Skills for Real Engineers. Straight from my .agents directory.
alfworld-task-verifier
Agent skill fromzjunlp/SkillNet
Use when the agent needs to check whether an ALFWorld task objective has been met after completing a sub-action (e.g., placing an object). This skill parses the task goal, evaluates the latest environment observation, and outputs a verification decision — task complete, task incomplete, or action ineffective — to guide the next step.
How to install alfworld-task-verifier
npx skills add zjunlp/SkillNet# or add only this skill to Claude Code: copy the folder
experiments/src/skills/alfworld/alfworld-task-verifier/
# into
~/.claude/skills/alfworld-task-verifier/ (all projects)
.claude/skills/alfworld-task-verifier/ (one project)
1# Skill: Task Verifier for ALFWorld23## When to Use4Trigger this skill when:51. The agent has just completed a key sub-action (e.g., `put {obj} in/on {recep}`)62. The agent needs to determine whether the overall task goal is satisfied73. The agent must decide whether to continue searching or conclude the task89## Core Workflow1011### 1. Parse the Task Goal12Extract from the original task description:13- **Target object(s)**: What needs to be found/placed (including quantity)14- **Target receptacle**: Where objects must end up15- **Required transformations**: Any cleaning, heating, or cooling steps1617### 2. Analyze the Observation18Evaluate the most recent `Observation:` text from the environment:19- Look for evidence that required objects are present in the target receptacle20- Count how many target objects have been successfully placed21- Note: Other items in the receptacle do not invalidate success2223### 3. Make a Verification Decision2425| Condition | Decision | Output |26|-----------|----------|--------|27| All required objects confirmed in target receptacle | Complete | `Verification: Task complete. No further action needed.` |28| Some but not all objects placed | Incomplete | `Verification: Task incomplete. Continue searching for {missing object(s)}.` |29| Observation says "Nothing happened" | Ineffective | `Verification: Last action was ineffective. Re-assess and try a different approach.` |30…
Excerpt shown under the repository's MIT license.
More skills in SkillNet
- ▸skillnet
- ▸alfworld-appliance-navigator
- ▸alfworld-appliance-preparer
- ▸alfworld-clean-object
- ▸alfworld-device-operator
- ▸alfworld-environment-scanner
- ▸alfworld-goal-interpreter
- ▸alfworld-heat-object-with-appliance
- ▸alfworld-inventory-management
- ▸alfworld-locate-target-object
- ▸alfworld-location-navigator
- ▸alfworld-navigation-planner
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
