Agent skill

Skill Optimizer

by rohitg00 in rohitg00/pro-workflow

SkillOpt-flavored offline training loop for any SKILL.md. An agent skill from rohitg00/pro-workflow.

No licenceAuto-check passedAgent Workflows

Install Skill Optimizer

skills CLI
$ npx skills add rohitg00/pro-workflow --skill skill-optimizer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install rohitg00/pro-workflow skill-optimizer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/rohitg00/pro-workflow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-optimizer .claude/skills/skill-optimizer && rm -rf skills-src

Use ~/.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/

Facts

Skill name
skill-optimizer
GitHub stars
2.9k
Token cost
~1.3k tokens
SKILL.md length
466 words
Files
1
Skills in repo
41
Repo updated
First seen
Licence
None found

At a glance

SkillOpt-flavored offline training loop for any SKILL.md. An agent skill from rohitg00/pro-workflow.

  • A skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better
  • SKILL.md covers When to use, Architecture (mirrors…, Run it and Output, plus 2 more sections
  • Calls sqlite3
  • Not just longer

What it does

Skill Optimizer is an agent skill from rohitg00/pro-workflow. SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated…

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Skill management and Deep learning. It works with SQLite. The repository describes itself as: Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context engineering, parallel worktrees, agent teams, and 17 battle-tested…

When your agent uses it

  • A skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better
  • Not just longer

Example prompts

  • “/skill-optimizer”

What it can do on your machine

Read from SKILL.md and the folder at commit 86d5f27. 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

    Shell commands in SKILL.md call:

    • sqlite3

    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

Skill Optimizer loads about 1.3k tokens when it runs. Until then it costs about 155 tokens; SKILL.md has 466 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~155
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 466 words (~1,289 tokens).

“Train an existing SKILL.md the way a deep-learning optimizer trains weights: via rollouts, gradient-like reflections, validation-gated acceptance. No model retraining; only the skill markdown changes.”

— opening of SKILL.md by rohitg00
name
skill-optimizer
user-invocable
true

Read the full SKILL.md on GitHub

Files

Just SKILL.md in skills/skill-optimizer of rohitg00/pro-workflow.

Open the folder on GitHubat commit 86d5f27

Compare with similar skills

Skill Optimizer 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 Optimizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Skill Optimizer this skillrohitg00/pro-workflow2.9k—~1.3kAutomated safety check: PassNone
Skills ManagementCodeAlive-AI/ai-driven-development155—~6.2kAutomated safety check: PassMIT
Frontmcp Setupagentfront/frontmcp146—~5.8kAutomated safety check: PassApache-2.0
External Mindstudio Ascend Profiler DB Explorerascend-ai-coding/awesome-ascend-skills174—~1.4kAutomated safety check: PassNone
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT

Similar skills

  • Skills Management

    CodeAlive-AI/ai-driven-development

    Search, find, discover, install, remove, update, review, deduplicate, list, move, optimise, and iterate on skills for AI coding agents.

    155 GitHub stars~6.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Frontmcp Setup

    agentfront/frontmcp

    A skill your agent uses when starting, scaffolding, or organizing a FrontMCP project.

    146 GitHub stars~5.8k tokensUpdated today
    DatabasesAuto-check passed
  • External Mindstudio Ascend Profiler DB Explorer

    ascend-ai-coding/awesome-ascend-skills

    面向 Ascend PyTorch Profiler / msprof DB(如 ascendpytorchprofiler.db、msprof.db)的 SQL 分析技能。将自然语言问题(算子耗时、通信、下发、调度、schema/table 查询)转为安全可执行 SQL,并按需从官方文档提取表结构详情。

    174 GitHub stars~1.4k tokensUpdated today
    DevelopmentAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    102k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

More from rohitg00/pro-workflow

All 41 skills in this repo
  • Survey Generator

    rohitg00/pro-workflow

    Compile a structured literature survey on any AI/ML topic. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed
  • Wiki Builder

    rohitg00/pro-workflow

    Start, structure, and grow a persistent research wiki indexed in pro-workflow's SQLite knowledge base.

    2.9k GitHub stars~1k tokensUpdated 8 days ago
    Auto-check passed
  • Wiki Query

    rohitg00/pro-workflow

    Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub starsUsed in 1 repo~554 tokens
    Auto-check passed
  • LLM Council

    rohitg00/pro-workflow

    Provider-agnostic multi-LLM deliberation. An agent skill from rohitg00/pro-workflow.

    2.9k GitHub stars~1.1k tokensUpdated 8 days ago
    Auto-check passed
  • Wiki Research Loop

    rohitg00/pro-workflow

    Auto-grow a pro-workflow wiki by running a budget-capped BFS research loop over pluggable source fetchers (web, arXiv, GitHub).

    2.9k GitHub stars~1.5k tokensUpdated 8 days ago
    Auto-check passed
  • Insights

    rohitg00/pro-workflow

    Show session analytics, learning patterns, correction trends, heatmaps, and productivity metrics.

    2.9k GitHub starsUsed in 1 repo~719 tokens
    Auto-check passed

Works with

Categories

Questions about Skill Optimizer

What does Skill Optimizer do?

SkillOpt-flavored offline training loop for any SKILL.md. An agent skill from rohitg00/pro-workflow. Skill Optimizer is an agent skill from rohitg00/pro-workflow.md.

When should I use Skill Optimizer?

Skill Optimizer fits situations like: A skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better; not just longer.

How do I install Skill Optimizer in Claude Code?

Run `npx skills add rohitg00/pro-workflow --skill skill-optimizer -a claude-code`. Or copy the skill folder (skills/skill-optimizer in rohitg00/pro-workflow) into .claude/skills/skill-optimizer in your project. Claude Code loads it when a task matches its description.

How do I install Skill Optimizer in Codex?

Run `npx skills add rohitg00/pro-workflow --skill skill-optimizer -a codex`. Or copy the skill folder (skills/skill-optimizer in rohitg00/pro-workflow) into .agents/skills/skill-optimizer in your project. Codex loads it when a task matches its description.

Can I use Skill Optimizer 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 rohitg00/pro-workflow --skill skill-optimizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-optimizer, .gemini/skills/skill-optimizer, .github/skills/skill-optimizer and .opencode/skills/skill-optimizer in your project.

What does Skill Optimizer need to run?

Going by SKILL.md and its folder, Skill Optimizer needs the command-line tools its instructions call (sqlite3).

Does Skill Optimizer 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 Skill Optimizer 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 Skill Optimizer use?

No licence was found for Skill Optimizer or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Skill Optimizer use?

About 1.3k tokens (SKILL.md is roughly 5.2k 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 Skill Optimizer?

Skills that share tags, products or a category with Skill Optimizer: Skills Management (CodeAlive-AI/ai-driven-development, 155 stars), Frontmcp Setup (agentfront/frontmcp, 146 stars), External Mindstudio Ascend Profiler DB Explorer (ascend-ai-coding/awesome-ascend-skills, 174 stars) and MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Skill Optimizer?

rohitg00 (a GitHub user) maintains it in rohitg00/pro-workflow, which has 2,906 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on September 29, 2026.

Source: rohitg00/pro-workflow on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.