Mecatl Perf MCP Interpretation
stacklok/mecatl
Guides reading mecatl's perf MCP data to find why a running harness is slow, leaking goroutines or growing in memory, using cheap reads before any CPU capture.
Profiles a slow command or runtime you own with the right profiler for its language, using uninstrumented baseline timings and keeping raw profiling evidence local and private.
Install LoopX Performance Diagnosis
$ npx skills add loopx-project/loopx --skill loopx-performance-diagnosis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install loopx-project/loopx loopx-performance-diagnosis --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/loopx-project/loopx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/loopx-performance-diagnosis .claude/skills/loopx-performance-diagnosis && 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 "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .claude/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosisType 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 loopx-project/loopx --skill loopx-performance-diagnosis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install loopx-project/loopx loopx-performance-diagnosis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/loopx-project/loopx.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/loopx-performance-diagnosis .agents/skills/loopx-performance-diagnosis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .agents/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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 loopx-project/loopx --skill loopx-performance-diagnosis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install loopx-project/loopx loopx-performance-diagnosis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/loopx-project/loopx.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/loopx-performance-diagnosis .cursor/skills/loopx-performance-diagnosis && 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 "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .cursor/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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/loopx-project/loopx.git --path skills/loopx-performance-diagnosis--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 loopx-project/loopx --skill loopx-performance-diagnosis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install loopx-project/loopx loopx-performance-diagnosis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/loopx-project/loopx.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/loopx-performance-diagnosis .gemini/skills/loopx-performance-diagnosis && 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 "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .gemini/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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 loopx-project/loopx loopx-performance-diagnosisInstalls 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 loopx-project/loopx --skill loopx-performance-diagnosis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/loopx-project/loopx.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/loopx-performance-diagnosis .github/skills/loopx-performance-diagnosis && 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 "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .github/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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 loopx-project/loopx --skill loopx-performance-diagnosis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install loopx-project/loopx loopx-performance-diagnosis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/loopx-project/loopx.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/loopx-performance-diagnosis .opencode/skills/loopx-performance-diagnosis && 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 "loopx-performance-diagnosis" agent skill from https://github.com/loopx-project/loopx/tree/main/skills/loopx-performance-diagnosis into .opencode/skills/loopx-performance-diagnosis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "loopx-performance-diagnosis", 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
loopx-performance-diagnosis- GitHub stars
- 6.2k
- Token cost
- ~880 tokens
- SKILL.md length
- 428 words
- Files
- 3
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Profiles a slow command or runtime you own with the right profiler for its language, using uninstrumented baseline timings and keeping raw profiling evidence local and private.
- Works in 7 steps: Run the uninstrumented target and record… → Verify the optional tool version… → Write the exact target argv to an… → …
- Finding out why a command you own got slower than before
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Choosing a profiler for a Python, Node or compiled-language performance regression
What it does
This skill guides diagnosis of a demonstrated slowdown in CPU time, wall time, allocations or IO. The agent states the real user operation and the failure observed, keeps the exact source, interpreter, inputs and concurrency, and runs the target without instrumentation first to record ordinary elapsed time from repeated controlled samples. Profiling time never counts as a baseline.
Tool choice depends on the runtime: Pyinstrument for Python waits and startup, py-spy for Python threads and native code on Linux, Memray for allocations, and V8 CPU or heap profiles for Node and TypeScript, while Go, JVM and kernel costs need their own tools. The agent writes the target's argv to an ignored JSON file, asks the loopx CLI for a plan, runs the profile command as an argv array without shell interpolation, then reads the result with the loopx inspect command. It does not attach to production processes, raise privileges or start paid or remote workloads without authorization, and raw stacks and paths stay out of public summaries. The excerpt is cut off after the fifth step.
When your agent uses it
- Finding out why a command you own got slower than before
- Choosing a profiler for a Python, Node or compiled-language performance regression
- Collecting profiling evidence that keeps paths and stack traces out of public reports
Example prompts
- “Our nightly import script went from a short run to many minutes; profile it and tell me where the time goes.”
- “Use Memray to see why this Python job's memory climbs during the export step.”
- “Take a baseline of the build command first, then profile it with the right tool.”
Requirements
- The loopx CLI
- The profiler that matches the runtime, installed in an isolated environment
Workflow steps
7 steps, taken from the first numbered list in SKILL.md.
- Run the uninstrumented target and record ordinary elapsed time. Use repeated
- Verify the optional tool version locally. Preserve the selected interpreter;
- Write the exact target argv to an ignored JSON array. Run
- Execute profile_argv through the Host executor as an argv array without shell
- Require actual successful target exit and nonempty artifact. Read Speedscope
- Turn the hotspot into a falsifiable hypothesis. Use a controlled intervention
- Repeat the original uninstrumented workload and semantic checks after a fix.
What it can do on your machine
Read from SKILL.md and the folder at commit 82d1b83. 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
LoopX Performance Diagnosis loads about 880 tokens when it runs. Until then it costs about 75 tokens; SKILL.md has 428 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 loopx-project/loopx at commit 82d1b83, republished under its Apache-2.0 licence (© loopx-project). 428 words, ~880 tokens.
Download SKILL.mdSave it as
.claude/skills/loopx-performance-diagnosis/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- loopx-performance-diagnosis
- description
- Diagnose an owned slow command or runtime with language-appropriate profilers, independent baseline measurements and local-private evidence. Use for demonstrated CPU, wall-time, allocation or IO regressions; profiling does not qualify a budget or grant execution authority.
LoopX performance diagnosis
Read the current Goal/Todo contract and repository optimization evidence rules. State the real user operation, observed failure and owning acceptance. Preserve the exact source, runtime/interpreter, backend/history, inputs and concurrency. Use an owned disposable target for writes. Do not attach to a production process, elevate privileges, weaken OS policy, or start paid/remote workloads without the existing authorization. Raw stacks, paths, arguments and profiles stay ignored and local-private; public summaries contain only generalized evidence.
Read loopx/capabilities/performance_diagnosis/README.md for tool selection and
blind spots. On installed copies use loopx capability show performance-diagnosis
to locate its canonical documentation. Python waits/startup: Pyinstrument; Python
threads/native on Linux: py-spy; allocations: Memray; Node/TS: V8 CPU/heap.
Go/JVM/kernel costs need their native tools. Research official sources when the
installed runtime or missing evidence makes the documented choice uncertain.
Do not choose a tool from popularity or claim one profiler covers every layer.
- Run the uninstrumented target and record ordinary elapsed time. Use repeated controlled samples for comparisons; profiling time is not a baseline or p95.
- Verify the optional tool version locally. Preserve the selected interpreter; install optional tools in an isolated environment when authorized. Do not silently install them into product dependencies or fall back on permissions.
- Write the exact target argv to an ignored JSON array. Run
loopx performance-diagnosis plan --tool TOOL --command-json FILE --output-directory FRESH_IGNORED_DIRECTORY --format json. Read the whole plan. A plan has not executed or verified tool readiness. - Execute
profile_argvthrough the Host executor as an argv array without shell interpolation. Capture only the owned process; record failures and coverage gaps. Profile a separate Node worker instead of inferring its CPU from Python transport waits. Do not collect locals or automatically profile unrelated children. - Require actual successful target exit and nonempty artifact. Read Speedscope
or V8 CPU using
loopx performance-diagnosis inspect --profile-json FILE --format json; Memray/heap use their own reporters. Keep threads independent and self/inclusive time distinct. Never sum inclusive rows to obtain latency. - Turn the hotspot into a falsifiable hypothesis. Use a controlled intervention to distinguish caller/transport, shared semantics and backend cost. Reuse the owning contract; do not skip freshness, authority checks or decision inputs.
- Repeat the original uninstrumented workload and semantic checks after a fix. Preserve passed, failed and untested results and update the existing checkpoint. Readback of a stack does not prove root cause, improvement or provider admission.
Show full SKILL.md (34 more words)Show less
Do not add a new receipt/approval requirement or automatically mutate scheduling, Goal state or telemetry. Stop invoking the workflow to disable it; remove optional tools/captures from their owned local environment when no longer needed.
© loopx-project, 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 in skills/loopx-performance-diagnosis of loopx-project/loopx.
- SKILL.md
- .loopx-skill-scope
- agents/openai.yaml
Open the folder on GitHubat commit 82d1b83
Compare with similar skills
LoopX Performance Diagnosis 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 |
|---|---|---|---|---|---|---|
| LoopX Performance Diagnosis this skillloopx-project/loopx | 6.2k | — | ~880 | Automated safety check: Pass | Apache-2.0 | |
| Mecatl Perf MCP Interpretationstacklok/mecatl | 241 | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| Debugging Techniquesancoleman/ai-design-components | 526 | — | ~3.3k | Automated safety check: Pass | MIT | |
| Python Performance Optimizationwshobson/agents | 40k | 13 repos | ~814 | Automated safety check: Pass | MIT | |
| Keybase RPC Log Analysiskeybase/client | 9.3k | — | ~3k | Automated safety check: Pass | BSD-3-Clause | |
| The Art of Debuggingstas00/the-art-of-debugging | 1.7k | — | ~6.1k | Automated safety check: Notes | CC-BY-SA-4.0 |
Similar skills
Debugging Techniques
ancoleman/ai-design-components
Debugging workflows for Python (pdb, debugpy), Go (delve), Rust (lldb), and Node.js, including container debugging (kubectl debug, ephemeral containers) and production-safe debugging techniques with…
Python Performance Optimization
wshobson/agents
Profiles slow Python code with cProfile and memory profilers, then applies targeted fixes for CPU, memory, I/O and query bottlenecks.
Keybase RPC Log Analysis
keybase/client
Captures a clean Keybase service log and analyzes it for redundant, duplicated or looping RPCs, then checks whether a caching fix reduced the calls.
The Art of Debugging
stas00/the-art-of-debugging
Condensed debugging method and tool recipes for Unix, Python and PyTorch programs: crashes, hangs, segfaults, wrong output, CUDA OOM, NaN values and slowness.
Kernel Debugging Advanced
mohitmishra786/low-level-dev-skills
Advanced kernel debugging skill for ftrace, trace-cmd, perf, kprobes, kgdb, and crash analysis.
More from loopx-project/loopx
All 12 skills in this repoLoopX PR Program Manager
loopx-project/loopx
Tracks a group of pull or merge requests across repositories as durable LoopX state: inventory, reconcile changes, keep priorities and a roadmap, and monitor over time.
LoopX Self Repair
loopx-project/loopx
Diagnoses surprising LoopX behavior, such as stale recommendations or tiny progress, assigns it to the responsible layer and repairs it at the lowest durable level.
LoopX Auto-Research Worker
loopx-project/loopx
Role playbook for a LoopX worker running an auto-research lane, with execution checklists, artifact contracts and stop conditions.
LoopX Benchmark Operator
loopx-project/loopx
Operates or analyzes a LoopX-managed benchmark experiment: launching runs, maintaining the experiment board, qualifying integrity, and writing case insights.
LoopX Doc Registry
loopx-project/loopx
Registers durable project materials such as design docs, SOPs and research notes in a LoopX project's own registry so future agents can find them without raw URLs or private content.
LoopX PR Review
loopx-project/loopx
Runs an evidence-backed pull request review through the loopx CLI and posts bilingual reviews: a full Chinese review plus one concise English verdict.
Related
Works with
Categories
Questions about LoopX Performance Diagnosis
What does LoopX Performance Diagnosis do?
Profiles a slow command or runtime you own with the right profiler for its language, using uninstrumented baseline timings and keeping raw profiling evidence local and private. This skill guides diagnosis of a demonstrated slowdown in CPU time, wall time, allocations or IO. The agent states the real user operation and the failure observed, keeps the exact source, interpreter, inputs and concurrency, and runs the target without instrumentation first to record ordinary elapsed time from repeated controlled samples.
When should I use LoopX Performance Diagnosis?
LoopX Performance Diagnosis fits situations like: finding out why a command you own got slower than before; choosing a profiler for a Python, Node or compiled-language performance regression; collecting profiling evidence that keeps paths and stack traces out of public reports.
How do I install LoopX Performance Diagnosis in Claude Code?
Run `npx skills add loopx-project/loopx --skill loopx-performance-diagnosis -a claude-code`. Or copy the skill folder (skills/loopx-performance-diagnosis in loopx-project/loopx) into .claude/skills/loopx-performance-diagnosis in your project. Claude Code loads it when a task matches its description.
How do I install LoopX Performance Diagnosis in Codex?
Run `npx skills add loopx-project/loopx --skill loopx-performance-diagnosis -a codex`. Or copy the skill folder (skills/loopx-performance-diagnosis in loopx-project/loopx) into .agents/skills/loopx-performance-diagnosis in your project. Codex loads it when a task matches its description.
Can I use LoopX Performance Diagnosis 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 loopx-project/loopx --skill loopx-performance-diagnosis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/loopx-performance-diagnosis, .gemini/skills/loopx-performance-diagnosis, .github/skills/loopx-performance-diagnosis and .opencode/skills/loopx-performance-diagnosis in your project.
What does LoopX Performance Diagnosis need to run?
SKILL.md names no scripts, command-line tools or credentials: LoopX Performance Diagnosis is instructions for the agent only. Our summary lists: The loopx CLI; The profiler that matches the runtime, installed in an isolated environment.
Does LoopX Performance Diagnosis 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 LoopX Performance Diagnosis 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 LoopX Performance Diagnosis use?
LoopX Performance Diagnosis 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 LoopX Performance Diagnosis use?
About 880 tokens (SKILL.md is roughly 3.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to LoopX Performance Diagnosis?
Skills that share tags, products or a category with LoopX Performance Diagnosis: Mecatl Perf MCP Interpretation (stacklok/mecatl, 241 stars), Debugging Techniques (ancoleman/ai-design-components, 526 stars), Python Performance Optimization (wshobson/agents, 40k stars) and Keybase RPC Log Analysis (keybase/client, 9.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LoopX Performance Diagnosis?
loopx-project (a GitHub organization) maintains it in loopx-project/loopx, which has 6,190 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 8, 2026.
Source: loopx-project/loopx on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.