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.
A skill your agent uses when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot…
Apache-2.0Auto-check passed
Install Tsz Performance Engineering
$ npx skills add tsz-org/tsz --skill tsz-performance-engineering -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tsz-org/tsz tsz-performance-engineering --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/tsz-org/tsz.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .claude/skills/tsz-performance-engineering && 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 "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .claude/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineeringType 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 tsz-org/tsz --skill tsz-performance-engineering -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tsz-org/tsz tsz-performance-engineering --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsz-org/tsz.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .agents/skills/tsz-performance-engineering && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .agents/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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 tsz-org/tsz --skill tsz-performance-engineering -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tsz-org/tsz tsz-performance-engineering --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsz-org/tsz.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .cursor/skills/tsz-performance-engineering && 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 "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .cursor/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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/tsz-org/tsz.git --path .agents/skills/tsz-performance-engineering--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 tsz-org/tsz --skill tsz-performance-engineering -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tsz-org/tsz tsz-performance-engineering --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsz-org/tsz.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .gemini/skills/tsz-performance-engineering && 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 "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .gemini/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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 tsz-org/tsz tsz-performance-engineeringInstalls 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 tsz-org/tsz --skill tsz-performance-engineering -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tsz-org/tsz.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .github/skills/tsz-performance-engineering && 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 "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .github/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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 tsz-org/tsz --skill tsz-performance-engineering -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tsz-org/tsz tsz-performance-engineering --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tsz-org/tsz.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/tsz-performance-engineering .opencode/skills/tsz-performance-engineering && 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 "tsz-performance-engineering" agent skill from https://github.com/tsz-org/tsz/tree/main/.agents/skills/tsz-performance-engineering into .opencode/skills/tsz-performance-engineering/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "tsz-performance-engineering", 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
tsz-performance-engineering- GitHub stars
- 577
- Token cost
- ~746 tokens
- SKILL.md length
- 243 words
- Files
- 3 (incl. references)
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot…
- Interpreting TSZ performance work
- SKILL.md covers Rules, Evidence and Cache Checklist
- Calls python3 and cargo
- Including benchmark regressions
What it does
Tsz Performance Engineering is an agent skill from tsz-org/tsz. Use when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot investigations, OOM/timeout/stack-overflow blockers, or optimization PR evidence.
Its SKILL.md is about 750 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/perf-mistakes.md`).
The repository describes itself as: An experiment in fully hand-off software engineering: A performance-first TypeScript checker. The licence is Apache-2.0.
When your agent uses it
- Interpreting TSZ performance work
- Including benchmark regressions
- Cache/residency changes
- Hotspot investigations
Example prompts
- “/tsz-performance-engineering”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 153b25a. 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
Shell commands in SKILL.md call:
python3cargo
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
Tsz Performance Engineering loads about 746 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 72 tokens; SKILL.md has 243 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
The full file from tsz-org/tsz at commit 153b25a, republished under its Apache-2.0 licence (© tsz-org). 243 words, ~746 tokens.
Download SKILL.mdSave it as
.claude/skills/tsz-performance-engineering/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- tsz-performance-engineering
- description
- Use when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot investigations, OOM/timeout/stack-overflow blockers, or optimization PR evidence.
TSZ Performance Engineering
Use for performance, cache/residency, OOM/timeout/stack-overflow, counters, benchmark regressions, and timing claims.
Rules
- Read
AGENTS.md,docs/plan/ROADMAP.md, and relevant PR/issues. - Correctness first. Timing claims matter only for green rows or explicit runtime/residency blockers.
- Optimize the repeated operation, not a fixture spelling.
- State invariant: cache key, invalidation/reset, request scope, fuel/cycle behavior, residency bound, or complexity change.
- No checker-local semantic algorithms, display-string heuristics, source-text
shortcuts, name allowlists, or cross-interner
TypeIdcomparisons. - Read
references/perf-mistakes.mdbefore adding/widening caches, changing residency, or claiming speedups.
Evidence
Use narrow, reproducible commands; wrap heavy runs.
python3 scripts/perf/cache-visibility-report.py --json
python3 scripts/perf/visited-clone-report.py --json
python3 scripts/perf/debug-print-report.py --json
python3 scripts/perf/migration_callsite_counts.py --json
python3 scripts/perf/query-perf-counters.py --json <artifact> --baseline <baseline>
scripts/safe-run.sh ./scripts/bench/perf-hotspots.sh --quick --json-file /tmp/hotspots.json
scripts/safe-run.sh ./scripts/bench/bench-vs-tsgo.sh --filter '<row>' --json-file /tmp/bench.json
scripts/bench/measure-tsz.sh --timeout 420 --json-file /tmp/m.json -- --noEmit -p <tsconfig>Use focused compile guard or cargo nextest run -E 'test(...)' when shortest.
Do not run full conformance, emit, fourslash, or broad project suites locally.
For ad-hoc timing or perf bisects on shared boxes, use
scripts/bench/measure-tsz.sh: it snapshots the binary to an immutable
hash-verified copy (never time the live dist-fast/ path — sibling sessions
overwrite it) and records process CPU time next to wall time, so wall-only
timeouts under CPU contention are reported as unmeasured instead of slow.
See references/perf-mistakes.md and issue #13174.
Cache Checklist
- What semantic question is cached?
- What stable identity is the key? Avoid cross-file
NodeIndexand cross-internerTypeId. - Does the key include all behavior modes: relation, variance, freshness,
contextual typing, inference source,
any, target/module/options, request scope, cycle/fuel, file/session generation? - Where is reset/invalidation?
- What happens cold/disabled/order-randomized?
- Is size/residency bounded or observable?
PR/comment packet: goal (usually fast) and affected rows, invariant, exact
commands/CI, green row timing only, RSS/failure-class evidence for runtime
blockers, counter deltas, noise/caveats.
© tsz-org, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in .agents/skills/tsz-performance-engineering of tsz-org/tsz.
- SKILL.md
- agents/openai.yaml
- references/perf-mistakes.md
Open the folder on GitHubat commit 153b25a
Compare with similar skills
Tsz Performance Engineering 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 |
|---|---|---|---|---|---|---|
| Tsz Performance Engineering this skilltsz-org/tsz | 577 | — | ~746 | Automated safety check: Pass | Apache-2.0 | |
| TransformerLens InterpretabilityOrchestra-Research/AI-Research-SKILLs | 13k | 4 repos | ~3k | Automated safety check: Pass | MIT | |
| Nnsight Remote InterpretabilityOrchestra-Research/AI-Research-SKILLs | 13k | 3 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Paper Interpretationdigoal/blog | 8.6k | — | ~1.5k | Automated safety check: Pass | GPL-2.0 | |
| Interpret Resultsbrycewang-stanford/Auto-Empirical-Research-Skills | 4.5k | — | ~620 | Automated safety check: Notes | Custom licence | |
| Culture Index Interpretertrailofbits/skills | 7.4k | — | ~3.6k | Automated safety check: Notes | CC-BY-SA-4.0 |
Similar skills
Nnsight Remote Interpretability
Orchestra-Research/AI-Research-SKILLs
Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution.
Paper Interpretation
digoal/blog
从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读，并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…
Interpret Results
brycewang-stanford/Auto-Empirical-Research-Skills
Writes academic prose interpreting regression output. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.
- Official
Culture Index Interpreter
trailofbits/skills
Interprets Culture Index surveys and behavioral profiles, from single-person readings to team composition, burnout risk, hiring profiles and interview analysis.
Paper Interpreter
digoal/blog
深度解读学术论文，将论文 PDF（文件或 URL）转化为通俗易懂、图文并茂的 Markdown 解读文档，保存到项目的 markdown/ 目录。触发条件：用户上传或提供论文 PDF、提到"解读论文"/"读论文"/"分析这篇论文"/"帮我看这篇 paper"，或任何需要深入理解一篇学术论文的场景。即使用户只说"帮我看这个 PDF"但内容是论文，也应使用本…
More from tsz-org/tsz
All 12 skills in this repoRust Hygiene Audit
tsz-org/tsz
Run a deep DRY + code-hygiene audit of the Rust workspace and turn the findings into verified, deduplicated, hierarchical GitHub tech-debt issues.
Tsz Iteration Audit
tsz-org/tsz
Audit TSZ repo iteration speed and quality. An agent skill from tsz-org/tsz.
Tsz PR Coordination
tsz-org/tsz
Create, refresh, and publish TSZ pull requests with correct body and state.
Tsz Worktree Intake
tsz-org/tsz
Start TSZ work safely in a crowded multi-agent checkout. An agent skill from tsz-org/tsz.
Tsz Architecture
tsz-org/tsz
Preserve TSZ architecture boundaries while changing checker, solver, binder, emitter, LSP, WASM, or CLI code.
Tsz CI PR
tsz-org/tsz
Drive TSZ GitHub PRs through review, CI, and the merge queue.
Questions about Tsz Performance Engineering
What does Tsz Performance Engineering do?
A skill your agent uses when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot…. Tsz Performance Engineering is an agent skill from tsz-org/tsz. Use when planning, implementing, reviewing, or interpreting TSZ performance work, including benchmark regressions, cache/residency changes, timing claims, perf counters, hotspot investigations, OOM/timeout/stack-overflow blockers, or optimization PR evidence.
When should I use Tsz Performance Engineering?
Tsz Performance Engineering fits situations like: interpreting TSZ performance work; including benchmark regressions; cache/residency changes; hotspot investigations.
How do I install Tsz Performance Engineering in Claude Code?
Run `npx skills add tsz-org/tsz --skill tsz-performance-engineering -a claude-code`. Or copy the skill folder (.agents/skills/tsz-performance-engineering in tsz-org/tsz) into .claude/skills/tsz-performance-engineering in your project. Claude Code loads it when a task matches its description.
How do I install Tsz Performance Engineering in Codex?
Run `npx skills add tsz-org/tsz --skill tsz-performance-engineering -a codex`. Or copy the skill folder (.agents/skills/tsz-performance-engineering in tsz-org/tsz) into .agents/skills/tsz-performance-engineering in your project. Codex loads it when a task matches its description.
Can I use Tsz Performance Engineering 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 tsz-org/tsz --skill tsz-performance-engineering -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tsz-performance-engineering, .gemini/skills/tsz-performance-engineering, .github/skills/tsz-performance-engineering and .opencode/skills/tsz-performance-engineering in your project.
What does Tsz Performance Engineering need to run?
Going by SKILL.md and its folder, Tsz Performance Engineering needs the command-line tools its instructions call (python3 and cargo). Our summary lists: Python 3.
Does Tsz Performance Engineering 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 Tsz Performance Engineering 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 Tsz Performance Engineering use?
Tsz Performance Engineering is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Tsz Performance Engineering use?
About 746 tokens (SKILL.md is roughly 3k 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 1.5k tokens, read only when the agent opens those files.
What are the alternatives to Tsz Performance Engineering?
Skills that share tags, products or a category with Tsz Performance Engineering: TransformerLens Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Nnsight Remote Interpretability (Orchestra-Research/AI-Research-SKILLs, 13k stars), Paper Interpretation (digoal/blog, 8.6k stars) and Interpret Results (brycewang-stanford/Auto-Empirical-Research-Skills, 4.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Tsz Performance Engineering?
tsz-org (a GitHub organization) maintains it in tsz-org/tsz, which has 577 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 9, 2026.
Source: tsz-org/tsz on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.