lulufoolulufoo/lulu-workflow/lulu-bet/SKILL.md

lulu-bet

Skill3 starsChanged 8 days agoMITView on GitHub

Domain holder for product-level diagnostic decisions. Delegates the full DDF execution to the decision kernel under product domain constraints. - $SKILL_ROOT, $WORKFLOW_DIR, $PLATFORM, $CACHE_DIR from ## Platform Context - $SKILL_DIR = $SKILL_ROOT/lulu-bet (before Session Foundation) - $DECISION_SKILL_DIR = $SKILL_ROOT/decision - Feature identification logic from ## Session Foundation </HARD-GATE> Machine constraints SSOT: $SKILL_DIR/constraints-$CYCLE_TYPE.json (resolve $CYCLE_TYPE from _runtime.md § Session Foundation; passed to decision CLI via --constraints). Subcommand contract: module docstring / --help. Complete _runtime.md § Session Foundation before running decision start.

In this repository11 other files it gives its agents.
- composeSkill
- decisionSkill
- eval-librarySkill
- lulu-approachSkill
- lulu-brainstormSkill
- lulu-designSkill
- lulu-execSkill
- lulu-planSkill
- lulu-specSkill
- lulu-tasksSkill
- lulu-workflowSkill

The file

We split this skill into the rules it gives an agent

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

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Do NOT proceed until you have read ../_runtime.md and loaded:
line 12
Very specific:
Do NOT proceed until you have read ../decision/SKILL.md in full.
line 21
Distinctive:
All DDF rules, gates, and registers defined there apply to this session.
line 22
Very specific:
After DC completion: $GATE_CONTROL prepare, then $BET_DELIVER.
line 55

≈ “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

lulu-bet

Domain holder for product-level diagnostic decisions. Delegates the full DDF execution to the decision kernel under product domain constraints.

<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-bet (before Session Foundation)
$DECISION_SKILL_DIR = $SKILL_ROOT/decision
Feature identification logic from ## Session Foundation</HARD-GATE>

<HARD-GATE>
Do NOT proceed until you have read `../decision/SKILL.md` in full.
All DDF rules, gates, and registers defined there apply to this session.
</HARD-GATE>

Machine constraints SSOT: $SKILL_DIR/constraints-$CYCLE_TYPE.json (resolve $CYCLE_TYPE from _runtime.md § Session Foundation; passed to decision CLI via --constraints).

Script Macros

Macro	Command
`$RESOLVE_CONTEXT`	`python3 "$SKILL_DIR/scripts/resolve_context.py" --cycle-id "<cycle_id>" --constraints "$SKILL_DIR/constraints-$CYCLE_TYPE.json"`
`$BET_DELIVER`	`python3 "$SKILL_DIR/scripts/decision_package_control.py" --holder-root "$CACHE_DIR/<cycle_id>/lulu-bet" --cycle-id "<cycle_id>"`

Subcommand contract: module docstring / --help.

start

Complete _runtime.md § Session Foundation before running decision start.

Step 1: Run $RESOLVE_CONTEXT. Holder builds flat context.docs map (key→path); missing docs omit keys. Writes to a file and prints that path — capture as $RESOLVED_CONTEXT_PATH. Non-zero exit → stop and report stderr.

Step 2: Run $DEC_START from decision/SKILL.md § Start with:

--constraints "$SKILL_DIR/constraints-$CYCLE_TYPE.json" \
--domain-constraints-file "$RESOLVED_CONTEXT_PATH"

Pass the same --constraints "$SKILL_DIR/constraints-$CYCLE_TYPE.json" on every $GATE_CONTROL / $REGISTER_* invocation. --domain-constraints-file is only needed on $DEC_START.

If $DEC_START exits non-zero ("Gate blocked: <stage> is not Delivered"): tell the user which prior stage must be delivered first. Do not retry start.

Deliver

After DC completion: $GATE_CONTROL prepare, then $BET_DELIVER. On success, announce stage complete from stdout next_steps (join when non-empty).

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