skill CX Codex

perf-investigation-logger — Claude Code skill: how to install

Q: How do I install perf-investigation-logger in Claude Code?

Run `npx skills add composio-community/awesome-claude-plugins --skill perf-investigation-logger -a claude-code` in your terminal.

Q: Where are the investigation notes stored?

Notes are appended to `{state-dir}/perf/investigations/.md`. The directory path resolves via `AI_STATE_DIR` or defaults to `.claude`.

Appends structured performance investigation notes, quotes, and evidence to project logs. Keeps benchmarks and optimization decisions organized.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add composio-community/awesome-claude-plugins --skill perf-investigation-logger -a claude-code
npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a claude-code

Open on GitHub

What perf-investigation-logger does

This skill writes performance findings directly into {state-dir}/perf/investigations/<id>.md. It relies on docs/perf-requirements.md as its primary reference contract.

Every logged phase captures exact user quotes, a phase summary, decisions with reasoning, and evidence pointers. Evidence must include executed commands or file paths with line references. Paraphrasing user words is strictly forbidden.

The target directory uses the AI_STATE_DIR environment variable, falling back to .claude if unset. Missing the contract file will leave your notes without defined project constraints.

What it helps with

record verbatim user feedback during performance debugging
append structured investigation summaries to markdown logs
attach evidence commands and file paths to optimization records
document performance decisions alongside their rationale

Example prompts for the agent

Log this performance phase and attach the benchmark command output
Append our profiling notes to the investigation log with the user quote
Record the latency decision into perf/investigations/<id>.md

How to install perf-investigation-logger

1Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill perf-investigation-logger -a claude-code

npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a claude-code

2Manually: put the files in place

~/.claude/skills/investigation-logger/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/investigation-logger/

1Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a codex

2Manually: put the files in place

.agents/skills/investigation-logger/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a cursor

2Manually: put the files in place

.cursor/skills/investigation-logger/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install composio-community/awesome-claude-plugins investigation-logger

2Manually: put the files in place

.github/skills/investigation-logger/SKILL.md

1Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a gemini-cli

2Platform CLI

gemini skills install https://github.com/composio-community/awesome-claude-plugins --path perf/skills/investigation-logger

Manually: put the files in place

.devin/skills/investigation-logger/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add composio-community/awesome-claude-plugins --skill investigation-logger -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about perf-investigation-logger

How do I install perf-investigation-logger in Claude Code?

Run npx skills add composio-community/awesome-claude-plugins --skill perf-investigation-logger -a claude-code in your terminal.

Where are the investigation notes stored?

Notes are appended to {state-dir}/perf/investigations/<id>.md. The directory path resolves via AI_STATE_DIR or defaults to .claude.

Can the skill summarize user quotes instead of copying them?

No. The skill enforces verbatim quotes and prohibits paraphrasing user statements.

session-logger zhaono1 Writes a short, redacted summary of an agent session: what was decided, which files were touched, what stayed open. Useful when you pick the work up later. CX Codex +1 743installs change-logger davila7 This hook writes each file mutation to a CSV: timestamp, tool, path, action and details. Handy when you are prepping a demo and need to show what the agent touched. 163installs ue-testing-debugging quodsoler A skill for logging, assertions, automation tests and profiling in Unreal Engine 5.8. Useful when the agent writes a test or digs into a bad frame time. CX Codex +1 1,300installs web-perf cloudflare Audit Core Web Vitals, diagnose rendering bottlenecks, and inspect network dependencies directly through your agent. CX Codex +1 110,200installs tilegym-improve-cutile-kernel-perf TileGym Team Systematically profiles, tunes, and benchmarks cuTile GPU kernels in TileGym. Runs iterations on real hardware to lower latency while preserving accuracy. CX Codex +1 1,600installs perf-lighthouse tech-leads-club Runs local Lighthouse audits via CLI or Node API, parses reports, and configures performance budgets. Useful for tracking Core Web Vitals and integrating speed checks into CI. CX Codex +1 320installs

From the same set8

perf-theory-tester A skill that keeps perf experiments honest: one change per hypothesis, repeated runs, a recorded verdict. Useful when you need proof that an optimization helped. CX Codex +1 1,500installs perf-profiler Runs profilers against CPU and memory hot paths, captures flame graphs, and records file and line evidence. CX Codex +1 1,600installs perf-code-paths This skill maps likely execution paths, entrypoints, and related files for a performance scenario before profiling. Useful when the hot area is unclear. CX Codex +1 1,600installs perf-theory-gatherer A skill that turns git history and code evidence into up to five hypotheses about a performance problem. CX Codex +1 1,600installs perf-benchmarker Runs benchmarks sequentially under strict duration rules to catch performance regressions and set baseline metrics. CX Codex +1 1,600installs perf-analyzer Turns profiling and experiment results into evidence-backed performance recommendations. Use it when a decision needs a traceable basis. CX Codex +1 1,600installs changelog-generator Turns git history into a user-facing changelog: sorts commits into categories and rewrites developer messages for customers. CX Codex +1 1,500installs