SKILLEMALL.ai
GitHub ↗ RU Sign in

CD pr-simplify

Simplify your own Windows-node change to its smallest complete fix while preserving distinct regressions, platform contracts, and required proof. Use after implementation before PR preparation, after large repairs, or when asked to shrink a change or remove slop.

The skillemall take

Promises to trim Windows-node changes to minimal working patches while preserving regressions and platform contracts. Single instruction file at 2807 tokens, no scripts or examples. Quality score 68 — average: no broken references detected, but process score only 46. Not tested on models, no sandbox runs.

For Windows developers willing to apply recommendations manually. The instruction text exists, but without real PR or diff examples, it's unclear how well the skill catches bloat. Install if you need a pre-submission checklist — works as a reminder, not automation.

openclaw/openclaw-windows-node Agent Skills author: openclaw 1 file body ≈ 2 807 tokens Open the sourcegithub.com↗ analyzed 32 h ago

Simplify your own Windows-node change to its smallest complete fix while preserving distinct regressions, platform contracts, and required proof.

As a process D 46/100 · Unfinished process — References files that are not bundled: ../../../AGENTS.md, ../../../docs/ARCHITECTURE.md, ../../../src/OpenClaw.Tray.WinUI/AGENTS.md

ProcedureSoftware developmentData and analyticstype 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
46/100
Unfinished process
References files that are not bundled: ../../../AGENTS.md, ../../../docs/ARCHITECTURE.md, ../../../src/OpenClaw.Tray.WinUI/AGENTS.md
Tools and files w 18
0
Inputs and preconditions w 11
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: ../../../AGENTS.md
  • warning missing-ref reference to a missing file: ../../../docs/ARCHITECTURE.md
  • warning missing-ref reference to a missing file: ../../../src/OpenClaw.Tray.WinUI/AGENTS.md
  • warning missing-ref reference to a missing file: ../../../docs/CONNECTION_ARCHITECTURE.md
  • warning missing-ref reference to a missing file: ../../../docs/SETUP_ENGINE_REDESIGN.md
  • warning missing-ref reference to a missing file: ../../../docs/WSL_GATEWAY_ADMIN.md
  • warning missing-ref reference to a missing file: ../../../docs/WINDOWS_NODE_TESTING.md
  • warning missing-ref reference to a missing file: ../../../docs/TEST_COVERAGE.md
  • warning missing-ref reference to a missing file: ../../../docs/RELEASING.md
  • warning missing-ref reference to a missing file: ../test-audit/SKILL.md
  • warning missing-ref reference to a missing file: ../../../docs/TEST_COVERAGE.md
  • warning missing-ref reference to a missing file: ../openclaw-proof-validation/SKILL.md
  • warning missing-ref reference to a missing file: ../windows-pr-prepare/SKILL.md
  • note edit-residue the text marks something as outdated (lines 171, 176): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 46/100

Will not run. References files that are not bundled: ../../../AGENTS.md, ../../../docs/ARCHITECTURE.md, ../../../src/OpenClaw.Tray.WinUI/AGENTS.md
  • 0Tools and files. 13 referenced file(s) missing: ../../../AGENTS.md, ../../../docs/ARCHITECTURE.md, ../../../src/OpenClaw.Tray.WinUI/AGENTS.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 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
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 15 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2807 tokens
  • 100Running it twice. Mutating operations check current state

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 263: enough signal without eating the budget
  • +4Structure: 11 headings
  • +3Step-by-step instructions: 15 items

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