Menu
Shared setup for shaping sessions. Determines if an artefact exists or needs creating, creates it if needed, starts the transcript, reads the type taxonomy. Called by the parent router or by any sub-skill invoked directly.
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
Identify changed code and dispatch reuse, quality, and efficiency reviewer agents in parallel; return the raw findings list.
Review changed code for reuse, quality, and efficiency, and produce a triaged list of findings (no edits). Use after writing code, for simpler code with fewer bugs and better performance.
Provides guidance on good software design principles, with trade-off calibration, examples, and common failure modes. Applies when making decisions while writing, designing, or refactoring code, or evaluating trivial code for clarity, maintainability, and common mistakes.
Reviews code with a team against established software design principles, and returns triaged findings (no edits). Use when evaluating code, or after writing or refactoring complex code, systems or technical designs: for code that is clearer, easier to maintain, and avoids common mistakes.
Shape an artefact through structured Q&A. Routes to the right sub-skill: brainstorm (new/unclear artefacts), refine (open decisions), or discover (exploration-driven artefacts like People and Ideas).
Review changed code for reuse, quality, and efficiency, then fix any issues found.
| name | shaping:assess |
| description | Shared setup for shaping sessions. Determines if an artefact exists or needs creating, creates it if needed, starts the transcript, reads the type taxonomy. Called by the parent router or by any sub-skill invoked directly. |
Handles session setup for all shaping sub-skills. Called by the parent shaping skill before routing, or by any sub-skill invoked directly that doesn't have context yet.
brain_read(resource="artefact", name="..."). If it doesn't resolve, ask the user what type to create, then create via brain_create.brain_create.brain_action("start-shaping", params={"target": "{path}", "skill_type": "{type}"}) where skill_type is the sub-skill that will run (Brainstorm, Refine, or Discover). This creates or appends to the day's transcript.brain_read(resource="type", name="{type-key}"). Find the ## Shaping section for flavour (convergent or discovery), bar, and completion status.**Transcripts:** line, this is a resumption. The artefact is the source of truth for current state — read it, not old transcripts. Only consult prior transcripts if you need to understand why something was decided.{path}. Transcript: {path}. Type: {type}. Shaping flavour: convergent/discovery. Bar: {bar}."These rules apply to all shaping sub-skills. Sub-skills reference this section instead of defining their own.
brain_create(type="research"), investigate, fold findings back into the parent artefact, and resume shaping. The spike is an offer, not a claim — the user might just need to think.### Agent heading with your exact text, ### User heading with the user's exact response. Record what was said, nothing more — synthesis belongs in the artefact.