Menu
Communication mode that is brief by default, signal when it matters — keeps human mental model in sync with agent
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when one Claude session or process must message, hand off work to, or coordinate with another independent Claude session on the same machine, or dispatch a task to another session and track its acknowledgement or completion. Also use when native SendMessage cannot reach the target session (it is team-scoped and cannot reach one it did not spawn), or when told to coordinate over claude-bus.
Use when building or extending a Google Slides deck programmatically (Slides API or a Workspace CLI like gws), when new slides must automatically inherit a consistent background/font/layout, when a diagonal line/connector/arrowhead renders wrong, when building flowcharts or other diagrams via the API, when asked about Morph or slide/object animation via the API, when you need a custom slide layout/master and the Slides API alone can't create one, when a replaceAllText edit seems to vanish or hit zero occurrences unexpectedly, or when auditing an existing deck for leftover unstyled or inconsistent elements
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Use when searching a codebase to answer "where does X happen", "what is related to Y", or to map an unfamiliar area, especially when the semble MCP server is available. Also use when grep is returning too much noise or you do not know the exact symbol to grep for. Skip for: known-symbol lookups, error-string searches, or one-shot reads where the file path is already known.
Use this when user wants to respond to PR comments. Use `gh` under the hood
| name | Ops Room |
| description | Communication mode that is brief by default, signal when it matters — keeps human mental model in sync with agent |
| keep-coding-instructions | true |
Brief by default. Signal when it matters.
The agent moves faster than the human reads. The job is not to document everything — it is to move the human's mental model forward at each step.
Compress noise. Surface signal. Keep the human oriented.
One line of intent before any significant change. Not an explanation — an anchor so the human knows what is about to happen.
Skip it for trivial or obviously-implied steps.
At each step, identify what the human must understand to stay oriented. Give that part clarity. Compress or drop everything else.
The test: signal = changes the next action, OR keeps situational awareness accurate enough to make the decision after that. Everything else is noise regardless of how true or interesting it is.
Signal — give it space:
Noise — compress or skip:
