agentleFS
Sign inStart free
opencueopencue/cuecards/.agents/skills/code-dev-workflow/SKILL.md

code-dev-workflow

Skill6 starsChanged 3 months agoMITView on GitHub

Near code_dev harness — Explore, Read, Author phases with outline-first context discipline.

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the session is in code_dev mode.

    line 14
  2. Distinctive:

    Never read entire large files without outline + line ranges.

    line 24
  3. Very specific:

    Do not mirror document milestones into todo_write unless executing multi-step work.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Code Dev Workflow

Use when the session is in code_dev mode.

Phases

  1. Explore — code_outline, grep, lsp_*, code_search (if enabled). Write scratchpad_write(key="phase", value="explore") and a file list to read.
  2. Read — file_read with start_line/end_line only. Summarize into scratchpad. Then phase=read.
  3. Author — file_write skeleton first, then section-by-section updates. phase=author.

Rules

  • Never read entire large files without outline + line ranges.
  • Do not mirror document milestones into todo_write unless executing multi-step work.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free