CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

doctor

Quick-action diagnostic skill to audit installed CLI binaries and authentication states across Quintet providers (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode). Use when verifying provider pools or diagnosing CLI readiness via /doctor.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-5

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

A tight, highly actionable diagnostic workflow with an explicit re-verification loop and per-provider fix commands. The one structural defect is its only external reference: the link path escapes the bundle and the referenced file is missing, so progressive disclosure fails at exactly the point it is used.

Suggestions

Fix the reference link from (../../references/CLI_REFERENCE.md) to (references/CLI_REFERENCE.md) and ship the file in the skill's references/ directory — the current path escapes the bundle and no references/ directory exists, so the link is dead.

Fold step 2 (Binary Resolution Guard) into step 1 as a short note on the fallback chain, removing the duplication of the bash block's path-resolution logic.

Drop the intro sentence that restates the frontmatter description, saving tokens without losing information.

DimensionReasoningScore

Conciseness

Overall lean and executable with no explanations of concepts Claude already knows, but step 2 ('Binary Resolution Guard') restates the fallback logic already embedded in the bash block's path checks, and the intro sentence duplicates the frontmatter description. Anchor 5 ('every token earns its place') is not quite met; anchor 3's unnecessary explanations are absent.

4 / 5

Actionability

Fully executable guidance: a copy-paste-ready bash block resolves the quintet binary and runs 'doctor', and each unauthenticated provider gets an exact fix command ('claude login', 'codex login', 'gh auth login or copilot auth', 'opencode auth login'). Specific commands cover the common cases per provider.

5 / 5

Workflow Clarity

The 5-step sequence has explicit validation and a feedback loop: step 4 ('Re-verification Feedback Loop') instructs re-running "$QBIN" doctor to verify state updated to 'ready: true', and step 2 guards against a missing binary. This is read-only diagnostics, so the destructive/batch cap does not apply.

5 / 5

Progressive Disclosure

The single reference is well-labeled ('Complete CLI subcommands, options, and setup') and one level deep, but the link target '(../../references/CLI_REFERENCE.md)' escapes the skill bundle two directories up, and no references/ directory or CLI_REFERENCE.md exists in the bundle at all — navigation to the reference fails. More than the 'minor organization gaps' of anchor 4.

3 / 5

Total

17

/

20

Passed

Description

82%Weight 40%Scale 1-5

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 strong description with explicit what/when structure, third-person voice, and a highly distinctive niche. The main weakness is moderate specificity — only 1-2 concrete actions are named, leaving capability coverage thin.

Suggestions

Add one or two more concrete outcome actions to the description (e.g., 'lists ready providers with one-time auth-fix commands and summarizes active pool capacity') so specificity reaches comprehensive coverage rather than 1-2 actions.

Include a few more natural user phrasings as triggers — e.g. 'check CLI installs', 'login status', 'provider readiness' — to cover common variations beyond 'verifying provider pools' and 'diagnosing CLI readiness'.

DimensionReasoningScore

Specificity

The description names the domain and 1-2 concrete actions — 'audit installed CLI binaries and authentication states across Quintet providers' — but coverage is not comprehensive; outcome actions like listing ready providers, reporting auth fixes, or summarizing pool capacity are absent. Anchor 4 requires 'several specific actions', which this does not meet.

3 / 5

Completeness

Clearly answers both: what — 'audit installed CLI binaries and authentication states across Quintet providers' — and when — 'Use when verifying provider pools or diagnosing CLI readiness via /doctor', with concrete trigger phrases. Matches the anchor-5 example structure.

5 / 5

Trigger Term Quality

Good keyword coverage: 'verifying provider pools', 'diagnosing CLI readiness', '/doctor', and the six named providers give natural trigger phrases. Falls short of anchor 5 because common variations users might say ('check CLI installs', 'login status', 'auth check') are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: 'Quintet providers (Claude, Codex, Antigravity, Copilot, Qwen, OpenCode)' plus the '/doctor' command make collision with other skills unlikely. Not 4 because overlap risk is essentially nil, not 'minor'.

5 / 5

Total

17

/

20

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository

salemaziel/omc-octo-quintet

Path

skills/doctor/SKILL.md

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.