prompt-tuning
Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run…
Skill by hiroro-work
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hiroro-work-prompt-tuning
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/prompt-tuning
Tools it pre-approves 2
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Agent
What's inside
- Skill name
prompt-tuning- Description
- Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements plateau. Use after creating or revising a prompt or skill.
- License
- unknown
- Allowed tools
- Read,, Agent
- Instructions
- 334 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from hiroro-work/claude-plugins
- 0.658score
furikaeri
hiroro-work
Retrospective of one Claude Code session, built from its jsonl log and published as a single artifact page — where the time went (AI working vs.
SkillAFreshness: A★ 47Claude Code +9 - 0.658score
tidy
hiroro-work
Review changed code for reuse, quality, and efficiency, then apply cleanup edits.
SkillAFreshness: A★ 47Claude Code +9 - 0.658score
artifactor
hiroro-work
A background drawing hand for a one-page, picture-first HTML artifact that grows over a session — one agent dispatched once and resumed with a message each…
SkillAFreshness: A★ 47Claude Code - 0.658score
dev-workflow
hiroro-work
Guided development workflow — task decomposition, planning, peer plan review, approval, implementation, tidy, prose polish, check/test, rules compliance…
SkillAFreshness: A★ 47Claude Code - 0.658score
skill-review
hiroro-work
Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements.
SkillAFreshness: A★ 47Claude Code - 0.658score
verify-diff
hiroro-work
Empirically verify that a code diff achieves its stated objective by dispatching a bias-free executor that actually runs auto-derived evaluation scenarios…
SkillAFreshness: A★ 47Claude Code - 0.655score
apply-rules
hiroro-work
Apply organization-wide rules (from merge-rules output) to the current project.
SkillAFreshness: A★ 47Claude Code +9 - 0.653score
ask-peer
hiroro-work
Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming.
SkillAFreshness: A★ 47Claude Code +9 - 0.653score
review-with-untracked
hiroro-work
Temporarily visualize untracked new files into the git diff so a chain of diff-deriving review callees can see them, then restore the files to untracked.
SkillAFreshness: A★ 47Claude Code - 0.653score
publicity-review
hiroro-work
Review uncommitted diff for content unsuitable for publication to a public repository — secrets/credentials, user-specific absolute paths, internal-only…
SkillAFreshness: A★ 47Claude Code - 0.653score
rules-review
hiroro-work
Check code changes for .claude/rules/ compliance.
SkillAFreshness: A★ 47Claude Code +9 - 0.650score
ask-gemini
hiroro-work
Asks Gemini CLI for coding assistance.
SkillAFreshness: A★ 47Claude Code +9
Signals
- Stars
- 47
- Forks
- 3
- Open issues
- 1
- Last commit (this folder)
- Oct 1, 2026 (28 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/hiroro-work/claude-plugins
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from hiroro-work
- 0.658score
furikaeri
hiroro-work
Retrospective of one Claude Code session, built from its jsonl log and published as a single artifact page — where the time went (AI working vs.
SkillAFreshness: A★ 47Claude Code +9 - 0.658score
verify-diff
hiroro-work
Empirically verify that a code diff achieves its stated objective by dispatching a bias-free executor that actually runs auto-derived evaluation scenarios…
SkillAFreshness: A★ 47Claude Code - 0.658score
artifactor
hiroro-work
A background drawing hand for a one-page, picture-first HTML artifact that grows over a session — one agent dispatched once and resumed with a message each…
SkillAFreshness: A★ 47Claude Code - 0.658score
dev-workflow
hiroro-work
Guided development workflow — task decomposition, planning, peer plan review, approval, implementation, tidy, prose polish, check/test, rules compliance…
SkillAFreshness: A★ 47Claude Code - 0.658score
skill-review
hiroro-work
Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements.
SkillAFreshness: A★ 47Claude Code - 0.658score
tidy
hiroro-work
Review changed code for reuse, quality, and efficiency, then apply cleanup edits.
SkillAFreshness: A★ 47Claude Code +9
Cite this page
prompt-tuning skill. Agent Mart. https://agentmart.dev/skills/hiroro-work-prompt-tuning (last updated 2026-10-24)