skill-optimizer
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 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
- Installs
- 121
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/rohitg00/pro-workflow --skill skill-optimizer- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads skill-optimizer automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Skill Optimizer
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.
When to use
Use this skill when:
- A pro-workflow skill has accumulated 8+ learn-rule rows for it
- The user reports the skill is "getting bloated" or "rules keep being repeated"
- The user wants offline, budget-capped improvement over multiple sessions
Do not use when:
- Skill has fewer than 8 trajectories (nothing to learn from)
- The user wants real-time edits (this is offline, single-shot)
- No key has been explicitly configured for the selected provider
Architecture (mirrors SkillOpt's six-stage loop)
rollout pull recent learnings from SQLite (existing learn-rule rows)
reflect optimizer LLM analyzes a minibatch, proposes add/delete/replace patches
aggregate vote-merge patches across minibatches
select clip by LR budget (default: 3 adds, 2 deletes, 3 replaces per step)
update apply selected patches to a candidate skill content
evaluate evaluator LLM scores candidate against held-out validation items
gate accept candidate only if weighted score >= current + acceptThreshold
slow update at epoch boundary, consolidate accepted edits into a coherent rewrite
Failed candidates are stored in a rejection buffer and fed back to the next reflect step so the optimizer doesn't propose the same patch twice.
Run it
In a plugin session, use the providers MCP server's run_provider_task tool with task: "optimizer" and args: ["--slug", "<slug>", "--budget-usd", "0.50"]. Keys come from the plugin configuration dialog. Standalone CLI installations use explicit PRO_WORKFLOW_*_API_KEY variables. See provider configuration; never request keys in chat or retrieve existing machine credentials.
/skill-optimize <slug> [options]
Options (all optional; sensible defaults shown):
| Flag | Default | Notes |
|---|---|---|
--epochs N | 3 | Outer loop count |
--batch-size N | 8 | Trajectories per minibatch |
--minibatches N | 2 | Minibatches per epoch |
--holdout N | 6 | Validation items reserved (max ~25% of trajectories) |
--budget-usd X | 0.50 | Hard cap; loop aborts when spent |
--optimizer-model M | claude-sonnet-5 | Reflect + slow-update model |
--evaluator-model M | claude-haiku-4-5 | Gate model (cheaper) |
--max-adds N | 3 | LR budget per step |
--max-deletes N | 2 | |
--max-replaces N | 3 | |
--accept-threshold X | 0.0 | Minimum score delta to accept candidate |
--max-skill-tokens N | 2000 | Hard cap on candidate length |
--slow-every N | 2 | Epochs between consolidation passes |
--json | off | Machine-readable output |
Kill switch: touch ~/.pro-workflow/STOP aborts the loop between steps.
Output
- Candidate accepted → SKILL.md overwritten, hash stamp appended in HTML comment
- Run details persist in
optimization_runs,optimization_candidates,optimization_patches,optimization_rejections - Validation set persists in
optimization_validation(reusable across runs)
Inspect after:
sqlite3 ~/.pro-workflow/data.db "SELECT id, skill_slug, initial_score, best_score, accepted_steps, rejected_steps, spent_usd FROM optimization_runs ORDER BY id DESC LIMIT 5"
Rules
- Validation set is frozen at run start. Never re-derive from new corrections mid-run.
- One candidate per step. No parallel branches.
- Slow-update output is itself a candidate; it must pass the gate to replace the best.
- The optimizer LLM and evaluator LLM may be different models. Mixing a strong optimizer with a cheap evaluator is the SkillOpt-recommended config.
- If
spent_usd >= budget_usdat any step boundary, the loop ends withstopped_reason="budget exhausted". - Patches whose anchor is no longer present in the skill (because a prior patch in the same step removed it) are recorded as rejected with reason
anchor_missing.
Provenance
Inspired by Microsoft SkillOpt (arXiv:2605.23904). The six-stage rollout/reflect/aggregate/select/update/evaluate pipeline, LR budget, rejection buffer, and slow / meta update mechanics are adapted to pro-workflow's existing SQLite + learn-rule data plane. No SkillOpt code is reused. "ReflACT" is not a SkillOpt term and is not used here; the loop is referred to by stage names only.
FAQ
What does the skill-optimizer skill do?
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 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.
How do I install skill-optimizer?
Run npx skills add https://github.com/rohitg00/pro-workflow --skill skill-optimizer in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/skill-optimizer/ (personal) or .claude/skills/skill-optimizer/ (project).
Which AI agents can use skill-optimizer?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is skill-optimizer safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains skill-optimizer?
It is published by rohitg00 in rohitg00/pro-workflow. It has 121 recorded installs.
More from rohitg00/pro-workflow
token-efficiency
rohitg00/pro-workflow
Reduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and read-before-write enforcement. Inspired by drona23/claude-token-efficient.
pro-workflow
rohitg00/pro-workflow
Complete AI coding workflow system. Orchestration patterns, 18 hook events, 8 agents, cross-agent support, reference guides, and searchable learnings. Works with Claude Code, Cursor, and 32+ agents.
wrap-up
rohitg00/pro-workflow
End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.
deslop
rohitg00/pro-workflow
Remove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate, simplifies abstractions, strips defensive code, and in skill-file mode lints SKILL.md files for quality. Use when cleaning up code, simplifying, removing boilerplate, before committing, or when reviewing a skill before promoting it.
learn-rule
rohitg00/pro-workflow
Open the skill to read its SKILL.md instructions.
session-handoff
rohitg00/pro-workflow
Generate a structured handoff document capturing current progress, open tasks, key decisions, and context needed to resume work. Use when ending a session, saying "continue later", "save progress", "session summary", or "pick up where I left off".
Popular productivity & automation skills
agent-browser
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
lark-doc
open.feishu.cn
飞书云文档（Docx / Wiki）内容操作：读取、创建、编辑文档，插入或下载图片附件，以及操作思维笔记。用户提供文档 URL/token（包括 doubao.com 的 /docx/、/wiki/）时使用；按 URL 路径/token 而非域名路由；/page/ 是妙搭应用，非飞书云文档。文档内嵌资源按读取参考中的统一规则分流。独立评论操作走 lark-drive；随正文读取评论使用 docs +fetch。表格或 Base 内部数据操作不在本 skill。
lark-base
open.feishu.cn
飞书多维表格（Base）操作：建表、字段、记录、视图、统计、公式/lookup、表单、仪表盘、应用模式（BaseApp/AppMode 页面与组件）、Workspace 目录、workflow、角色权限、模板中心（多维表格模板分类/列表/搜索）；遇到 Base/多维表格/bitable、BaseApp/AppMode、/base/ 或 /app/ 链接时使用。BaseApp 不走 lark-apps；文件导入/导出转 lark-drive，认证/授权转 lark-shared。
lark-drive
open.feishu.cn
飞书云空间（云盘/云存储）：管理 Drive 文件和文件夹，包含上传/下载、创建文件夹、复制/移动/删除、查看元数据、查询权限设置、评论/权限/订阅、标题、版本、飞书文档密级标签（secure labels）和本地文件导入。用户需要整理云盘目录、处理云空间资源 URL/token、判断链接类型/真实 token/标题，或导入 Word/Markdown/Excel/CSV/PPTX/.base 为 docx/sheet/bitable/slides 时使用；doubao.com 云空间 URL/token 也按资源路径和 token 路由，不回退 WebFetch。不负责：文档内容编辑（走 lark-doc）、表格/Base 表内数据操作（走 lark-sheets/lark-base）、知识空间节点/成员管理（走 lark-wiki）、原生 Markdown 文件读写/patch/diff（走 lark-markdown）。
lark-shared
open.feishu.cn
Use for lark-cli setup/auth tasks: auth login/status/logout, user vs bot identity, business-domain permissions (--domain, including all/docs/drive), missing scopes, revoking authorization, or handling notice JSON.
lark-im
open.feishu.cn
飞书即时通讯：收发消息和管理群聊。发送和回复消息、搜索聊天记录、管理群聊成员、上传下载图片和文件、管理表情回复、发送应用内/短信/电话加急、发送和处理交互卡片（Interactive Card）、监听卡片按钮回调（card.action.trigger）。当用户需要发消息、查看或搜索聊天记录、下载聊天中的文件、查看群成员、搜索群、创建群聊或话题群、管理标记数据、管理 Feed 置顶（添加/移除/查询置顶会话）、管理标签数据、处理卡片回调时使用。