auto-improve
After completing any task, extract reusable rules from what worked and what failed.
Skill by Ronnasayd Machado - github.com/Ronnasayd
Chalk Labs
Need help deploying auto-improve?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ronnasayd-auto-improve
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/auto-improve
What's inside
- Skill name
auto-improve- Description
- After completing any task, extract reusable rules from what worked and what failed. Produces output in the exact format used by agent.instructions.md (## Mandatory: Rules to Follow / ## Mandatory: Rules to Avoid). Trigger after a task finishes when the user asks for a retrospective, lessons learned, or rule extraction — or implicitly with phrases like "what did we learn", "what went wrong", "what should we avoid next time". Do NOT trigger mid-task or before execution completes.
- License
- unknown
- Metadata
- author: Ronnasayd Machado - github.com/Ronnasayd · version: 1.0.0
- Instructions
- 169 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from Ronnasayd/aipp
- 0.592score
author-claude-hook
Ronnasayd Machado - github.com/Ronnasayd
Write a new Claude Code hook script for this repo following its established conventions, then wire it into claude/settings.json and give the user the settings…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
skill-inspector
Ronnasayd
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review.
SkillAFreshness: A★ 1Claude Code +9 - 0.569score
skill-judge
Ronnasayd
Evaluate Agent Skill design quality against official specifications and best practices.
SkillAFreshness: A★ 1Claude Code +9 - 0.542score
adversarial-dev
Ronnasayd Machado - github.com/Ronnasayd
Orchestrates a code task through two separate agents in an adversarial loop — an executor that implements and a strict evaluator (no write tools) that scores…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
analyze-comfyui-workflow-json
Ronnasayd Machado - github.com/Ronnasayd
Analyze a ComfyUI workflow JSON and produce a structured map of nodes, links, subgraphs, and data flow before making changes.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
code-review
Ronnasayd Machado - github.com/Ronnasayd
A skill for performing structured code reviews based on git diffs and specialist instructions.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
compress-skill
Ronnasayd Machado - github.com/Ronnasayd
Compresses a verbose SKILL.md into a short, scannable core file by moving prose into tables, mermaid flowcharts, and reference files — without losing…
SkillBFreshness: B★ 1Claude Code +9 - 0.493score
apk-reverse
Ronnasayd Machado - github.com/Ronnasayd
Reverse engineering of Android APK files.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
codebase-linguistic-analysis-to-csv-export
Ronnasayd Machado - github.com/Ronnasayd
Identify all non-English text in a codebase (specifically Portuguese characters) and export findings to a structured CSV for translation/remediation workflows.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
codebase-rules-extractor
Ronnasayd Machado - github.com/Ronnasayd
Extract and document coding rules, patterns, conventions, and anti-patterns from a codebase.
SkillCFreshness: C★ 1Claude Code +9 - 0.483score
agent-creator
Ronnasayd Machado - github.com/Ronnasayd
Create new specialist agents, modify and improve existing agents, and validate agent behavior.
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
pdf
Ronnasayd
Use this skill whenever the user wants to do anything with PDF files.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 18, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0.0
- License
- License unknown
- Repository
- github.com/Ronnasayd/aipp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Ronnasayd Machado - github.com/Ronnasayd
- 0.592score
author-claude-hook
Ronnasayd Machado - github.com/Ronnasayd
Write a new Claude Code hook script for this repo following its established conventions, then wire it into claude/settings.json and give the user the settings…
SkillAFreshness: A★ 1Claude Code +9 - 0.542score
analyze-comfyui-workflow-json
Ronnasayd Machado - github.com/Ronnasayd
Analyze a ComfyUI workflow JSON and produce a structured map of nodes, links, subgraphs, and data flow before making changes.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
adversarial-dev
Ronnasayd Machado - github.com/Ronnasayd
Orchestrates a code task through two separate agents in an adversarial loop — an executor that implements and a strict evaluator (no write tools) that scores…
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
code-review
Ronnasayd Machado - github.com/Ronnasayd
A skill for performing structured code reviews based on git diffs and specialist instructions.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
compress-skill
Ronnasayd Machado - github.com/Ronnasayd
Compresses a verbose SKILL.md into a short, scannable core file by moving prose into tables, mermaid flowcharts, and reference files — without losing…
SkillBFreshness: B★ 1Claude Code +9 - 0.493score
apk-reverse
Ronnasayd Machado - github.com/Ronnasayd
Reverse engineering of Android APK files.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get auto-improve running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
auto-improve skill. Agent Mart. https://agentmart.dev/skills/ronnasayd-auto-improve (last updated 2026-10-24)