Agent skill

Reflect Performance Review

by Nunchi-trade in Nunchi-trade/agent-cli

Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review

MITAuto-check passedBusiness, Finance & HR

Install Reflect Performance Review

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a claude-code

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

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review --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/Nunchi-trade/agent-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/reflect .claude/skills/reflect-performance-review && 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/

Paste into Claude Code

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .claude/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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

$skill-installer install https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect

Type 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.

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/reflect .agents/skills/reflect-performance-review && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .agents/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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.

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/reflect .cursor/skills/reflect-performance-review && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .cursor/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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

$ gemini skills install https://github.com/Nunchi-trade/agent-cli.git --path skills/reflect

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/reflect .gemini/skills/reflect-performance-review && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .gemini/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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.

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review

Installs 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).

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/reflect .github/skills/reflect-performance-review && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .github/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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.

skills CLI

$ npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install Nunchi-trade/agent-cli reflect-performance-review --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/Nunchi-trade/agent-cli.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/reflect .opencode/skills/reflect-performance-review && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "reflect-performance-review" agent skill from https://github.com/Nunchi-trade/agent-cli/tree/main/skills/reflect into .opencode/skills/reflect-performance-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflect-performance-review", 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: reflect-performance-review
GitHub stars: 521
Token cost: ~1.3k tokens
SKILL.md length: 538 words
Files: 1
Skills in repo: 7
Repo updated: Jul 8, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review

Works in 6 steps: Load: Read trade log from… → Pair: FIFO round-trip matching (buys to… → Compute: Win rate, PF, FDR, holding… → …
Tasks that involve Performance reviews
SKILL.md covers Architecture, Key Metrics, Usage and Agent Mandate, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Reflect Performance Review is an agent skill from Nunchi-trade/agent-cli. Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Business, Finance & HR, covering Performance reviews. The licence is MIT.

When your agent uses it

Tasks that involve Performance reviews

Example prompts

“/reflect-performance-review”

Workflow steps

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

Load: Read trade log from data/cli/trades.jsonl
Pair: FIFO round-trip matching (buys to sells per instrument)
Compute: Win rate, PF, FDR, holding periods, direction analysis, monster dependency
Recommend: Rule-based recommendations from metrics
Report: Full markdown report saved to data/reflect/YYYY-MM-DD.md
Distill: 3-5 line summary for agent memory

What it can do on your machine

Read from SKILL.md and the folder at commit 58619a2. 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 (its code samples are bash).
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

Reflect Performance Review loads about 1.3k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 538 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~32
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 Nunchi-trade/agent-cli at commit 58619a2, republished under its MIT licence (© Nunchi-trade). 538 words, ~1,285 tokens.

Download SKILL.mdSave it as .claude/skills/reflect-performance-review/SKILL.md (or your agent's skills folder).

name: reflect-performance-review
description: Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review
version: 1.0.0
author: Nunchi Trade
tags: reflect, performance, review, analytics, self-improvement
cron: 55 23 * * *
dependencies: modules/reflect_engine.py, modules/reflect_reporter.py

REFLECT — Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform

Nightly automated performance review engine. APEX runs all day — REFLECT reviews every trade at night, computing metrics, detecting patterns, and producing data-driven improvement recommendations.

Architecture

trades.jsonl → ReflectEngine.compute() → ReflectMetrics → ReflectReporter.generate() → report.md

Load: Read trade log from data/cli/trades.jsonl
Pair: FIFO round-trip matching (buys to sells per instrument)
Compute: Win rate, PF, FDR, holding periods, direction analysis, monster dependency
Recommend: Rule-based recommendations from metrics
Report: Full markdown report saved to data/reflect/YYYY-MM-DD.md
Distill: 3-5 line summary for agent memory

Key Metrics

Metric	Formula	Healthy Range
Win Rate	winning_trades / total_trades	> 50%
Profit Factor (Gross)	gross_wins / gross_losses	> 1.5
Profit Factor (Net)	(gross_wins - fees) / gross_losses	> 1.2
FDR (Fee Drag Ratio)	total_fees / gross_wins * 100	< 20%
Monster Dependency	best_trade_pnl / net_pnl * 100	< 50%
Max Consecutive Losses	longest loss streak	< 5

Usage

bash

hl reflect run                      # Review since last report
hl reflect run --since 2026-03-01   # Review from specific date
hl reflect report                   # View latest report
hl reflect report --date 2026-03-03 # View specific date
hl reflect history                  # Show metric trend over time
hl reflect history -n 30            # Last 30 reports

Agent Mandate

You are the REFLECT reviewer. Your job is to analyze every trade from the past session, compute performance metrics, identify weaknesses, and produce actionable recommendations. You run nightly — the APEX runs by day, you review at night.

RULES:

Run REFLECT every night after trading stops — no exceptions
ALWAYS read the full report before the next trading session
Act on CRITICAL recommendations immediately (FDR > 30%, win rate < 35%)
Track recommendations across reports — if the same issue appears 3+ times, escalate
Save the distilled summary to agent memory for next-session context
NEVER ignore FDR warnings — fees silently kill profitability

Decision Rules

Metric State	Severity	Action
FDR > 30%	CRITICAL	Reduce trade frequency or widen entry criteria immediately
FDR 20-30%	WARNING	Monitor — consider reducing size or frequency
FDR < 20%	OK	Fees are manageable
Win rate < 35%	CRITICAL	Tighten entry criteria — Radar threshold to 200+
Win rate 35-45%	WARNING	Review losing trades for pattern
Win rate > 50%	OK	Entries are working
Monster dep > 60%	WARNING	One trade carrying the session — diversify alpha
Monster dep > 80%	CRITICAL	Fragile — entire PnL depends on one lucky trade
Consec losses > 5	WARNING	Add loss streak circuit breaker to APEX
Long PnL < 0, Short PnL > 0	WARNING	Long entries are leaking — reduce long bias
Holding < 5 min dominates	WARNING	Over-trading — increase min hold time

Show full SKILL.md (192 more words)Show less

Anti-Patterns

Ignoring REFLECT reports: Running APEX without reviewing REFLECT is flying blind. The same mistakes repeat.
Acting on single-day anomalies: One bad day doesn't mean the strategy is broken. Look at 5+ day trends via hl reflect history.
Optimizing for win rate alone: High win rate with low profit factor means you're taking small wins and large losses. Focus on PF.
Not tracking FDR: Fees are invisible during trading but compound devastatingly. FDR is the single most important "hidden" metric.
Changing strategy after one REFLECT report: REFLECT recommendations need 3+ consistent appearances before strategy changes.

Error Recovery

Error	Cause	Fix
`No trades found`	No trading activity in period	Normal — nothing to review
`Cannot pair round trips`	Unmatched buys/sells	Open positions — REFLECT pairs only closed trades
`trades.jsonl not found`	First run or wrong data dir	Run at least one trade first
`Report generation failed`	Disk full or permissions	Check `data/reflect/` directory permissions

Composition

REFLECT is the learning layer of the APEX system. Run REFLECT nightly after APEX stops. Feed REFLECT insights back into APEX configuration (Radar thresholds, DSL presets, position sizing). Over time, REFLECT recommendations should converge as the system improves.

Cron Template

bash

# Nightly REFLECT review at 11:55 PM
55 23 * * * cd ~/agent-cli && source .venv/bin/activate && hl reflect run >> logs/reflect.log 2>&1

Files

Just SKILL.md in skills/reflect of Nunchi-trade/agent-cli.

Open the folder on GitHubat commit 58619a2

Compare with similar skills

Reflect Performance Review 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.

Reflect Performance Review compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Reflect Performance Review this skillNunchi-trade/agent-cli	521	—	~1.3k	Automated safety check: Pass	MIT	3 mo ago
Wp Performance Reviewelvismdev/claude-wordpress-skills	235	1 repos	~4.5k	Automated safety check: Pass	MIT	10 mo ago
Align Humanagentscope-ai/OpenJudge	871	—	~3.1k	Automated safety check: Pass	Apache-2.0	1 mo ago
Run Mv Hoi Reconstructionnvidia-isaac/video_to_data	861	—	~1.5k	Automated safety check: Pass	Custom licence	2 days ago
Company Analysiszhu1090093659/dsh-trading	238	—	~4.2k	Automated safety check: Pass	Custom licence	today
Windbg Diagnostic Methodmicrosoft/win-dev-skills	466	—	~1.9k	Automated safety check: Pass	MIT	3 days ago

Similar skills

Wp Performance Review
elvismdev/claude-wordpress-skills
WordPress performance code review and optimization analysis.
235 GitHub starsUsed in 1 repo~4.5k tokens
Business, Finance & HRAuto-check passed
Align Human
agentscope-ai/OpenJudge
A skill your agent uses when the user has a judge/grader and human-labeled data, and wants to measure how well the judge agrees with humans, detect systematic biases, determine whether automatic…
871 GitHub stars~3.1k tokensUpdated 1 mo ago
Business, Finance & HRAuto-check passed
Run Mv Hoi Reconstruction
nvidia-isaac/video_to_data
Run and validate the repository-local multi-view camera calibration and human-object reconstruction pipelines.
861 GitHub stars~1.5k tokensUpdated 2 days ago
Business, Finance & HRAuto-check passed
Company Analysis
zhu1090093659/dsh-trading
A skill your agent uses when the user wants to analyze a listed company, stock, business, or investment target; challenge or revise an existing company report; compare A/H or primary-listing/ADR…
238 GitHub stars~4.2k tokensUpdated today
Business, Finance & HRAuto-check passed
Windbg Diagnostic Method
microsoft/win-dev-skills
Official
Use with every WinDbg plugin investigation to apply evidence-first reasoning, confidence calibration, contrarian review, structured reporting, and deterministic validation.
466 GitHub stars~1.9k tokensUpdated 3 days ago
Business, Finance & HRAuto-check passed
AI Index
mizchi/skills
Method and tooling for measuring how AI-generated a piece of prose reads, in Japanese or English.
360 GitHub stars~3.6k tokensUpdated 9 days ago
Business, Finance & HRAuto-check passed

Questions about Reflect Performance Review

What does Reflect Performance Review do?

Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform — nightly automated performance review. Reflect Performance Review is an agent skill from Nunchi-trade/agent-cli.

When should I use Reflect Performance Review?

Reflect Performance Review fits situations like: tasks that involve Performance reviews.

How do I install Reflect Performance Review in Claude Code?

Run `npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a claude-code`. Or copy the skill folder (skills/reflect in Nunchi-trade/agent-cli) into .claude/skills/reflect-performance-review in your project. Claude Code loads it when a task matches its description.

How do I install Reflect Performance Review in Codex?

Run `npx skills add Nunchi-trade/agent-cli --skill reflect-performance-review -a codex`. Or copy the skill folder (skills/reflect in Nunchi-trade/agent-cli) into .agents/skills/reflect-performance-review in your project. Codex loads it when a task matches its description.

Can I use Reflect Performance Review 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 Nunchi-trade/agent-cli --skill reflect-performance-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reflect-performance-review, .gemini/skills/reflect-performance-review, .github/skills/reflect-performance-review and .opencode/skills/reflect-performance-review in your project.

What does Reflect Performance Review need to run?

SKILL.md names no scripts, command-line tools or credentials: Reflect Performance Review is instructions for the agent only.

Does Reflect Performance Review 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 Reflect Performance Review 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 Reflect Performance Review use?

Reflect Performance Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Reflect Performance Review use?

About 1.3k tokens (SKILL.md is roughly 5.1k 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 Reflect Performance Review?

Skills that share tags, products or a category with Reflect Performance Review: Wp Performance Review (elvismdev/claude-wordpress-skills, 235 stars), Align Human (agentscope-ai/OpenJudge, 871 stars), Run Mv Hoi Reconstruction (nvidia-isaac/video_to_data, 861 stars) and Company Analysis (zhu1090093659/dsh-trading, 238 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reflect Performance Review?

Nunchi-trade (a GitHub organization) maintains it in Nunchi-trade/agent-cli, which has 521 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on July 8, 2026.

Source: Nunchi-trade/agent-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Reflect Performance Review

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

REFLECT — Reflect, Evaluate, Fine-tune, Learn, Evolve, Correct, Transform

Architecture

Key Metrics

Usage

Agent Mandate

Decision Rules

Anti-Patterns

Error Recovery

Composition

Cron Template

Files

Compare with similar skills

Similar skills

More from Nunchi-trade/agent-cli

Related

Questions about Reflect Performance Review