Results for “improv”

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Autonomous experiment loop that optimizes any file by a measurable metric. Inspired by Karpathy's autoresearch. The agent edits a target file, runs a fixed evaluation, keeps improvements (git commit), discards failures (git reset), and loops indefinitely. Use when: user wants to optimize code speed, reduce bundle/image size, improve test pass rate, optimize prompts, improve content quality (headlines, copy, CTR), or run any measurable improvement loop. Requires: a target file, an evaluation command that outputs a metric, and a git repo.

Patterns and techniques for evaluating and improving AI agent outputs. Use this skill when: - Implementing self-critique and reflection loops - Building evaluator-optimizer pipelines for quality-critical generation - Creating test-driven code refinement workflows - Designing rubric-based or LLM-as-judge evaluation systems - Adding iterative improvement to agent outputs (code, reports, analysis) - Measuring and improving agent response quality

Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.

Iteratively reviews and fixes Claude Code skill quality issues by running automated fix-review cycles using the skill-reviewer agent until they meet standards.

Generates four improved variations of any installed skill, scores them against a weighted rubric, and applies the winning version while preserving the original.

Finds architectural friction in a codebase and proposes deep-module refactors to improve testability and AI-navigability, informed by the domain glossary and ADRs.

This skill enables makepad-skills to self-improve continuously during development.

This skill enables makepad-skills to self-improve continuously during development.

Convert delivery findings into skill, eval, workflow, and documentation improvements.

This skill enables makepad-skills to self-improve continuously during development.

This skill enables makepad-skills to self-improve continuously during development.

This skill enables makepad-skills to self-improve continuously during development.

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Logs and scores skill usage quality, tracking output effectiveness, user satisfaction signals, and improvement opportunities. Expert in skill analytics, quality metrics, feedback loops, and continuous improvement. Activate on "skill logging", "skill quality", "skill analytics", "skill scoring", "skill performance", "skill metrics", "track skill usage", "skill improvement". NOT for creating skills (use agent-creator), skill documentation (use skill-coach), or runtime debugging (use debugger skills).

Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".

This skill enables makepad-skills to self-improve continuously during development.

Synthesize retrospectives into themes, root causes, decisions, and team improvements.

After a Content Factory run completes successfully, harvest prompts, character references, cost data, and quality scores; diff them against the canonical prompt_registry and character_identity store; open improvement PRs (prompt updates + new character references). Runs ONCE per successful run, then closes. Also files findings into a CF_IMPROVER_ISSUES.csv (Intelliverse audit framework pattern) for the librarian's weekly roll-up.

This skill should be used when the user wants to "improve a skill", "update skill based on feedback", "optimize skill after use", or says "自更新", "/自更新". Collects user feedback after using a skill and automatically updates that skill with improvements.

>- DMAIC (Define-Measure-Analyze-Improve-Control) — Six Sigma structured problem-solving for chronic, data-driven quality improvement projects. Use when a problem recurs despite corrective actions, when a process needs systematic capability improvement, or when a customer requests a Six Sigma approach. Use 8D for reactive single-incident problems; use DMAIC for recurring systemic issues requiring statistical analysis. Covers IATF 16949 §10.1 and ISO 9001 §10.3.

Review a code file or directory and produce an evidence-backed GitHub or Jira issue proposing bug fixes, performance improvements, modularity improvements, DRY refactors, file splitting, reusable helpers, and architecture-alignment work. Use when a user asks for a code review, technical-debt proposal, refactor proposal, quality audit, bug-risk review, architecture-alignment review, or issue creation. This skill proposes work; it does not modify code.

Guide for refactoring code to improve quality without changing behavior. Use when refactoring, cleaning up code, reducing duplication, improving readability, or restructuring code. Integrates Firecrawl for researching modern patterns before refactoring, and codebase-aware dependency analysis to avoid breaking changes.

Manually improve corpus quality by adding missing docs and filling retrieval gaps

Write a useful, author-consistent article and substantively improve it before verification.

Use this skill when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand voice", or mentions content strategy, voice analysis, competitive research, or iterative content improvement.

Read-only animation audit system — analyze a project's existing animations, identify quality gaps, and generate actionable improvement plans. Never modifies source code. Phases: Recon → Parallel Audit → Vetting → Implementation Plans. Pairs with apple-design for physics validation and gsap-animation for implementation.

Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology, including dataset creation, metric selection, failure analysis, and iterative improvement.

Autonomous experiment loop — iteratively mutate code, measure a metric, keep only improvements (hill-climbing ratchet)

Improve existing content and close the learning loop without cannibalizing new-content work.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Update or correct an existing skill file based on judge feedback or improved understanding.

When the user wants to audit or optimize an App Store or Google Play listing. Also use when the user mentions 'ASO audit,' 'app store optimization,' 'optimize my app listing,' 'improve app visibility,' 'app store ranking,' 'audit my listing,' 'why aren't people downloading my app,' 'improve my app conversion,' 'keyword optimization for app,' or 'compare my app to competitors.' Use when the user shares an App Store or Google Play URL and wants to improve it.

When the user wants to audit or optimize an App Store or Google Play listing. Also use when the user mentions 'ASO audit,' 'app store optimization,' 'optimize my app listing,' 'improve app visibility,' 'app store ranking,' 'audit my listing,' 'why aren't people downloading my app,' 'improve my...

Improve unclear UX copy, error messages, microcopy, labels, and instructions. Makes interfaces easier to understand and use.

Improve interface performance across loading speed, rendering, animations, images, and bundle size. Makes experiences faster and smoother.