config syntax, `journalctl -u <service> -p err` for systemd failures), in an ordered sequence with a validation step before reporting root causes.
Replace the 'Questions' FAQ and 'Why use this skill' sections (purchase terms, 'lifetime access', time-savings pitch) with operational content — checklists of failure patterns per service and expected output interpretation.
Either include the diagnostic scripts/modules the description advertises (e.g., a `scripts/` directory referenced from the body) or rewrite the body to be self-contained, since the file currently states the original package's logic 'are not in this folder', leaving the advertised capabilities unactionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Noticeably verbose with padded sections aimed at a human buyer rather than Claude: 'Why use this skill' ('Manually debugging a broken home lab or production server is time-consuming'), a five-question FAQ including 'What exactly is included with my purchase of the selfhosted-env-doctor skill?' and 'lifetime access', plus promotional footer links. It is not 1 because it does not explain concepts Claude already knows — the marketing padding, not concept tutoring, is the problem — and roughly half the body ('What it does', 'How it works', 'Known limitations') is on-topic. | 2 / 5 |
Actionability | Minimal concrete guidance: the body names the tools checked ('Systemd, Netstat/SS, df/du') and what it looks for ('default_server collisions', '.env file permission risks'), but never gives the commands to execute a diagnosis (no 'nginx -t', 'ss -tulpn', 'journalctl -u <unit>', 'systemctl status'), and the only real command shown is inside example output ('sudo systemctl stop apache2...'), not an instruction. This matches 'high-level hints but missing the specific steps to execute'; it is above 1 only because concrete tools, checks, and a worked example are at least named. | 2 / 5 |
Workflow Clarity | No sequence of diagnostic steps exists anywhere in the body — 'How it works' describes outcomes ('checks systemd unit health, validates Nginx configuration syntax, audits listening sockets') in prose without any ordered procedure, and the file admits the actual logic is absent ('Scripts, extension source, and templates from the original package are not in this folder'). This matches the 1 anchor 'steps missing or incoherent; no sequence'; the simple-skill exception does not apply because the single action (run the diagnostic) is not unambiguous — it is unspecified. | 1 / 5 |
Progressive Disclosure | The body has clear section headers ('What it does', 'How it works', 'When to use', 'Known limitations') but no bundle files exist and no references point to the deeper material that clearly exists elsewhere, while ~35% of the content (purchase FAQ, marketing links) belongs in a sales page, not a skill document. This fits 'some structure but could be better organized'; it is above 2 because structure is genuinely present (eight labeled sections), and below 4 because most content is not appropriately placed for an operational skill. | 3 / 5 |
Total | 8 / 20 Passed |