CtrlK
BlogDocsLog inGet started
Tessl Logo

ctx-upgrade

Update context-mode from GitHub and fix hooks/settings. Pulls latest, builds, installs, updates npm global, configures hooks. Trigger: /context-mode:ctx-upgrade

67

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 content is a tight, actionable, well-sequenced single-purpose workflow with a sensible fallback and a built-in verification checklist, held back only by an embedded version literal and the lack of an error-recovery loop around the Doctor check.

Suggestions

Replace the literal "v1.0.39" in the checklist example with a placeholder like "vX.Y.Z" to avoid time-sensitive detail, since the instruction already says to show actual version numbers.

Add an explicit recovery step after the Doctor check (e.g., "If any check fails, re-run the fallback command and report the failing check") to close the validate→fix→retry loop.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence, but the checklist example embeds a literal version number ("v1.0.39") — time-sensitive detail that the rubric penalizes unless isolated in a deprecated section.

4 / 5

Actionability

Steps give concrete, executable guidance with a real fallback shell command, but the main path delegates the actual upgrade command to the MCP tool's runtime output and the fallback uses a derived <PLUGIN_ROOT> placeholder, leaving minor gaps versus copy-paste-ready.

4 / 5

Workflow Clarity

A clear numbered sequence includes a verification checkpoint ("Doctor: all checks PASS" checklist) and an MCP-failure fallback branch, but there is no validate→fix→retry recovery loop for a failed Doctor check, so it sits below the top anchor.

4 / 5

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized sections (# title, ## Instructions, numbered steps) satisfy the simple-skill exception for maximal progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

83%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 specific and occupies a clear niche with an explicit trigger, but its "when" guidance is a command name rather than natural scenario phrasing, leaving trigger term coverage and completeness slightly short of maximal.

Suggestions

Add a natural-language "Use when..." clause naming the scenarios (e.g., "Use when upgrading context-mode or repairing broken hooks/settings") alongside the slash-command trigger.

Include a few synonyms or plain-language variants of the trigger ("update", "reinstall", "fix hooks") so users who don't type the exact command still match.

DimensionReasoningScore

Specificity

Lists multiple concrete upgrade actions — "Pulls latest, builds, installs, updates npm global, configures hooks" plus "fix hooks/settings" — giving comprehensive coverage of the upgrade flow in third person.

5 / 5

Completeness

The "what" is explicit (pull/build/install/update/configure hooks); the "when" is present via the slash-command trigger, which is explicit guidance rather than a missing "Use when..." clause, but the scenario language could be more specific.

4 / 5

Trigger Term Quality

Includes the explicit "Trigger: /context-mode:ctx-upgrade" plus natural terms like "upgrade" and "update", but lacks synonyms or broader scenario phrasing users might naturally say, so it stops short of comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

It targets a single, narrowly-scoped niche (upgrading the context-mode plugin) with a distinct slash-command trigger, so conflict with other skills is minimal.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mksglu/context-mode
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.