Loading...
Loading...
Found 11 Skills
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.
Guide for creating and reviewing skills. This skill should be used when users want to create a new skill, review an existing skill for quality, or optimize a skill that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
Audit and automatically optimize a lovstudio skill against repo conventions and official Anthropic skill-creator best practices, then bump the semver version and append a CHANGELOG entry. Checks SKILL.md frontmatter/trigger quality, script CLI hygiene, directory naming, README badge, and progressive disclosure structure. Prioritizes issues raised in the current conversation (e.g. bugs the user just hit) over a generic sweep. Use when the user asks to "optimize", "refine", "audit", or "polish" an existing skill, or when they say "bump version", "update changelog", or "fix this skill". Also trigger when the user mentions "优化 skill", "skill 审计", "刷一遍 skill", "skill-optimizer", "bump skill version", "update skill changelog".
Use when creating, running, debugging, or documenting skill-optimizer workbench evals; working with agent skill cases, suites, graders, traces, Docker workspaces, OpenRouter model matrices, or the skill-optimizer SDK/CLI.
Optimizer that refines and professionalizes AI agent skills through real usage — saves tokens, eliminates redundancy, and tightens instructions so skills cost less to run. Learns from mistakes, reviews quality, and improves over time. Observes skill execution in the current conversation, analyzes up to four sources (conversation friction, file diffs, user feedback, static diagnostic) plus accumulated lessons, and proposes concrete improvements to the target skill's SKILL.md. Works with Claude Code and compatible SKILL.md-based agent frameworks. Use after executing any skill: `/skill-optimizer [name]` or `/skill-optimizer` to auto-detect. `--review` processes accumulated lessons.
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.
Analyze and optimize document quality issues of other Skills, including checks on frontmatter format, progressive disclosure structure, file reference integrity, AI-friendliness, etc. When to use: When users say "optimize this skill", "check skill quality", "review skill", "there's something wrong with the skill", "help me look at this skill", "diagnose the skill"
Optimize agent skills to reduce context bloat while preserving answer coverage. Use when: (1) A skill's SKILL.md body exceeds ~250 lines or duplicates its references/ files (2) A skill's YAML description is verbose or triggers false positives from sibling skills (3) Planning or executing a body/reference split for a skill (4) Auditing skill token efficiency
Use when mining coding-agent session history, archived transcripts, memories, or repeated local work to discover recurring workflows that should become new Agent Skills.
Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or public sharing, especially when private paths, personal habits, credentials, internal hosts, or user-specific context must be removed.
Use when auditing or adapting newly created, downloaded, forked, installed, or community Agent Skills to the user's tools, habits, directories, session history, and preferred workflows, especially when triggers feel wrong, noisy, or too generic.