Agent skill · Code Review & Quality

self-improver

Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from my results", "post-mortem on my campaign".

Affitorgithub.com/AffitorGitHub ↗
claude-codecursorMIT
Install
npx skills add Affitor/affiliate-skills --skill self-improver --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 10 KB
Bundled scripts: none
Version: 1.0.0
Declared author: affitor
Requires: Claude Code, ChatGPT, Gemini CLI, Cursor, Windsurf, OpenClaw, any AI agent
Path: skills/meta/self-improver/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 586
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Self-Improver Review affiliate campaign results, diagnose what worked and what didn't, and generate a prioritized improvement plan. Uses affiliate-specific diagnostic frameworks (offer-market fit, traffic-content match, funnel leak analysis) to identify root causes and actionable fixes. ## Stage S8: Meta — Most affiliates repeat the same mistakes because they never do structured retrospectives. Self-Improver closes the feedback loop: it takes your results, compares them to expectations, diagnoses gaps using affiliate-specific frameworks, and produces concrete actions that feed back into S1-S7 for the next iteration. ## When to Use - User has run a campaign and wants to understand results - User's affiliate content isn't converting and wants to diagnose why - User wants to compare actual vs expected results - User says "what went wrong?", "why no conversions?", "how to improve?" - User wants a structured retrospective on their affiliate efforts - Chaining from S6.3 (performance-report) — analyze the data and plan improvements ## Input Schema ```yaml campaign: description: string # REQUIRED — what was done (e.g., "Published 3 blog reviews # of AI video tools, shared on LinkedIn and

What's inside
Steps it walks through
  1. Stage
  2. When to Use
  3. Input Schema
  4. Workflow
  5. Step 1: Establish Baseline
  6. Step 2: Compare Results vs Expectations
  7. Step 3: Diagnose Root Causes
  8. Step 4: Prioritize Improvements
  9. Step 5: Create Iteration Plan
  10. Step 6: Self-Validation
  11. Output Schema
  12. Output Format
  13. Error Handling
  14. Examples
Ships with 1 file
  • LICENSE.txt
More from affiliate-skills
All skills →
About this skill
What does the self-improver skill do?

Review affiliate campaign results and improve strategy. Triggers on: "review my results", "what went wrong", "how to improve conversions", "analyze my campaign", "affiliate retrospective", "why am I not converting", "improve my strategy", "what should I change", "campaign review", "optimize my approach", "learn from my results", "post-mortem on my campaign".

How do I install it?

Run `npx skills add Affitor/affiliate-skills --skill self-improver --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From Affitor/affiliate-skills, a repository with 586 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going