WeChat Account Topic and Title Writer
BigPengSays/bigpeng-hot-gzh
Produces topic directions and candidate headlines for WeChat official account articles using seven title formulas, without writing the article itself.
Improves copy by scoring each draft against explicit criteria, diagnosing weak spots and rewriting until every criterion passes a threshold, for headlines, CTAs and ads.
Install Recursive Improvement Loop
$ npx skills add dylanfeltus/skills --skill recursive-improvement -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install dylanfeltus/skills recursive-improvement --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/dylanfeltus/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/recursive-improvement .claude/skills/recursive-improvement && 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 "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .claude/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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/dylanfeltus/skills/tree/main/recursive-improvementType 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 dylanfeltus/skills --skill recursive-improvement -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install dylanfeltus/skills recursive-improvement --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/recursive-improvement .agents/skills/recursive-improvement && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .agents/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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 dylanfeltus/skills --skill recursive-improvement -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install dylanfeltus/skills recursive-improvement --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/recursive-improvement .cursor/skills/recursive-improvement && 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 "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .cursor/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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/dylanfeltus/skills.git --path recursive-improvement--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 dylanfeltus/skills --skill recursive-improvement -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install dylanfeltus/skills recursive-improvement --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/recursive-improvement .gemini/skills/recursive-improvement && 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 "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .gemini/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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 dylanfeltus/skills recursive-improvementInstalls 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 dylanfeltus/skills --skill recursive-improvement -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/recursive-improvement .github/skills/recursive-improvement && 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 "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .github/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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 dylanfeltus/skills --skill recursive-improvement -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install dylanfeltus/skills recursive-improvement --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/dylanfeltus/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/recursive-improvement .opencode/skills/recursive-improvement && 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 "recursive-improvement" agent skill from https://github.com/dylanfeltus/skills/tree/main/recursive-improvement into .opencode/skills/recursive-improvement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recursive-improvement", 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
recursive-improvement- GitHub stars
- 179
- Token cost
- ~1.3k tokens
- SKILL.md length
- 565 words
- Files
- 2
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Improves copy by scoring each draft against explicit criteria, diagnosing weak spots and rewriting until every criterion passes a threshold, for headlines, CTAs and ads.
- Works in 5 steps: Generate → Evaluate → Diagnose → …
- Polishing a headline or call to action that has to perform
- SKILL.md covers The Pattern, How It Works, Adversarial Pressure (Optional… and Example Criteria by Use Case, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
The pattern runs in five steps: generate a draft, score it on each criterion from 1 to 10, diagnose what is weak and why, rebuild the weak sections instead of patching them, and repeat until every score clears the threshold, usually 8 out of 10. It is meant for important content rather than quick first drafts.
An optional adversarial pass attacks a passing draft as a skeptical customer, a distracted scroller or a competitor. Example criteria tables are given by use case: social content (hook strength, curiosity gap, clarity, voice match, engagement, thumb-stop power, value density, CTA clarity) and landing page copy (headline clarity, value proposition, benefit focus, CTA effectiveness, trust signals, readability, objection handling, specificity).
When your agent uses it
- Polishing a headline or call to action that has to perform
- Improving landing page or ad copy against a scoring rubric
- Checking social posts for hook strength and clarity before posting
- Stress-testing copy from a skeptical reader's point of view
Example prompts
- “Write three headline options for our invoicing app and iterate each until it scores at least 8 out of 10.”
- “Run the improvement loop on this LinkedIn post and show the scores for each round.”
- “Score my landing page hero copy, then rewrite the weak parts.”
Workflow steps
5 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit b97a48f. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Recursive Improvement Loop loads about 1.3k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 565 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 dylanfeltus/skills at commit b97a48f, republished under its MIT licence (© dylanfeltus). 565 words, ~1,327 tokens.
Download SKILL.mdSave it as
.claude/skills/recursive-improvement/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- recursive-improvement
- description
- A pattern for generating higher-quality output by iterating against explicit scoring criteria. Use for headlines, CTAs, landing page copy, social content, ad copy — anything where quality matters. Generate → Evaluate → Diagnose → Improve → Repeat.
Recursive Self-Improvement Loop
A pattern for generating higher-quality output by iterating against explicit scoring criteria.
The Pattern
generate → evaluate → diagnose → improve → repeat (until passing)Never ship first-draft output for important content. Run the loop.
How It Works
1. Generate
Create the initial output as you normally would.
2. Evaluate
Score the output against each criterion (1-10). Be brutally honest.
3. Diagnose
For any criterion scoring below threshold:
- What specifically is weak?
- Why does it fail?
- What would "passing" look like?
4. Improve
Rewrite addressing each diagnosed weakness. Don't patch — rebuild the weak sections.
5. Repeat
Re-evaluate. Keep looping until all criteria pass threshold (usually 8/10 minimum).
Adversarial Pressure (Optional but Powerful)
After passing criteria, attack the output from a hostile perspective:
- Skeptical customer: "Why should I believe this? What's the catch?"
- Distracted scroller: "Would I stop for this? In 2 seconds?"
- Competitor: "How would a rival tear this apart?"
If it survives, ship it. If not, iterate.
Example Criteria by Use Case
Social Content
| Criterion | What to evaluate |
|---|---|
| Hook strength | First line grabs attention? Pattern interrupt? |
| Curiosity gap | Creates urge to keep reading? |
| Clarity | One clear idea? No confusion? |
| Voice match | Sounds like the target voice/brand? |
| Engagement potential | People will reply/share/save? |
| Thumb-stop power | Scroller would pause? |
| Value density | Every line earns its place? |
| CTA clarity | Clear what reader should do next? |
Adversarial test: Would a distracted, skeptical user at 11pm engage with this?
Landing Page / Web Copy
| Criterion | What to evaluate |
|---|---|
| Headline clarity | Instantly clear what this business does? |
| Value prop strength | Why choose them over competitors? |
| Benefit focus | Features translated to customer benefits? |
| CTA effectiveness | Clear, compelling action? Low friction? |
| Trust signals | Credibility established? Social proof? |
| Readability | Scannable? Short paragraphs? Clear hierarchy? |
| Objection handling | Common concerns addressed? |
| Specificity | Concrete details vs vague claims? |
Adversarial test: Would someone searching on their phone take action within 30 seconds?
Email Copy
| Criterion | What to evaluate |
|---|---|
| Subject line | Would this get opened? Stands out in inbox? |
| Opening hook | First sentence earns the second? |
| Single focus | One clear ask per email? |
| Skimmability | Can get the gist in 5 seconds? |
| CTA prominence | Action is obvious and easy? |
| Voice consistency | Matches brand/sender personality? |
| Length appropriate | No fluff, nothing missing? |
| Mobile friendly | Works on small screens? |
Adversarial test: Would a busy person with 200 unread emails act on this?
Show full SKILL.md (190 more words)Show less
Ad Copy
| Criterion | What to evaluate |
|---|---|
| Thumb-stop power | Pattern interrupt in first 2 seconds? |
| Curiosity gap | Creates need to know more? |
| Emotional trigger | Hits a real pain point or desire? |
| Credibility | Believable? Not too good to be true? |
| CTA strength | Clear next step with low friction? |
| Persona match | Speaks directly to target audience? |
| Differentiation | Stands out from competitor ads? |
| Platform native | Fits the platform's style/format? |
Adversarial test: Would this stop YOUR scroll? Would you click?
When to Use
Always use for:
- Headlines and hooks
- CTAs and value props
- Key landing page sections
- Social posts (especially threads)
- Ad copy
- Important emails
Can skip for:
- Internal notes
- First-pass brainstorming
- Technical documentation
- Boilerplate content
Building Your Own Criteria
- Pick one task you do repeatedly
- Write down how YOU evaluate that output — what makes "good" vs "mid"?
- Turn each into a pass/fail threshold — be specific ("9/10 minimum" not "make it good")
- Add adversarial pressure — who would attack this? What would they say?
- Save and reuse — now you have a system, not just a prompt
Quick Loop Template
## Output v1
[Initial generation]
## Evaluation v1
- Hook strength: 6/10 — Opens weak, no pattern interrupt
- Clarity: 8/10 — Clear enough
- Voice match: 7/10 — Too formal
[... score all criteria]
## Diagnosis
1. Hook needs a surprising stat or contrarian take
2. Voice should be more casual, shorter sentences
3. [...]
## Output v2
[Revised version addressing weaknesses]
## Evaluation v2
[Re-score — continue until all pass]The loop typically adds 2-3 iterations. Worth it for anything that matters.
© dylanfeltus, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in recursive-improvement of dylanfeltus/skills.
- SKILL.md
- README.md
Open the folder on GitHubat commit b97a48f
Compare with similar skills
Recursive Improvement Loop 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 |
|---|---|---|---|---|---|---|
| Recursive Improvement Loop this skilldylanfeltus/skills | 179 | — | ~1.3k | Automated safety check: Pass | MIT | |
| WeChat Account Topic and Title WriterBigPengSays/bigpeng-hot-gzh | 265 | — | ~501 | Automated safety check: Pass | MIT | |
| WeChat Article Title Strategistliucongg/liucong-skills | 248 | — | ~471 | Automated safety check: Pass | Apache-2.0 | |
| WeChat Article Topics and Titlesaiworkskills/wechat-article-skills | 667 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Money Contentiamzifei/show-me-the-money | 1k | — | ~9.6k | Automated safety check: Pass | Custom licence | |
| Content Engineindranilbanerjee/digital-marketing-pro | 855 | 1 repos | ~8.9k | Automated safety check: Pass | MIT |
Similar skills
WeChat Article Title Strategist
liucongg/liucong-skills
Generates, rewrites, critiques and ranks titles for Chinese WeChat official account articles, grounded in the article's real content and any history data supplied.
WeChat Article Topics and Titles
aiworkskills/wechat-article-skills
Researches topics, titles, digests and series plans for WeChat Official Account articles; used on its own only to revise titles or digests that already exist.
Money Content
iamzifei/show-me-the-money
Automated content creation pipeline for business growth. An agent skill from iamzifei/show-me-the-money.
Content Engine
indranilbanerjee/digital-marketing-pro
Draft marketing content in brand voice — blog posts, ad copy, email sequences, social posts, landing pages, and brand-voice guides — through a gated pipeline (research, outline, draft, fact-check…
Content Writer Agent
mastra-ai/mastra
Authoring playbook for building agents that draft written content — blog posts, marketing copy, social media posts, newsletters, product descriptions, landing pages, or ad copy.
More from dylanfeltus/skills
All 10 skills in this repoApp Store Intelligence
dylanfeltus/skills
Looks up app details, ratings and reviews and searches the iOS and Mac App Stores through Apple's free iTunes APIs, with a web-search fallback for Google Play.
AI Image Creative Direction
dylanfeltus/skills
Gives prompt templates, a model-selection guide and anti-generic rules for AI-generated visuals: hero images, feature illustrations, OG cards, icons and backgrounds.
Design Token Generator
dylanfeltus/skills
Generates type scales, color palettes, spacing systems, WCAG contrast checks and dark mode palettes from formulas, as CSS custom properties, a Tailwind config or JSON tokens.
Hacker News Search
dylanfeltus/skills
Searches and monitors Hacker News stories, comments and users through the free Algolia HN Search API, with tag, points and date filters.
Motion Design Patterns for React
dylanfeltus/skills
Framer Motion (Motion) patterns for React: spring presets, staggers, layout animations, micro-interactions, scroll effects and page transitions, with performance rules.
Privacy.com Virtual Cards
dylanfeltus/skills
Creates, updates, and monitors Privacy.com virtual payment cards with spending limits for an agent making controlled purchases.
Related
Categories
Questions about Recursive Improvement Loop
What does Recursive Improvement Loop do?
Improves copy by scoring each draft against explicit criteria, diagnosing weak spots and rewriting until every criterion passes a threshold, for headlines, CTAs and ads. The pattern runs in five steps: generate a draft, score it on each criterion from 1 to 10, diagnose what is weak and why, rebuild the weak sections instead of patching them, and repeat until every score clears the threshold, usually 8 out of 10. It is meant for important content rather than quick first drafts.
When should I use Recursive Improvement Loop?
Recursive Improvement Loop fits situations like: polishing a headline or call to action that has to perform; improving landing page or ad copy against a scoring rubric; checking social posts for hook strength and clarity before posting; stress-testing copy from a skeptical reader's point of view.
How do I install Recursive Improvement Loop in Claude Code?
Run `npx skills add dylanfeltus/skills --skill recursive-improvement -a claude-code`. Or copy the skill folder (recursive-improvement in dylanfeltus/skills) into .claude/skills/recursive-improvement in your project. Claude Code loads it when a task matches its description.
How do I install Recursive Improvement Loop in Codex?
Run `npx skills add dylanfeltus/skills --skill recursive-improvement -a codex`. Or copy the skill folder (recursive-improvement in dylanfeltus/skills) into .agents/skills/recursive-improvement in your project. Codex loads it when a task matches its description.
Can I use Recursive Improvement Loop 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 dylanfeltus/skills --skill recursive-improvement -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recursive-improvement, .gemini/skills/recursive-improvement, .github/skills/recursive-improvement and .opencode/skills/recursive-improvement in your project.
What does Recursive Improvement Loop need to run?
SKILL.md names no scripts, command-line tools or credentials: Recursive Improvement Loop is instructions for the agent only.
Does Recursive Improvement Loop 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 Recursive Improvement Loop 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 Recursive Improvement Loop use?
Recursive Improvement Loop 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 Recursive Improvement Loop use?
About 1.3k tokens (SKILL.md is roughly 5.3k 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 Recursive Improvement Loop?
Skills that share tags, products or a category with Recursive Improvement Loop: WeChat Account Topic and Title Writer (BigPengSays/bigpeng-hot-gzh, 265 stars), WeChat Article Title Strategist (liucongg/liucong-skills, 248 stars), WeChat Article Topics and Titles (aiworkskills/wechat-article-skills, 667 stars) and Money Content (iamzifei/show-me-the-money, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Recursive Improvement Loop?
dylanfeltus (a GitHub user) maintains it in dylanfeltus/skills, which has 179 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 17, 2026.
Source: dylanfeltus/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.