TransformerLens Interpretability
Orchestra-Research/AI-Research-SKILLs
Guides mechanistic interpretability work with TransformerLens: loading models, caching activations, using HookPoints, activation patching and attention-pattern analysis.
Programming language interpreter design and implementation guide.
No licenceAuto-check passed
Install Interpreter Design
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install revfactory/claude-code-harness interpreter-design --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .claude/skills/interpreter-design && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .claude/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-designType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install revfactory/claude-code-harness interpreter-design --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .agents/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .agents/skills/interpreter-design && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .agents/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install revfactory/claude-code-harness interpreter-design --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .cursor/skills/interpreter-design && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .cursor/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/revfactory/claude-code-harness.git --path experiments/results/case-007/harness/.claude/skills/interpreter-design--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install revfactory/claude-code-harness interpreter-design --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .gemini/skills/interpreter-design && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .gemini/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install revfactory/claude-code-harness interpreter-designInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .github/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .github/skills/interpreter-design && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .github/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add revfactory/claude-code-harness --skill interpreter-design -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install revfactory/claude-code-harness interpreter-design --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/revfactory/claude-code-harness.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/experiments/results/case-007/harness/.claude/skills/interpreter-design .opencode/skills/interpreter-design && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "interpreter-design" agent skill from https://github.com/revfactory/claude-code-harness/tree/main/experiments/results/case-007/harness/.claude/skills/interpreter-design into .opencode/skills/interpreter-design/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "interpreter-design", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
interpreter-design- GitHub stars
- 120
- Token cost
- ~387 tokens
- SKILL.md length
- 108 words
- Files
- 3 (incl. references)
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- None found
At a glance
Programming language interpreter design and implementation guide.
- Works in 4 steps: Lexer: 소스 코드를 토큰 스트림으로 변환 → Parser: 재귀 하강 + Pratt Parser로 AST 생성 → Evaluator: Tree-walking으로 AST 평가 → …
- The user requests building an interpreter
- SKILL.md covers 4단계 파이프라인 워크플로우, 파일 구조 (필수), 핵심 원칙 and 테스트 전략
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Interpreter Design is an agent skill from revfactory/claude-code-harness. Programming language interpreter design and implementation guide. Use when the user requests building an interpreter, parser, lexer, or language implementation — including Pratt parsing, AST evaluation, scope chains, and closures.
Its SKILL.md is about 390 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/ast-evaluator.md` and `references/pratt-parser.md`).
When your agent uses it
- The user requests building an interpreter
- Language implementation — including Pratt parsing
Example prompts
- “/interpreter-design”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Lexer: 소스 코드를 토큰 스트림으로 변환
- Parser: 재귀 하강 + Pratt Parser로 AST 생성
- Evaluator: Tree-walking으로 AST 평가
- Environment: 스코프 체인 + 클로저 지원
What it can do on your machine
Read from SKILL.md and the folder at commit 267005c. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Interpreter Design loads about 387 tokens when it runs, and up to ~1.3k if it reads all its reference files. Until then it costs about 62 tokens; SKILL.md has 108 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Without a licence we can't republish the file, so here is its outline and opening line. It has 108 words (~387 tokens).
“프로그래밍 언어 인터프리터 설계 및 구현 가이드”
- name
- interpreter-design
Files
SKILL.md and 2 other files (references) in experiments/results/case-007/harness/.claude/skills/interpreter-design of revfactory/claude-code-harness.
- SKILL.md
- references/ast-evaluator.md
- references/pratt-parser.md
Open the folder on GitHubat commit 267005c
Compare with similar skills
Interpreter Design next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Interpreter Design this skillrevfactory/claude-code-harness | 120 | — | ~387 | Automated safety check: Pass | None | |
| TransformerLens InterpretabilityOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~3k | Automated safety check: Pass | MIT | |
| Strict Programming Practicescode-yeongyu/oh-my-openagent | 70k | — | ~9.5k | Automated safety check: Pass | Custom licence | |
| Referral Programalirezarezvani/claude-skills | 28k | — | ~3.4k | Automated safety check: Pass | MIT | |
| Nnsight Remote InterpretabilityOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Intern Programsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.9k | Automated safety check: Pass | MIT |
Similar skills
Strict Programming Practices
code-yeongyu/oh-my-openagent
Applies strict, type-first coding rules for Python, Rust, TypeScript and Go, loading the matching language reference before the agent writes or edits any code.
Referral Program
alirezarezvani/claude-skills
When the user wants to design, launch, or optimize a referral or affiliate program.
Nnsight Remote Interpretability
Orchestra-Research/AI-Research-SKILLs
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.
Intern Program
sickn33/agentic-awesome-skills
Internship register: intern and department, supervisor and mentor, institution, start and end dates, stipend, learning goals, mid-term and final scores, conversion flags.
Mentorship Program
sickn33/agentic-awesome-skills
Mentorship register: mentor and mentee pair, department, focus area, mentee goal, session counts, last and next session, overall rating, progress notes and status.
More from revfactory/claude-code-harness
All 15 skills in this repoMicroservice Patterns
revfactory/claude-code-harness
Event-driven microservice architecture patterns guide. An agent skill from revfactory/claude-code-harness.
Query Engine Design
revfactory/claude-code-harness
SQL query engine design and implementation guide. An agent skill from revfactory/claude-code-harness.
API Documentation
revfactory/claude-code-harness
Write accurate and complete library API documentation. An agent skill from revfactory/claude-code-harness.
Crdt Algorithms
revfactory/claude-code-harness
CRDT-based real-time collaborative text editor implementation guide.
Express API Design
revfactory/claude-code-harness
Express.js REST API design and implementation guide. An agent skill from revfactory/claude-code-harness.
Static Site Generator
revfactory/claude-code-harness
Build a markdown-based static site generator with zero dependencies.
Questions about Interpreter Design
What does Interpreter Design do?
Programming language interpreter design and implementation guide. Interpreter Design is an agent skill from revfactory/claude-code-harness. Programming language interpreter design and implementation guide.
When should I use Interpreter Design?
Interpreter Design fits situations like: the user requests building an interpreter; language implementation — including Pratt parsing.
How do I install Interpreter Design in Claude Code?
Run `npx skills add revfactory/claude-code-harness --skill interpreter-design -a claude-code`. Or copy the skill folder (experiments/results/case-007/harness/.claude/skills/interpreter-design in revfactory/claude-code-harness) into .claude/skills/interpreter-design in your project. Claude Code loads it when a task matches its description.
How do I install Interpreter Design in Codex?
Run `npx skills add revfactory/claude-code-harness --skill interpreter-design -a codex`. Or copy the skill folder (experiments/results/case-007/harness/.claude/skills/interpreter-design in revfactory/claude-code-harness) into .agents/skills/interpreter-design in your project. Codex loads it when a task matches its description.
Can I use Interpreter Design in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add revfactory/claude-code-harness --skill interpreter-design -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/interpreter-design, .gemini/skills/interpreter-design, .github/skills/interpreter-design and .opencode/skills/interpreter-design in your project.
What does Interpreter Design need to run?
SKILL.md names no scripts, command-line tools or credentials: Interpreter Design is instructions for the agent only.
Does Interpreter Design access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Interpreter Design safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Interpreter Design use?
No licence was found for Interpreter Design or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.
How many tokens does Interpreter Design use?
About 387 tokens (SKILL.md is roughly 1.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 887 tokens, read only when the agent opens those files.
What are the alternatives to Interpreter Design?
Skills that share tags, products or a category with Interpreter Design: TransformerLens Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Strict Programming Practices (code-yeongyu/oh-my-openagent, 70k stars), Referral Program (alirezarezvani/claude-skills, 28k stars) and Nnsight Remote Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Interpreter Design?
revfactory (a GitHub user) maintains it in revfactory/claude-code-harness, which has 120 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on March 6, 2026.
Source: revfactory/claude-code-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.