CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

get-context

Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.

Quality

89%

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

92%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.

An exemplary instruction-only skill body: terse, fully directive, with a clearly gated workflow, explicit done criteria, and a feedback loop. The only meaningful gap is the absence of a worked example of the brief playback note itself, which is the skill's central output.

DimensionReasoningScore

Conciseness

The ~46-line body is lean and assumes Claude's competence: no basic concepts are explained, and every line is directive ("Do not re-ask answered questions", "Playback is not a request for approval", "Do not send this note for tiny static changes"). This matches anchor 5; the only near-redundancy ("Do not inspect every saved reference. Inspect only what the current task needs.") is deliberate emphasis rather than padding, so it does not drop to anchor 4.

5 / 5

Actionability

Guidance is mostly executable: a concrete checklist of unclear conditions, a hard boundary ("do not implement UI, scaffold a prototype, start a server, or create files"), numbered handoff steps, and a copy-paste example note. It sits at anchor 4 rather than 5 because the central artifact — the brief playback — is never exemplified; "play back the minimum brief and any defaults in one pithy user-visible note" leaves the note's actual content and format unspecified.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced with explicit checkpoints: question mode triggers, "When both are clear, play back the brief", "If the target and intended user outcome are clear, continue to the next workflow in the same turn", a feedback loop ("If the user provides feedback, incorporate it and course-correct"), and an explicit done criterion. No destructive or batch operations exist, so no validation cap applies; this matches anchor 5.

5 / 5

Progressive Disclosure

The skill is under 50 lines, single-purpose, and well-organized into clear sections (question mode, hard boundary, overrides, user context, handoff), which per the simple-skill note qualifies for a 5 without bundle files; no references/, scripts/, or assets/ directories exist. Its cross-references to the plugin router ($index), critical-overrides.md, and user-context SKILL.md are clearly signaled and one level deep, not buried or nested.

5 / 5

Total

19

/

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.

A strong description that explicitly covers both what the skill does and when to use it, with concrete domain triggers and third-person phrasing. Its main limitations are slightly abstract 'what' wording and a few missing natural trigger synonyms like 'design' or 'prototype'.

DimensionReasoningScore

Specificity

The description lists several concrete actions for the product-design domain — "design-brief gate", "clarify missing product information", "play back the brief" — which matches the 'several specific actions; minor gaps' anchor. It falls short of anchor 5 because "clarifying the product and outcome" is somewhat abstract compared to the fully concrete action lists in the top anchor, and above anchor 3 because more than 1-2 actions are named with adequate coverage of this narrow skill's scope.

4 / 5

Completeness

Both questions are explicitly answered: what ("clarifying the product and outcome... clarify missing product information and play back the brief") and when ("Use before ideation, image-to-code builds, redesigns, or product UI work") with concrete trigger phrases. This matches anchor 5 and exceeds anchor 4 because the 'when' clause is explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

Triggers include natural phrases users would say — "redesigns", "product UI work", "image-to-code builds" — giving good coverage, matching anchor 4. A few natural terms are missing (e.g., "design", "prototype", "mockup", "landing page"), preventing the comprehensive synonym coverage of anchor 5, while "ideation" leans jargon-ish but is still a plausible user term.

4 / 5

Distinctiveness Conflict Risk

The niche — a mandatory brief-clarification gate run before design workflows — is mostly distinct with clear triggers, matching anchor 4. Minor overlap risk remains with the very workflows it precedes (ideation, image-to-code) and with broadly phrased "product UI work", keeping it below anchor 5's minimal-conflict bar.

4 / 5

Total

17

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository

openai/plugins

Path

plugins/product-design/skills/get-context/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.