prompt optimization skills

mateaix/mateclaw

Skill Claude CodeCodex

DSPy: declarative LM programs, auto-optimize prompts, RAG.

OmidZamani/dspy-skills

Skill Claude CodeCodex

Use for composing DSPy modules with Ensemble, MultiChainComparison, ensemble voting, sequential pipelines, and multi-program workflows.

OmidZamani/dspy-skills

Skill Claude CodeCodex

Use for debugging DSPy programs, inspecthistory, tracing LLM calls, custom callbacks, observability, monitoring, and cost tracking.

OmidZamani/dspy-skills

Skill Claude CodeCodex

Use for GEPA optimizeanything on text artifacts such as code, prompts, agent architectures, configs, and non-DSPy optimization targets.

AtlasOmnia/hermes-tool-router

Skill Claude CodeCodex

First-run onboarding for the hermes-tool-router plugin — explain what the router does, offer the optional classifier API key exactly once, and verify the router is live. Use when a fresh Hermes profile has hermes-tool-router installed and was never onboarded, or when the user asks about router setup, the classifier…

SlanchaAI/ingot

Skill Claude CodeCodex

Research this page in a browser.

SlanchaAI/ingot

Skill Claude CodeCodex

Review a pull request through GitHub.

SlanchaAI/ingot

Skill Claude CodeCodex

Resolve the identical priority task.

0p9b/TLDR

Skill Claude CodeCodex

Quick-reference card for all tldr modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /tldr-help, "tldr help", "what TLDR commands", "how do I use TLDR".

0p9b/TLDR

Skill Claude CodeCodex

Verdict-first communication mode. Cuts token usage 60-75% by enforcing TLDR rules (1-sentence default, 3-word target, shape dispatch) while preserving full technical accuracy and truth priority. Supports levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "tldr mode", "talk…

0p9b/TLDR

Skill Claude CodeCodex

Decision guide for delegating to tldr-style subagents. Tells the main thread WHEN to spawn tldrcrew-investigator (locate code), tldrcrew-builder (1-2 file edit), or tldrcrew-reviewer (diff review) instead of doing the work inline or using vanilla Explore. Subagent output is tldr-compressed so the tool-result injected…

bobmatnyc/claude-mpm-agents

Skill Claude CodeCodex

Token-optimized prompt compression techniques for reducing LLM instruction size while preserving or improving quality.

JularDepick/user-thoughts.SKILL

Skill Claude CodeCodex

Persist user decisions and project constraints to mdbase across sessions. Trigger on /user-thoughts or /ustht, or when user discusses architecture, tech stack, rules, UI/UX, or mentions '想法', '记录', 'mdbase'.

TIKAZI/TIKAZ-Codex-Context-Economy

Skill Claude CodeCodex

Automatically prepare fidelity-first, bounded context when users paste text, attach files or folders, provide webpages or PDFs for Markdown conversion, continue long conversations, or supply documents containing images and complex tables. Route each input through Text, Hybrid, or Source; reduce exact or…

TIKAZI/TIKAZ-Codex-Context-Economy

Skill Claude CodeCodex

Measure context preparation across fixed cases. Use when token savings, hard-budget compliance, protected-fact recall, evidence anchors, determinism, runtime, or downstream answer quality must be demonstrated with reproducible evidence rather than marketing claims.

TIKAZI/TIKAZ-Codex-Context-Economy

Skill Claude CodeCodex

Prepare files, folders, code, logs, and structured data as a bounded, traceable context pack for Codex. Use when source material must be converted, deduplicated, selected, budgeted, or handed off with exact evidence anchors.

zhengbowenai-cmd/caliper

Skill Claude CodeCodex

Statistically test whether a prompt or SKILL.md change is actually better than the old version. Use when the user asks to compare two prompts, A/B test a prompt change, check if a recent edit really improved things, find rule conflicts in a long prompt, or identify which sections of a prompt are pulling weight.…

Waylish/skillopt-skill-writer

Skill Claude CodeCodex

Create, improve, and validate agent skills using a SkillOpt-inspired workflow: scored evidence, bounded add/delete/replace edits, validation gates, rejected-edit memory, and compact deployable SKILL.md artifacts. Trigger when the user says "write a skill", "create a Codex skill", "make a Claude skill", "turn this…