SkillsAdd

mcollina/skills

skill-optimizer

Optimizes AI skills for activation, clarity, and cross-model reliability.

All-time #8876 Trending #6185 Hot #4670 First seen Mar 13, 2026
8-week activity · all time api

Installation

$ npx skills add mcollina/skills --skill skill-optimizer
View on skills.sh ↗ GitHub repository ↗

Summary

  • Optimizes AI skills for activation, clarity, and cross-model reliability.
  • Use when creating or editing skill packs, diagnosing weak skill uptake, reducing regressions, tuning instruction salience, improving examples, shrinking context cost, or setting benchmark/release gates for skills.
  • Trigger terms: skill optimization, activation gap, benchmark skill, with/without skill delta, regression, context budget, prompt salience.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

skill-optimizer Linked neighbor
tdimino/claude-code-minoan

Guide creating and reviewing skills that extend Claude with specialized knowledge, workflows, o…

52 installs
next-cache-components-optimizer Similar name
vercel/next.js

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Componen…

11.8K installs
neon-postgres-egress-optimizer Similar name
neondatabase/agent-skills

>- Diagnose and fix excessive Postgres egress (network data transfer) in a codebase. Use when a…

5.5K installs
mongodb-query-optimizer Similar name
mongodb/agent-skills

>- Help with MongoDB query optimization and indexing. Use only when the user asks for optimizat…

4.9K installs
prompt-optimizer Similar name
getsentry/skills

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, a…

1.6K installs
markdown-token-optimizer Similar name
microsoft/azure-skills

markdown-token-optimizer — an installable skill for AI agents.

1.1K installs

Also in this package

Other skills from mcollina/skills · top by installs.

npx skills add mcollina/skills
fastify-best-practices 46.2K node 5.1K typescript-magician 2.3K nodejs-core 1.6K documentation 1.5K oauth 1.2K octocat 1.1K init 1.1K linting-neostandard-eslint9 987 snipgrapher 805

Browse all from mcollina/skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 1.9K
License LICENSE
Default branch main
Open issues 5
Status Active

Skill metadata

Parsed from SKILL.md frontmatter.

More metadata
tags
skills, optimization, benchmarking, activation, regressions, prompt-engineering

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,327 B
  • docs SUMMARY.md 446 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1,200 installs

SKILL.md

When to use

Use this skill when you need to:

  • Improve whether a skill is actually applied by models
  • Diagnose why some criteria fail across all models
  • Prevent a skill from making outputs worse
  • Refactor skill text for stronger retrieval under context pressure
  • Build repeatable benchmark loops and release gates

Optimization loop (default workflow)

  1. Measure baseline and skill-on behavior (per model, per scenario, per criterion)
  2. Find failure pattern:

- universal failure (0% with skill) - model-specific weakness - regression (negative delta)

  1. Edit for salience:

- add explicit triggers - add concrete integrated examples - tighten checklists and decision rules

  1. Re-run evals and compare deltas
  2. Ship with guardrails (documented gate + run history + follow-up issues)

How to use

Read individual rule files for detailed procedures and templates:

  • [rules/benchmark-loop.md](rules/benchmark-loop.md) - End-to-end benchmark loop and scoring
  • [rules/activation-design.md](rules/activation-design.md) - Improve retrieval and instruction uptake
  • [rules/context-budget.md](rules/context-budget.md) - Reduce token cost without losing behavior
  • [rules/regression-triage.md](rules/regression-triage.md) - Diagnose and fix skill-on regressions
  • [rules/release-gates.md](rules/release-gates.md) - Go/no-go criteria before shipping skill updates

Practical heuristics

  • Prefer few high-signal rules over many soft recommendations
  • Put fragile, high-value behaviors in top-level checklists
  • Include at least one integrated example per common scenario
  • Add explicit wording for what must not be omitted
  • Track gains/losses with with-skill vs without-skill comparisons