SKILLEMALL.ai
GitHub ↗ RU Sign in

CC dsh-client-ui-ux

Design and review DeepSeek Harness client UI changes — visual token discipline, reuse-before-adding, feedback surfaces (toast vs in-place notice vs empty state), overlay and menu safety, platform window adaptation, loading states, and error copy placement. Use when adding or changing product-user-visible GUI behavior in packages/client, or when reviewing such a PR.

The skillemall take

The skill trains an AI agent to review DeepSeek Harness UI changes against a checklist: token reuse, toast vs notice vs empty state selection, overlay safety, platform adaptation, loading states, and error messaging. Works only within packages/client.

Scores show 68% quality and 44% process grade. No critical findings, but broken references flag missing files—the skill points to materials that don't exist in the folder. Models weren't run, sandbox untested. In practice, the agent gets instructions with gaps: guidance exists, but context links are dead.

Install if you'll patch missing files manually or if this serves as a reminder rather than a source of truth. For serious UI reviews—insufficient as-is.

deepseek-ai/deepseek-harness Agent Skills author: deepseek-ai MIT 1 file body ≈ 2 027 tokens Open the sourcegithub.com↗ analyzed 4 d ago

Design and review DeepSeek Harness client UI changes — visual token discipline, reuse-before-adding, feedback surfaces (toast vs in-place notice vs empty…

As a process C 52/100 · Has gaps — References files that are not bundled: ../dsh-prose-standard/SKILL.md, ../../notes/implemented/architecture/2026-08-23-locale-owned-client-ui-copy.md, ../../../docs/web-styling.md

AnalyzerDesigntype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
C
87/100
safety, quality, tests
Safety 60%
100
Quality 40%
68
Run on models
none yet
Process rating
C
52/100
Has gaps
References files that are not bundled: ../dsh-prose-standard/SKILL.md, ../../notes/implemented/architecture/2026-08-23-locale-owned-client-ui-copy.md, ../../../docs/web-styling.md
Tools and files w 18
0
Result and completion w 14
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../dsh-prose-standard/SKILL.md
  • warning missing-ref reference to a missing file: ../../notes/implemented/architecture/2026-08-23-locale-owned-client-ui-copy.md
  • warning missing-ref reference to a missing file: ../../../docs/web-styling.md
  • warning missing-ref reference to a missing file: ../../../packages/client/ui-primitives/README.md
  • warning missing-ref reference to a missing file: ../../../packages/client/AGENTS.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/client-components.md
  • warning missing-ref reference to a missing file: ../dsh-error-handling/SKILL.md
  • warning missing-ref reference to a missing file: ../dsh-responsive-ui/SKILL.md

Process rating: all ten parameters 52/100

Will not run. References files that are not bundled: ../dsh-prose-standard/SKILL.md, ../../notes/implemented/architecture/2026-08-23-locale-owned-client-ui-copy.md, ../../../docs/web-styling.md
  • 0Tools and files. 8 referenced file(s) missing: ../dsh-prose-standard/SKILL.md, ../../notes/implemented/architecture/2026-08-23-locale-owned-client-ui-copy.md, ../../../docs/web-styling.md
  • 0Result and completion. Does not say what the result is
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 100Steps. 26 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2027 tokens
  • 100Running it twice. No mutating operations
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 10 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 367: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 26 items

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.