Index of every page on this site: llms.txt
All skills
scode avatar

/scode-galaxy-brain

@03a9f7f
Run it yourself

Accomplish a goal by delegating suitable parts of the work to cost-effective models while the current session stays in charge of planning, quality gating, and all commit/PR management. Use when the user explicitly invokes scode-galaxy-brain, e.g. "Use scode-galaxy-brain for a goal", optionally with a prefer-gpt, prefer-claude, prefer-muse, or prefer-glm keyword and/or a request to work with concurrency. Also use when the user says "galaxy brain feedback: ..." to record feedback about how this skill performed. Once invoked, the skill stays active for the rest of the session — including across context compaction and resume — until the user expressly stops it, unless the invocation itself limited the scope up front.

  • 12 files
  • 82.3 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/scode/dotfiles/scode-galaxy-brain

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

feedback.md

≈597 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Feedback capture

Read this file when the user says "galaxy brain feedback: ..." or otherwise clearly gives feedback on how this skill performed.

When the user says "galaxy brain feedback: ..." (or clearly signals feedback about how this skill performed), pause whatever you are doing and record the feedback before resuming. The record exists so the skill's author can later hand it to an agent working in the skill's source repository and ask for improvements — write it with that reader in mind.

Append (never overwrite) a markdown entry to $XDG_STATE_HOME/scode-galaxy-brain/feedback.md, defaulting to ~/.local/state/scode-galaxy-brain/feedback.md when XDG_STATE_HOME is unset. Create the directory if needed. Compose the whole entry first and append it in one write (one >> redirect of a finished file or heredoc, not several) so that another session appending at the same moment cannot interleave with it — this file is the one piece of skill state that is shared by design, and SPEC.md requires that sharing never corrupt anything. After writing, tell the user explicitly which file you appended to.

Each entry should be self-contained — the future reader has no access to this session:

  • A ## <date> — <short title> heading.
  • Which layer the feedback concerns, so the report can be handed to the right skill's repository: scode-model-routing for a model, effort, or launch-mechanism choice, scode-agent-delegation for the task spec, checkpoints, or gate, scode-harness-shellout for the chosen mechanism's command, flags, monitoring, resume, or kill behavior, or scode-galaxy-brain itself for activation, decomposition, concurrency, or what was done with a verdict. Name more than one when the problem crossed a boundary.
  • The user's feedback, verbatim or near-verbatim.
  • What you were doing when the problem occurred: the task, which model and delegation path was involved, the actual commands or prompts where relevant, and what went wrong (exact errors beat paraphrases).
  • Your own analysis if you have one: root cause, and what change to the skill instructions would have prevented the problem. Mark speculation as such.

Avoid including private information (credentials, personal data), but do not sacrifice clarity of the problem description to scrub aggressively — the user reviews the file before forwarding it anywhere.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 03a9f7f. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month

README badge

README badge for scode/dotfiles/scode-galaxy-brain