Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements.

No licenceAuto-check passed

Install Reflect

skills CLI
$ npx skills add haddock-development/claude-reflect-system --skill reflect -a claude-code

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

GitHub CLI
$ gh skill install haddock-development/claude-reflect-system reflect --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/haddock-development/claude-reflect-system.git skills-src && mkdir -p .claude/skills && cp -r skills-src/reflect .claude/skills/reflect && 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
reflect
GitHub stars
379
Token cost
~725 tokens
SKILL.md length
276 words
Files
22 (incl. scripts, references)
Skills in repo
2
Repo updated
First seen
Licence
None found

At a glance

Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements.

  • Works in 3 steps: Manual Reflection (/reflect) → Automatic Reflection → Toggle Commands
  • Users provide corrections
  • SKILL.md covers Overview, Usage Modes, Confidence Levels and Workflow, plus 3 more sections
  • Runs Python and Shell scripts from its folder

What it does

Reflect is an agent skill from haddock-development/claude-reflect-system. Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Use this skill when users provide corrections, express preferences about code style, or when patterns emerge from successful approaches. Can be triggered manually with /reflect or automatically at session end when enabled.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 25 other files, including scripts and reference files (for example `.state/auto-reflection.json`, `README.md` and `USER_GUIDE.md`).

It works with Python. The repository describes itself as: Continual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes.

When your agent uses it

  • Users provide corrections
  • Express preferences about code style
  • Patterns emerge from successful approaches

Example prompts

  • “Use the reflect skill to analyz conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements”
  • “/reflect”

Requirements

  • Python 3
  • A Bash shell

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Manual Reflection (/reflect)
  2. Automatic Reflection
  3. Toggle Commands

What it can do on your machine

Read from SKILL.md and the folder at commit 41d03d0. 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

    Ships 8 files in scripts/ (Python and Shell, from the files we listed), which the agent can run.

    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 loads about 725 tokens when it runs, and up to ~2.3k if it reads all its reference files. Until then it costs about 89 tokens; SKILL.md has 276 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~725
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.3k

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 276 words (~725 tokens).

“This skill enables Claude Code to learn from conversations by analyzing corrections, approvals, and patterns, then proposing updates to relevant skills. It implements a "correct once, never again" learning system.”

— opening of SKILL.md by haddock-development
name
reflect

Read the full SKILL.md on GitHub

Files

SKILL.md and 21 other files (scripts, references) in reflect of haddock-development/claude-reflect-system.

  • SKILL.md
  • .state/auto-reflection.json
  • .state/last-reflection.timestamp
  • README.md
  • USER_GUIDE.md
  • commands/reflect-meta.md
  • commands/reflect-promote.md
  • commands/reflect-stats.md
  • references/signal-patterns.md
  • scripts/extract_signals.py
  • scripts/hook-stop.sh
  • scripts/learning_ledger.py
  • scripts/meta_learning.py
  • scripts/present_review.py
  • scripts/promote_learning.py
  • scripts/reflect.py
  • scripts/scope_analyzer.py
  • … and 5 more

Open the folder on GitHubat commit 41d03d0

Compare with similar skills

Reflect 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Reflect this skillhaddock-development/claude-reflect-system379—~725Automated safety check: PassNone
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 48 repos~2k tokens
    Documents & OfficeAuto-check passed
  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes
  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

More from haddock-development/claude-reflect-system

  • Python Project Creator

    haddock-development/claude-reflect-system

    Creates Python projects with proper structure, virtual environments, and dependency management.

    379 GitHub stars~1.4k tokensUpdated 8 mo ago
    Auto-check: notes

Works with

Questions about Reflect

What does Reflect do?

Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements. Reflect is an agent skill from haddock-development/claude-reflect-system. Analyzes conversation transcripts to extract user corrections, patterns, and preferences, then proposes skill improvements.

When should I use Reflect?

Reflect fits situations like: users provide corrections; express preferences about code style; patterns emerge from successful approaches.

How do I install Reflect in Claude Code?

Run `npx skills add haddock-development/claude-reflect-system --skill reflect -a claude-code`. Or copy the skill folder (reflect in haddock-development/claude-reflect-system) into .claude/skills/reflect in your project. Claude Code loads it when a task matches its description.

How do I install Reflect in Codex?

Run `npx skills add haddock-development/claude-reflect-system --skill reflect -a codex`. Or copy the skill folder (reflect in haddock-development/claude-reflect-system) into .agents/skills/reflect in your project. Codex loads it when a task matches its description.

Can I use Reflect 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 haddock-development/claude-reflect-system --skill reflect -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, .gemini/skills/reflect, .github/skills/reflect and .opencode/skills/reflect in your project.

What does Reflect need to run?

Going by SKILL.md and its folder, Reflect needs Python and a shell for the scripts in its folder. Our summary lists: Python 3; A Bash shell.

Does Reflect 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 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Reflect use?

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

How many tokens does Reflect use?

About 725 tokens (SKILL.md is roughly 2.9k 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 Reflect?

Skills that share tags, products or a category with Reflect: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Reflect?

haddock-development (a GitHub user) maintains it in haddock-development/claude-reflect-system, which has 379 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on January 17, 2026.

Source: haddock-development/claude-reflect-system on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.