# Step Efficient Execution

> Use this skill when the user wants data that tests whether the agent takes the shortest reasonable GUI path instead of wandering, overthinking, or repeating failed actions. Trigger it for requests like “same task but fewer clicks,” “penalize looping,” “test practical speed rather than just success,” or “make the good answer the one with the cleanest trajectory.” This skill is for GUI tasks where success alone is not enough and the trajectory must also be compact, purposeful, and low-latency.

- Skill: `dingxingdi/step-efficient-execution-2` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add dingxingdi/step-efficient-execution-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dingxingdi/step-efficient-execution-2/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: dingxingdi (https://skillmd.com/u/dingxingdi)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/dingxingdi/step-efficient-execution-2

---


# Skill: step-efficient-execution
## 1. Capability Definition & Real Case
* **Professional Definition**: The capability to complete a GUI task with a near-minimal sequence of effective actions, avoiding redundant planning loops, unnecessary reflection cycles, repeated failed attempts, and superfluous verification steps. The agent must preserve correctness while optimizing trajectory length and interaction efficiency.
* **Dimension Hierarchy**: Reliable and Aligned Operation->Safe and Efficient Control->step-efficient-execution
### Real Case
**[Case 1]**
* **Initial Environment**: A document editor is open with two paragraphs already selected or easily reachable through a short sequence of formatting actions. The task is operationally simple for a human user, but a weak agent may spend many extra steps searching menus, re-checking state, or recovering from avoidable misclicks.
* **Real Question**: Change the line spacing of two paragraphs in a document to double-spaced.
* **Real Trajectory**: Navigate directly to the relevant paragraph-formatting control, apply double spacing once, verify the state with a minimal check, and stop rather than continuing to re-open menus or re-apply the same action.
* **Real Answer**: Both paragraphs are double-spaced, using a compact trajectory with no unnecessary repetition.
* **Why this demonstrates the capability**: The benchmark value of this case comes from the gap between a short human solution path and the much longer trajectories many agents produce. A correct but bloated trajectory still reflects weak practical usability because planning and reflection overhead dominate runtime. That is why this case specifically targets step efficiency rather than raw success alone.

## Pipeline Execution Instructions
To synthesize data for this capability, you must strictly follow a 3-phase pipeline. **Do not hallucinate steps.** Read the corresponding reference file for each phase sequentially:

1. **Phase 1: Environment Exploration**
   Read the exploration guidelines to discover raw knowledge seeds:
   `references/EXPLORATION.md`

2. **Phase 2: Trajectory Selection**
   Once Phase 1 is complete, read the selection criteria to evaluate the trajectory:
   `references/SELECTION.md`

3. **Phase 3: Data Synthesis**
   Once a trajectory passes Phase 2, read the synthesis instructions to generate the final data:
   `references/SYNTHESIS.md`