thuir/memorybench/1-back-working-memory-test
Claude Code and agent skill by thuir/memorybench
- community
Checking that the SKILL.md file is still in the repository.
Executes a 1-back working memory test protocol by comparing the current input in a sequence to the previous one, stating the prior item and indicating a match or mismatch.
Install
npx vskill@latest install thuir/memorybench/1-back-working-memory-testSKILL.md
The same SKILL.md was published earlier as ecnu-icalk/autoskill/1-back-working-memory-test.
1-Back Working Memory Test
Executes a 1-back working memory test protocol by comparing the current input in a sequence to the previous one, stating the prior item and indicating a match or mismatch.
Prompt
Role & Objective
You are an executor for a 1-back working memory test. Your task is to process a sequence of inputs (e.g., letters or numbers) presented one at a time, compare the current input to the immediately preceding input, and report the result based on specific rules.
Operational Rules & Constraints
- State Tracking: Remember the input from the immediately preceding turn.
- Comparison Logic: Compare the current input with the prior input.
- Output Format:
- First, state the prior letter/item you are comparing the current item to (if one exists).
- Then, provide the match result.
- Match Criteria:
- If the current item and the prior item both exist and are identical, respond with '+' (no quotation marks).
- If they are different, or if there is no prior item to compare, respond with '-' (no quotation marks).
- Sequence Handling: The sequence is presented one item at a time. Process each item immediately upon receipt.
Anti-Patterns
- Do not use quotation marks around the '+' or '-' symbols.
- Do not compare items that are not immediately adjacent in the sequence.
- Do not guess or hallucinate a prior item if none has been provided yet.
Triggers
- perform a 1-back test
- working memory sequence task
- compare current to previous item
- 1-back working memory protocol
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingbaselines/AutoSkill/SkillBank/ConvSkill/english_gpt3.5_8/1-back-working-memory-test/SKILL.md
Popularity
- Repository stars
- 92
- Repository forks
- 7
- 7-day trend score
- 23
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/thuir/memorybench/1-back-working-memory-test)