SKILLEMALL.ai
GitHub ↗ RU Sign in

CD dsh-code-review

Use when reviewing a pull request in the deepseek-harness repo — orients the reviewer to this codebase's standards (AGENTS.md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

The skillemall take

This skill guides reviewers through deepseek-harness standards: AGENTS.md conventions, defensive patterns, ADRs, and quality gates. It promises to flag what matters in a pull request review.

Broken references and missing files turned up—no model runs or sandbox tests. Code quality sits at 68/100, process at 41/100. No critical findings listed, medium and low counts stay blank. The skill itself is 2170 tokens of instructions, not automation.

Install if you're already in deepseek-harness and need reminders about local conventions. If it's not your repo or the links point nowhere, fix the files first.

deepseek-ai/deepseek-harness Agent Skills author: deepseek-ai MIT 1 file body ≈ 2 814 tokens Open the sourcegithub.com↗ analyzed 4 d ago

md conventions, defensive patterns, ADRs, quality gates) and the review-specific checks that code alone can't show

As a process D 41/100 · Unfinished process — References files that are not bundled: ../../../AGENTS.md, ../../../packages/AGENTS.md, ../../../docs/defensive-patterns/README.md

AnalyzerSoftware developmenttype 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
D
41/100
Unfinished process
References files that are not bundled: ../../../AGENTS.md, ../../../packages/AGENTS.md, ../../../docs/defensive-patterns/README.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Failures and branches w 10
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: ../../../AGENTS.md
  • warning missing-ref reference to a missing file: ../../../packages/AGENTS.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/README.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/general.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/package-surface.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/remote-and-api.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/client-components.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/conversation-and-session.md
  • warning missing-ref reference to a missing file: ../../../docs/AGENTS.md
  • warning missing-ref reference to a missing file: ../dsh-prose-standard/SKILL.md
  • warning missing-ref reference to a missing file: ../dsh-ci-test-reliability/SKILL.md
  • warning missing-ref reference to a missing file: ../dsh-client-ui-ux/SKILL.md
  • warning missing-ref reference to a missing file: ../dsh-error-handling/SKILL.md
  • warning missing-ref reference to a missing file: ../dsh-session-projection/SKILL.md
  • warning missing-ref reference to a missing file: ../../../docs/testing.md
  • warning missing-ref reference to a missing file: ../../notes/README.md
  • warning missing-ref reference to a missing file: ../../../docs/i18n/translation-rules.md
  • warning missing-ref reference to a missing file: ../../../docs/i18n/terminology.md
  • warning missing-ref reference to a missing file: ../../../docs/subsystems/README.md
  • warning missing-ref reference to a missing file: ../cordis-styling-nitpicking/SKILL.md
  • warning missing-ref reference to a missing file: ../../../AGENTS.md
  • warning missing-ref reference to a missing file: ../../../AGENTS.md
  • warning missing-ref reference to a missing file: ../../../docs/defensive-patterns/general.md

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: ../../../AGENTS.md, ../../../packages/AGENTS.md, ../../../docs/defensive-patterns/README.md
  • 0Tools and files. 23 referenced file(s) missing: ../../../AGENTS.md, ../../../packages/AGENTS.md, ../../../docs/defensive-patterns/README.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 40Result and completion. Does not say what the result is
  • 100Steps. 39 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2814 tokens
  • 100Running it twice. No mutating operations

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 237: enough signal without eating the budget
  • +4Structure: 5 headings
  • +3Step-by-step instructions: 39 items

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