CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ctx-doctor

Check that context-mode is installed and working, as a table.

Quality

83%

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

100%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.

The body is an exemplar of a minimal, single-purpose skill: it names the exact tool to call, how to present its output, and how to handle failures, with zero wasted tokens. No bundle files exist and none are needed for a skill of this size.

DimensionReasoningScore

Conciseness

The body is two lean sentences with zero padding — "Call the mcp__context_mode__ctx_doctor tool and show its table to the user unchanged. If a row failed, list the fixes it names, in order." — assuming Claude's competence with every token earning its place. Nothing can be trimmed, so it matches anchor 5 rather than the minor-trimming of anchor 4.

5 / 5

Actionability

Gives the exact callable tool name (mcp__context_mode__ctx_doctor), exact display behavior ("show its table to the user unchanged"), and a conditional failure path ("If a row failed, list the fixes it names, in order") — fully executable instruction-only guidance covering the common cases. There are no gaps, so it matches anchor 5 rather than anchor 4.

5 / 5

Workflow Clarity

This is a simple single-task skill and the single action is unambiguous (call one tool, render its table, report failed-row fixes in order), which the guidelines state can score 5. It is a read-only diagnostic, not a destructive or batch operation, so the validation-cap at 3 does not apply.

5 / 5

Progressive Disclosure

The skill is under 50 lines (two sentences), needs no external references, and no bundle files exist — per the simple-skill guideline this scores 5. All content is appropriately inline; splitting two sentences into separate files would add navigation overhead, so it fits anchor 5 rather than anchor 4's 'minor organization gaps'.

5 / 5

Total

20

/

20

Passed

Description

57%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.

The description is concise and clearly states what the skill does with a distinct, low-conflict niche tied to a specific tool. Its main weaknesses are the complete absence of any 'when to use' trigger guidance (capping completeness) and thin trigger-term coverage lacking common diagnostic synonyms like 'status' or 'diagnose'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks whether context-mode is installed, working, or needs troubleshooting.'

Broaden trigger vocabulary with natural diagnostic synonyms users would say: 'status', 'health check', 'diagnose', 'setup', 'broken'.

Optionally enumerate what the check covers (e.g. 'verifies MCP server connection and reports per-check results') to lift specificity beyond a single action.

DimensionReasoningScore

Specificity

Names the domain ("context-mode") and one concrete action ("Check that context-mode is installed and working") plus an output format ("as a table"), matching the '1-2 concrete actions, not comprehensive' anchor. It does not list several specific actions, so it falls short of anchor 4, but is more concrete than the generic anchor 2.

3 / 5

Completeness

The 'what' is clear (diagnostic check of context-mode installation displayed as a table), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not anchor 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

"context-mode", "installed", and "working" are relevant natural terms users would say, but common variations and synonyms ("diagnose", "status", "health check", "setup", "broken", "fix") are missing, matching anchor 3 rather than the good coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

The description is scoped to a single named tool ("context-mode") performing a single diagnostic purpose, giving it a clear niche with minimal conflict risk — the tool name itself is the distinct trigger. No meaningful overlap with other skills, so it fits anchor 5 rather than anchor 4.

5 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

mksglu/context-mode

Path

plugins/claude-code/codex/skills/ctx-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.