agentleFS
Sign inStart free
lulufoolulufoo/lulu-workflow/lulu-exec/SKILL.md

lulu-exec

Skill3 starsChanged 6 days agoMITView on GitHub

Execute a delivered work order to a committed worktree delivery or an evidenced action receipt.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 0 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do NOT proceed until you have read ../_runtime.md and loaded:

    line 15
  2. Very specific:

    Run $TC_CTX and pin the JSON as $CTX.

    line 35
  3. Very specific:

    If $CTX.unit is starting, run $TC_START, then $TC_CTX again.

    line 36
  4. Very specific:

    If $CYCLE_TYPE is topic and $CTX.unit is executing or closing, announce $CTX.current_state / $CTX.current_task and ask to resume.

    line 37
  5. Very specific:

    When a unit returns, run $TC_CTX again and load the unit it names.

    line 49

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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-workflow

Execute a delivered work order by task kind. Done when $TC_CTX reports unit delivered.

A non-zero $MACRO is Blocking: stop, report, wait.

<HARD-GATE> Do NOT proceed until you have read `../_runtime.md` and loaded:
  • $SKILL_ROOT, $WORKFLOW_DIR, $PLATFORM, $CACHE_DIR from ## Platform Context
  • $SKILL_DIR = $SKILL_ROOT/lulu-exec
  • Feature identification from ## Session Foundation</HARD-GATE>

Script Macros

MacroCommand
$TC_STARTpython3 "$SKILL_DIR/scripts/tc_start.py" --cycle-id "$CYCLE_ID"
$TC_FLOWpython3 "$SKILL_DIR/scripts/tc_session_control.py" --cycle-dir "$CACHE_DIR/$CYCLE_ID"
$TC_CTX$TC_FLOW resolve-context

Subcommand contracts: module docstring / --help.

Start

  1. Identify the active cycle through _runtime.md § Session Foundation. Do not run $TC_START until $CYCLE_ID is confirmed.
  2. Run $TC_CTX and pin the JSON as $CTX.
  3. If $CTX.unit is starting, run $TC_START, then $TC_CTX again.
  4. If $CYCLE_TYPE is topic and $CTX.unit is executing or closing, announce $CTX.current_state / $CTX.current_task and ask to resume. No → $TC_START, then $TC_CTX. Feature containers auto-resume.

Router

Load the unit named by $CTX.unit:

  • preparing → $SKILL_DIR/references/preparing.md
  • executing → $SKILL_DIR/references/executing.md
  • closing → $SKILL_DIR/references/closing.md
  • delivered → stop
  • starting → ## Start

When a unit returns, run $TC_CTX again and load the unit it names.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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