Reflection
This is the skill that makes Claude learn from mistakes and user corrections. It kicks in when a tool fails or when you tell Claude to do something differently, analyzing what went wrong and proposing specific updates to either skill definitions or a CLAUDE.md preferences file. The key constraint is it only suggests one change at a time and waits for your approval before applying anything. In practice, this means fewer repeated mistakes and less need to give the same instructions every session. The focus on tool failures is smart since those are concrete signals something needs fixing. Worth noting it tries to balance being specific enough to address real issues while staying generic enough to apply broadly.
- skills.sh installs
- 734
- GitHub stars
- 4
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davidkiss/smart-ai-skills --skill reflection --agent claude-codeInstalls into .claude/skills of the current project.
Files
Reflection Skill
Overview
This skill is used to learn from interaction with the user and failures in tool calls. It analyzes what worked, what didn't (tool failures), and identifies recurring patterns or explicit user preferences that should be formalized.
Objectives
- Improve Skills: Identify gaps or inefficiencies in existing skill definitions and propose concise updates.
- Store Preferences: Capture user preferences, project-specific rules, or recurring instructions in a
AGENT.mdorCLAUDE.md(when used in Claude Code) file.
Process
- Analyze: Review the conversation history, tool calls, and any failures or corrections from the user.
- Identify: Determine if a specific behavior should be codified in a skill or if a user preference has emerged.
- Propose: Formulate a single, concise change.
- If updating a skill, show a diff of the proposed change.
- If adding a preference, show the proposed addition to
CLAUDE.md.
- Confirm: Present the proposal to the user and ask for explicit confirmation without making any changes first.
- Apply Changes: Once user confirmed the changes, only then apply them
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davidkiss/smart-ai-skills
- Categories
- Documentation, AI & Agent Building
- First seen
- Apr 16, 2026
More from davidkiss/smart-ai-skills
All 5Recommended
More Documentation
syncfusion-react-query-buildersyncfusion/react-ui-components-skillsComprehensive guide to implementing Syncfusion React Query Builder component. Use this skill when building advanced filter interfaces, creating complex data que734skills.sh installs
shadcnpproenca/dot-skillsshadcn/ui component library best practices and patterns (formerly shadcn-ui). This skill should be used when writing, reviewing, or refactoring shadcn/ui compon732skills.sh installs
sparc-refineruvnet/rufloRun the SPARC Refinement and Completion phases — review code, improve test coverage, validate against specification, and generate documentation730skills.sh installs
opencode-primitivesdifferent-ai/openworkReference OpenCode docs when implementing skills, plugins, MCPs, or config-driven behavior.729skills.sh installschrome-extensionpproenca/dot-skillsChrome Extensions (Manifest V3) performance and code quality guidelines. Use when writing, reviewing, or refactoring Chrome extension code including service wor729skills.sh installs
pest-testingspatie/freek.devTests applications using the Pest 4 PHP framework. Activates when writing tests, creating unit or feature tests, adding assertions, testing Livewire components,729skills.sh installs