stbenjam avatar

steering

v0.1.0

by stbenjam

Compact conversation-steering skills for changing direction, explaining decisions, asking for clarity, answering questions without implied action, finishing punted work, delegating research to a subagent, tightening prose, executing decisively, rethinking code architecture, and raising frontend quality.

What steering does, in the publisher's words

Three-letter skills for agent wrangling.

See the main installation guide for Claude Code, Codex, and standalone Agent Skills setup.

  • ask: Pause implementation and ask only the questions needed to produce a high-quality solution.
  • cut: Make the response terser while preserving important reasoning, decisions, and next steps.
  • dig: Revisit superficial or under-verified agent work by investigating its claims, assumptions, evidence, and missing edge cases.
  • dyj: Stop punting and complete the user's requested task. Use after the model evades, defers, or stops before doing work it can perform.
  • lfg: Implement the requested direction immediately using reasonable defaults and no unnecessary follow-up questions.
  • lmk: Spawn a subagent to perform the research task, then report back with the answer.

Inspired by bro from dmmulroy/skills.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
12
MCP servers
0
Stars
5
License
n/a
Repo created
2025-10-31
Last pushed
2026-09-19
Publisher type
User
Version
0.1.0

Links

Skills · 12

ask
Pause implementation and ask only the questions needed to produce a high-quality solution.
cut
Make the response terser while preserving important reasoning, decisions, and next steps.
dig
Revisit superficial or under-verified agent work by investigating its claims, assumptions, evidence, and missing edge cases.
dyj
Stop punting and complete the user's requested task. Use after the model evades, defers, or stops before doing work it can perform.
lfg
Implement the requested direction immediately using reasonable defaults and no unnecessary follow-up questions.
lmk
Spawn a subagent to perform the research task, then report back with the answer.
map
Explain the shape of an implementation, its key architectural decisions, and how its main pieces fit together.
nah
Abandon the current direction, propose three genuinely different approaches, and recommend the strongest one.
qna
Answer genuine questions directly without treating them as implied instructions to take action.
rip
wow
Rework a frontend with award-winning visual hierarchy, interaction design, polish, originality, and Webby-worthy quality.
wtf
Explain the reasoning, evidence, assumptions, and tradeoffs behind the immediately preceding action or result.

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

Category

Agent Tooling. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Related by publisher and keywords

  • skillsawstbenjam

    A configurable linter for agent skills, plugins, and AI coding assistant context

  • booksstbenjam

    Search and analyze a Calibre library or Goodreads export, including reading lists, series, statistics, and recommendations.

  • frictionstbenjam

    Eliminate everyday friction through direct action, delegation, specialist services, or automation within explicit authorization boundaries.

  • keepgoingstbenjam

    A Stop hook for Claude Code and Codex that requests one final completion pass, with an opt-in infinite mode.

  • loopsstbenjam

    Autonomous loops that shepherd work to completion, such as driving a PR to a mergeable state

  • openclawstbenjam

    A grab-bag of miscellaneous OpenClaw skills stbenjam uses day to day, with no unifying theme.

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/steering)

Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.