Skip to content
Back to skills

Lulu Tasks

ASecurity

Split a delivered plan or approach decision into an independently executable task-dependency list.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 2, 2026
ai-agentspythongo

Security analysis

A100/100

Pro scans all 20 files and shows the line behind each finding

Scanned October 5, 2026

npx -y skills add lulufoo/lulu-workflow --skill lulu-tasks --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Lulu Tasks?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Lulu Tasks
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lulufoo-lulu-tasks/badge)](https://www.skillsdirectory.com/skills/lulufoo-lulu-tasks)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: lulu-tasks
description: >-
  Split a delivered plan or approach decision into an independently executable task-dependency list.
disable-model-invocation: true
---

# tasks-workflow

Split a delivered plan, or an approach decision when no plan is delivered, into an independently executable task-dependency list. `tech-doc` in this skill means that reference document.

A task has `kind: coding` or `kind: action`.

- `coding` changes code. Signatures, TDD order, and `tdd_exempt` apply only to this kind.
- `action` reaches a stated goal by any means. It declares `effects`, lists acceptance criteria that evidence can answer one by one, and binds a worktree only when it names one. It does not commit code.

Delivery starts `lulu-exec` for the whole work order. That session dispatches by `kind`.

<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-tasks`
- Feature identification from `## Session Foundation`
</HARD-GATE>

## Script Macros

| Macro | Command |
|-------|---------|
| `$TT_START` | `python3 "$SKILL_DIR/scripts/tt_start.py" --cycle-id "$CYCLE_ID"` |
| `$TT_FLOW` | `python3 "$SKILL_DIR/scripts/tt_workflow_control.py" --cycle-id "$CYCLE_ID"` |
| `$TT_CTX` | `$TT_FLOW resolve-context` |

Subcommand contracts: module docstring / `--help`.

## Start

1. Identify the active cycle through `_runtime.md` § Session Foundation. Do not run `$TT_START` until `$CYCLE_ID` is confirmed.
2. Run `$TT_START`. It reads the delivered plan, or the delivered approach decision when no plan is delivered, from the cycle's delivered refs. A non-zero result is Blocking.
3. Run `$TT_CTX` and pin the JSON as `$CTX`.

## Router

Load the unit named by `$CTX.unit`:

- `drafting` → `$SKILL_DIR/references/drafting.md`
- `evaluating` → `$SKILL_DIR/references/evaluating.md`
- `delivery` → `$SKILL_DIR/references/delivery.md`

When a unit returns, run `$TT_CTX` again and load the unit it names. `current_state` `Delivered`: stop.

Files in this skill

  • SKILL.md2 KB
  • config.json377 B
  • eval/dimension-defs/compliance-crosscheck.json597 B
  • eval/dimension-defs/execution-admission.json556 B
  • eval/eval-profile.json196 B
  • eval/methods/compliance-crosscheck.md1.2 KB
  • eval/methods/execution-admission.md2.1 KB
  • references/delivery.md477 B
  • references/drafting.md1.6 KB
  • references/evaluating.md916 B
  • scripts/eval/tasks_eval_adapter.py10.3 KB
  • scripts/eval/tasks_eval_admission.py4.9 KB
  • scripts/eval/tasks_eval_publish.py5.8 KB
  • scripts/tests/test_tasks_eval_control.py6.2 KB
  • scripts/tests/test_tt_workflow_control.py7.3 KB
  • scripts/tt_archive.py1.3 KB
  • scripts/tt_delivery_gate_schema.py640 B
  • scripts/tt_eval_control.py7.2 KB
  • scripts/tt_eval_runtime_schema.py4 KB
  • scripts/tt_eval_target_schema.py1.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.