CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ctx-upgrade

Update context-mode to the latest release.

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/claude-code/codex/skills/ctx-upgrade/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 lean, directly executable instruction for a simple MCP-driven task: exact tool calls, clear ordering, and a defined conditional response. The only minor gap is the absence of guidance for handling a failed health check after the upgrade.

DimensionReasoningScore

Conciseness

The three-sentence body ("Call the mcp__context_mode__ctx_upgrade tool and show its table... Then call... If a restart is needed, say so in one sentence") contains zero padding and assumes Claude's competence, matching the 'lean and efficient; every token earns its place' anchor.

5 / 5

Actionability

It gives exact tool names (mcp__context_mode__ctx_upgrade, mcp__context_mode__ctx_doctor), explicit ordering, output presentation instructions, and a conditional message rule — fully executable instruction-only guidance with no gaps.

5 / 5

Workflow Clarity

The sequence (upgrade, then doctor, then restart notice) is explicit and ctx_doctor serves as a post-upgrade checkpoint, but there is no guidance on what to do if the doctor reports problems after the upgrade — a minor validation gap rather than a full feedback loop.

4 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and needs no external references; the bundle directories (references/, scripts/, assets/) do not exist and the body references no files, so per the simple-skill guideline a well-contained body scores 5.

5 / 5

Total

19

/

20

Passed

Description

53%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, third-person, and names a concrete action on a specific tool, but it omits any 'when to use' trigger guidance, which caps completeness and limits trigger-term coverage. Since the skill sets disable-model-invocation: true (manual invocation only), the missing triggers are less harmful in practice, but the description itself still reads as incomplete.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to update or upgrade context-mode to the latest version."

Include natural keyword variations such as "upgrade" and "new version" alongside "update" and "latest release" to improve trigger-term coverage.

Optionally mention the post-upgrade doctor check in the description so the capability scope is more comprehensive.

DimensionReasoningScore

Specificity

"Update context-mode to the latest release" names the domain and exactly one concrete action, matching the anchor for 1-2 concrete actions with limited coverage. It is above a 2 because the action stated is concrete rather than generic filler.

3 / 5

Completeness

The 'what' is clear (update context-mode to the latest release) but there is no 'Use when...' clause or any trigger guidance, so completeness is capped at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

The terms "update", "context-mode", and "latest release" are relevant and plausibly user-spoken, but common variations like "upgrade" or "new version" are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"context-mode" names a specific niche tool, keeping conflict risk low, but the description lacks explicit trigger phrases that would secure full distinctiveness. It sits between 'mostly distinct' (4) and 'clear niche with distinct triggers' (5), fitting 4 better since the anchor-5 example includes explicit triggers.

4 / 5

Total

13

/

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-upgrade/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.