Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation.
Install Reflection
$ npx skills add straubt1/tfx --skill reflection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install straubt1/tfx reflection --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/straubt1/tfx.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/reflection .claude/skills/reflection && 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 "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .claude/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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/straubt1/tfx/tree/main/.claude/skills/reflectionType 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 straubt1/tfx --skill reflection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install straubt1/tfx reflection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/straubt1/tfx.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/reflection .agents/skills/reflection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .agents/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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 straubt1/tfx --skill reflection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install straubt1/tfx reflection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/straubt1/tfx.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/reflection .cursor/skills/reflection && 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 "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .cursor/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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/straubt1/tfx.git --path .claude/skills/reflection--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 straubt1/tfx --skill reflection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install straubt1/tfx reflection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/straubt1/tfx.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/reflection .gemini/skills/reflection && 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 "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .gemini/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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 straubt1/tfx reflectionInstalls 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 straubt1/tfx --skill reflection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/straubt1/tfx.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/reflection .github/skills/reflection && 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 "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .github/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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 straubt1/tfx --skill reflection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install straubt1/tfx reflection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/straubt1/tfx.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/reflection .opencode/skills/reflection && 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 "reflection" agent skill from https://github.com/straubt1/tfx/tree/main/.claude/skills/reflection into .opencode/skills/reflection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "reflection", 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
reflection- GitHub stars
- 110
- Token cost
- ~793 tokens
- SKILL.md length
- 338 words
- Files
- 1
- Skills in repo
- 5
- Repo updated
- First seen
- Licence
- MIT
At a glance
This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation.
- Works in 8 steps: Read the full conversation from top to… → Review the diffs (supplementary) — Read… → Identify lessons in these categories → …
- Says reflection
- SKILL.md covers Current Git State…, Process and Output Format
- Calls git
What it does
Reflection is an agent skill from straubt1/tfx. This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation.
Its SKILL.md is about 790 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 Development. It works with Git. The repository describes itself as: TFx is a standalone CLI for HCP Terraform and Terraform Enterprise. The licence is MIT.
When your agent uses it
- Says reflection
- Reflect on the changes
- Reflect on this session
- Asks to capture lessons learned from the current conversation
Example prompts
- “reflection”
- “reflect on the changes”
- “reflect on this session”
- “/reflection”
Workflow steps
8 steps, taken from the first numbered list in SKILL.md.
- Read the full conversation from top to bottom. Pay attention to
- Review the diffs (supplementary) — Read modified files for context on what was built and why, but do not let this overshadow lessons from…
- Identify lessons in these categories
- Read the current CLAUDE.md to avoid duplicating what's already there and to find gaps.
- Propose edits to CLAUDE.md — For each lesson worth keeping, suggest the specific text to add, change, or remove, and where it belongs.
- If no lessons are found, explicitly state: "No CLAUDE.md updates needed from this session." This confirms the session was considered.
- Do not apply edits automatically. Present proposals to the user and wait for approval.
- After applying approved edits, print a brief summary in chat of what changed.
What it can do on your machine
Read from SKILL.md and the folder at commit f7494e5. 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
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Reflection loads about 793 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 338 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 straubt1/tfx at commit f7494e5, republished under its MIT licence (© straubt1). 338 words, ~793 tokens.
Download SKILL.mdSave it as
.claude/skills/reflection/SKILL.md (or your agent's skills folder).- name
- reflection
- description
- This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation.
- disable-model-invocation
- true
Reflection
The goal is to identify lessons from this session that should be permanently captured in CLAUDE.md — so future sessions benefit without repeating the same mistakes, clarifications, or decisions.
Review the entire conversation history — every message, correction, and preference — as the primary source. Code diffs are supplementary.
Current Git State (supplementary context)
- Branch: !
git branch --show-current - Changes since last commit: !
git diff --stat HEAD - Staged changes: !
git diff --stat --cached
Process
Read the full conversation from top to bottom. Pay attention to:
- Questions the user had to answer that should have been obvious from CLAUDE.md
- Corrections the user made to your approach or output
- Preferences or constraints the user stated (even casually)
- Things you got wrong on the first attempt and had to revise
- Decisions made about architecture, naming, tooling, or workflow
- Anything the user explicitly said to always/never do
Review the diffs (supplementary) — Read modified files for context on what was built and why, but do not let this overshadow lessons from the conversation itself.
Identify lessons in these categories:
- Patterns & conventions — Things that worked well and should be encoded as rules
- Gotchas & pitfalls — Things that caused confusion, required retries, or were non-obvious
- Architecture decisions — Choices made that future sessions should know about
- Workflow & communication preferences — How the user prefers to work, communicate, or receive output
- Outdated/wrong memory — Anything in CLAUDE.md or MEMORY.md that turned out to be incorrect or missing
Read the current CLAUDE.md to avoid duplicating what's already there and to find gaps.
Propose edits to CLAUDE.md — For each lesson worth keeping, suggest the specific text to add, change, or remove, and where it belongs.
If no lessons are found, explicitly state: "No CLAUDE.md updates needed from this session." This confirms the session was considered.
Do not apply edits automatically. Present proposals to the user and wait for approval.
After applying approved edits, print a brief summary in chat of what changed.
Output Format
When lessons are found:
## Reflection
### [Category]
**Lesson**: <what was learned>
**Proposed CLAUDE.md change**: <exact text, with target section>
---
(one block per lesson)When no lessons are found:
## Reflection
No CLAUDE.md updates needed from this session. The following were considered but already covered or not worth persisting:
- <item> — already in CLAUDE.md / too session-specific / etc.After applying approved changes:
## CLAUDE.md updated
- Added: "<description>" under ## Section
- Modified: "<what changed>" in ## Section
- Removed: "<what was removed>"© straubt1, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .claude/skills/reflection of straubt1/tfx.
Open the folder on GitHubat commit f7494e5
Compare with similar skills
Reflection 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 |
|---|---|---|---|---|---|---|
| Reflection this skillstraubt1/tfx | 110 | — | ~793 | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Code Review ChecklistshareAI-lab/learn-claude-code | 78k | 5 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything | 86k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Code Design Rationale Investigatorcursor/plugins | 10k | 9 repos | ~2.6k | Automated safety check: Pass | None | |
| Understand Diff AnalysisEgonex-AI/Understand-Anything | 86k | 1 repos | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
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.
Codebase Knowledge Graph Q&A
Egonex-AI/Understand-Anything
Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.
- Official
Code Design Rationale Investigator
cursor/plugins
Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
Understand Explain
Egonex-AI/Understand-Anything
Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.
More from straubt1/tfx
Go Upgrade
straubt1/tfx
Upgrade macOS Go and all module dependencies in TFx via task go:upgrade, then verify build and tests.
Release
straubt1/tfx
Prepare and cut TFx semver releases (CHANGELOG, validation, tagging via Taskfile).
Vhs Tape
straubt1/tfx
Create a VHS .tape file for recording terminal GIF/MP4/WebM demos.
New Data Function
straubt1/tfx
Create a new function in the data/ package following project conventions
Related
Works with
Categories
Questions about Reflection
What does Reflection do?
This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation. Reflection is an agent skill from straubt1/tfx. This skill should be used when the user says "reflection", "reflect on the changes", "reflect on this session", or asks to capture lessons learned from the current conversation.
When should I use Reflection?
Reflection fits situations like: says reflection; reflect on the changes; reflect on this session; asks to capture lessons learned from the current conversation.
How do I install Reflection in Claude Code?
Run `npx skills add straubt1/tfx --skill reflection -a claude-code`. Or copy the skill folder (.claude/skills/reflection in straubt1/tfx) into .claude/skills/reflection in your project. Claude Code loads it when a task matches its description.
How do I install Reflection in Codex?
Run `npx skills add straubt1/tfx --skill reflection -a codex`. Or copy the skill folder (.claude/skills/reflection in straubt1/tfx) into .agents/skills/reflection in your project. Codex loads it when a task matches its description.
Can I use Reflection 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 straubt1/tfx --skill reflection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/reflection, .gemini/skills/reflection, .github/skills/reflection and .opencode/skills/reflection in your project.
What does Reflection need to run?
Going by SKILL.md and its folder, Reflection needs the command-line tools its instructions call (git).
Does Reflection access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Reflection 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 Reflection use?
Reflection 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 Reflection use?
About 793 tokens (SKILL.md is roughly 3.2k 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 Reflection?
Skills that share tags, products or a category with Reflection: Finishing a Development Branch (obra/superpowers, 296k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 86k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Reflection?
straubt1 (a GitHub user) maintains it in straubt1/tfx, which has 110 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 28, 2026.
Source: straubt1/tfx on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.