New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Tirx Profile Kernel

by mlc-ai in mlc-ai/TIRx-harness

Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools.

No licenceAuto-check passed

Install Tirx Profile Kernel

skills CLI
$ npx skills add mlc-ai/TIRx-harness --skill tirx-profile-kernel -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mlc-ai/TIRx-harness tirx-profile-kernel --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mlc-ai/TIRx-harness.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tirx-profile-kernel .claude/skills/tirx-profile-kernel && rm -rf skills-src

Use ~/.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/

Facts

Skill name
tirx-profile-kernel
GitHub stars
126
Token cost
~783 tokens
SKILL.md length
384 words
Files
5 (incl. references)
Skills in repo
3
Repo updated
First seen
Licence
None found

At a glance

Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools.

  • Works in 5 steps: Resolve a reproducible launch and… → Record a stable baseline before… → Run the tools that answer the question.… → …
  • Performance must be measured
  • SKILL.md covers Tool routing, Workflow, Report tool defects and Finish
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Tirx Profile Kernel is an agent skill from mlc-ai/TIRx-harness. Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools. Use whenever performance must be measured, explained, compared, or improved.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `agents/openai.yaml`, `references/dump-source.md` and `references/iket.md`).

The repository describes itself as: An Open Compiler Harness for Agentic GPU Programming.

When your agent uses it

  • Performance must be measured

Example prompts

  • “/tirx-profile-kernel”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Resolve a reproducible launch and representative input. Treat user-provided
  2. Record a stable baseline before profiling. Keep inputs, environment, GPU,
  3. Run the tools that answer the question. Pick an idle GPU and do not run GPU
  4. Base each hypothesis on a specific metric, finding, or generated-code
  5. After a change, rerun the same benchmark and affected profilers and report

What it can do on your machine

Read from SKILL.md and the folder at commit 6449c3d. 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

Tirx Profile Kernel loads about 783 tokens when it runs, and up to ~8k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 384 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~783
With references · SKILL.md plus every file in references/, read only if the agent opens them
~8k

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 384 words (~783 tokens).

“Measure the kernel before explaining or optimizing it. Reading a profiler guide or inspecting source alone is not performance evidence when a runnable case is available.”

— opening of SKILL.md by mlc-ai
name
tirx-profile-kernel

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files (references) in skills/tirx-profile-kernel of mlc-ai/TIRx-harness.

  • SKILL.md
  • agents/openai.yaml
  • references/dump-source.md
  • references/iket.md
  • references/ncu.md

Open the folder on GitHubat commit 6449c3d

Compare with similar skills

Tirx Profile Kernel 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.

Tirx Profile Kernel compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tirx Profile Kernel this skillmlc-ai/TIRx-harness126—~783Automated safety check: PassNone
Linkedin Profile Optimizersickn33/agentic-awesome-skills47k1 repos~2.6kAutomated safety check: PassMIT
Parallel Execution Optimizeraffaan-m/ECC275k1 repos~712Automated safety check: PassMIT
Parallel Execution Optimizeraffaan-m/ECC275k—~363Automated safety check: PassMIT
Linkedin Profile Optimizerdavila7/claude-code-templates32k2 repos~2.6kAutomated safety check: PassMIT
Profile Optimizercharlie947/social-media-skills3.8k—~2.9kAutomated safety check: PassMIT

Similar skills

  • Linkedin Profile Optimizer

    sickn33/agentic-awesome-skills

    High-intent expert for LinkedIn profile checks and SEO optimization.

    47k GitHub starsUsed in 1 repo~2.6k tokens
    Business, Finance & HRAuto-check passed

  • Parallel Execution Optimizer

    affaan-m/ECC

    Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final…

    275k GitHub starsUsed in 1 repo~712 tokens
    DevelopmentAuto-check passed

  • Parallel Execution Optimizer

    affaan-m/ECC

    当用户希望通过并行工作、并发 agents、批量工具调用、隔离 worktree 或多条独立验证通道来大幅加速任务、同时不损失正确性时使用。

    275k GitHub stars~363 tokensUpdated 3 days ago
    DevelopmentAuto-check passed

  • Linkedin Profile Optimizer

    davila7/claude-code-templates

    Optimize a LinkedIn profile for searchability, recruiter visibility, and engagement.

    32k GitHub starsUsed in 2 repos~2.6k tokens
    Business, Finance & HRAuto-check passed

  • Profile Optimizer

    charlie947/social-media-skills

    Rebuild a LinkedIn profile for maximum conversions. An agent skill from charlie947/social-media-skills.

    3.8k GitHub stars~2.9k tokensUpdated 24 days ago
    Media & CreativeAuto-check passed

  • Happier Profile And Optimize

    happier-dev/happier

    The method for profiling and optimizing anything whose success is a measured cost — frame the phase and metric, choose an instrument that can actually see the cost, label the waste, falsify the…

    1.9k GitHub stars~3.2k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from mlc-ai/TIRx-harness

  • Tirx Wiki

    mlc-ai/TIRx-harness

    Authoritative reference for TIRx-lite authoring on TIRx: TIRx-lite APIs, canonical kernels, optimization guidance, PTX ISA, and GPU references.

    126 GitHub stars~816 tokensUpdated yesterday
    Auto-check passed

  • Tirx Debug Kernel

    mlc-ai/TIRx-harness

    Debug and validate runnable TIRx kernels by selecting and executing the applicable correctness tools.

    126 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

Questions about Tirx Profile Kernel

What does Tirx Profile Kernel do?

Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools. Tirx Profile Kernel is an agent skill from mlc-ai/TIRx-harness. Profile and optimize runnable TIRx kernels by selecting and executing the applicable measurement and analysis tools.

When should I use Tirx Profile Kernel?

Tirx Profile Kernel fits situations like: performance must be measured.

How do I install Tirx Profile Kernel in Claude Code?

Run `npx skills add mlc-ai/TIRx-harness --skill tirx-profile-kernel -a claude-code`. Or copy the skill folder (skills/tirx-profile-kernel in mlc-ai/TIRx-harness) into .claude/skills/tirx-profile-kernel in your project. Claude Code loads it when a task matches its description.

How do I install Tirx Profile Kernel in Codex?

Run `npx skills add mlc-ai/TIRx-harness --skill tirx-profile-kernel -a codex`. Or copy the skill folder (skills/tirx-profile-kernel in mlc-ai/TIRx-harness) into .agents/skills/tirx-profile-kernel in your project. Codex loads it when a task matches its description.

Can I use Tirx Profile Kernel 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 mlc-ai/TIRx-harness --skill tirx-profile-kernel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tirx-profile-kernel, .gemini/skills/tirx-profile-kernel, .github/skills/tirx-profile-kernel and .opencode/skills/tirx-profile-kernel in your project.

What does Tirx Profile Kernel need to run?

SKILL.md names no scripts, command-line tools or credentials: Tirx Profile Kernel is instructions for the agent only. Our summary lists: Python 3.

Does Tirx Profile Kernel 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 Tirx Profile Kernel 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 Tirx Profile Kernel use?

No licence was found for Tirx Profile Kernel or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Tirx Profile Kernel use?

About 783 tokens (SKILL.md is roughly 3.1k 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 7.2k tokens, read only when the agent opens those files.

What are the alternatives to Tirx Profile Kernel?

Skills that share tags, products or a category with Tirx Profile Kernel: Linkedin Profile Optimizer (sickn33/agentic-awesome-skills, 47k stars), Parallel Execution Optimizer (affaan-m/ECC, 275k stars), Parallel Execution Optimizer (affaan-m/ECC, 275k stars) and Linkedin Profile Optimizer (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tirx Profile Kernel?

mlc-ai (a GitHub organization) maintains it in mlc-ai/TIRx-harness, which has 126 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 8, 2026.

Source: mlc-ai/TIRx-harness on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.