From 432f5c19bd5a5a2e8bfa5cf1e65278c60dc6181a Mon Sep 17 00:00:00 2001 From: alexsoyes Date: Thu, 11 Jun 2026 13:08:03 +0200 Subject: [PATCH 1/2] feat(aidd-dev): add 10-todo skill for parallel todo fan-out Split a single user prompt into independent todos and run one implementer agent per todo in parallel, each refining its todo via a runtime-discovered refine skill before coding. Keeps the report to a single minimal table so the skill stays micro. Co-Authored-By: Claude Opus 4.8 (1M context) Signed-off-by: alexsoyes --- README.md | 4 +-- plugins/aidd-dev/.claude-plugin/plugin.json | 3 +- plugins/aidd-dev/CATALOG.md | 9 +++++ plugins/aidd-dev/skills/10-todo/README.md | 19 +++++++++++ plugins/aidd-dev/skills/10-todo/SKILL.md | 14 ++++++++ .../skills/10-todo/actions/01-todo.md | 33 +++++++++++++++++++ 6 files changed, 79 insertions(+), 3 deletions(-) create mode 100644 plugins/aidd-dev/skills/10-todo/README.md create mode 100644 plugins/aidd-dev/skills/10-todo/SKILL.md create mode 100644 plugins/aidd-dev/skills/10-todo/actions/01-todo.md diff --git a/README.md b/README.md index 71353db9..7123fad6 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ ### A community-maintained marketplace of skills, agents, and rules for Claude Code.

- 6 plugins · 31 skills · 3 agents · MIT + 6 plugins · 32 skills · 3 agents · MIT

@@ -146,7 +146,7 @@ Project init, architecture, generation of Claude Code context artifacts (skills, ### ⚙️ [aidd-dev](plugins/aidd-dev/README.md) -`10 skills` · stable +`11 skills` · stable SDLC loop: sdlc, plan, implement, assert, audit, review, test, refactor, debug, for-sure. diff --git a/plugins/aidd-dev/.claude-plugin/plugin.json b/plugins/aidd-dev/.claude-plugin/plugin.json index 8c4521cf..c384dae0 100644 --- a/plugins/aidd-dev/.claude-plugin/plugin.json +++ b/plugins/aidd-dev/.claude-plugin/plugin.json @@ -17,7 +17,8 @@ "./skills/06-test", "./skills/07-refactor", "./skills/08-debug", - "./skills/09-for-sure" + "./skills/09-for-sure", + "./skills/10-todo" ], "agents": [ "./agents/implementer.md", diff --git a/plugins/aidd-dev/CATALOG.md b/plugins/aidd-dev/CATALOG.md index bb39669d..90235310 100644 --- a/plugins/aidd-dev/CATALOG.md +++ b/plugins/aidd-dev/CATALOG.md @@ -19,6 +19,7 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai - [`skills/07-refactor`](#skills07-refactor) - [`skills/08-debug`](#skills08-debug) - [`skills/09-for-sure`](#skills09-for-sure) + - [`skills/10-todo`](#skills10-todo) --- @@ -162,3 +163,11 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | `-` | [README.md](skills/09-for-sure/README.md) | - | | `-` | [SKILL.md](skills/09-for-sure/SKILL.md) | `Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria.` | +#### `skills/10-todo` + +| Group | File | Description | +|-------|------|---| +| `actions` | [01-todo.md](skills/10-todo/actions/01-todo.md) | - | +| `-` | [README.md](skills/10-todo/README.md) | - | +| `-` | [SKILL.md](skills/10-todo/SKILL.md) | `Split the user prompt into independent todos, run one implementer agent per todo in parallel (each refines its todo first), and report a minimal table. Use when the user says "todo", "/todo", or asks to fan out a multi-part request into parallel implementations.` | + diff --git a/plugins/aidd-dev/skills/10-todo/README.md b/plugins/aidd-dev/skills/10-todo/README.md new file mode 100644 index 00000000..727b75be --- /dev/null +++ b/plugins/aidd-dev/skills/10-todo/README.md @@ -0,0 +1,19 @@ +← [aidd-framework](../../../../README.md) / [aidd-dev](../../README.md) + +# 10 - todo + +Split one prompt into independent todos, run one implementer agent per +todo in parallel (each refines its todo before coding), and report a +minimal table: category, what was launched, output. + +## When to use + +- The user says "todo" or `/todo`. +- A single prompt bundles several independent tasks that can be + implemented in parallel. + +## Actions + +| # | Action | Purpose | +| --- | --------------------------------- | --------------------------------------------- | +| 01 | [todo](actions/01-todo.md) | Categorize, launch parallel agents, report. | diff --git a/plugins/aidd-dev/skills/10-todo/SKILL.md b/plugins/aidd-dev/skills/10-todo/SKILL.md new file mode 100644 index 00000000..85a589b7 --- /dev/null +++ b/plugins/aidd-dev/skills/10-todo/SKILL.md @@ -0,0 +1,14 @@ +--- +name: 10-todo +description: Split the user prompt into independent todos, run one implementer agent per todo in parallel (each refines its todo first), and report a minimal table. Use when the user says "todo", "/todo", or asks to fan out a multi-part request into parallel implementations. +--- + +# Todo + +Turn one prompt into N independent todos, implement them in parallel, report a table. + +## Actions + +```markdown +@actions/01-todo.md +``` diff --git a/plugins/aidd-dev/skills/10-todo/actions/01-todo.md b/plugins/aidd-dev/skills/10-todo/actions/01-todo.md new file mode 100644 index 00000000..64fe4e9a --- /dev/null +++ b/plugins/aidd-dev/skills/10-todo/actions/01-todo.md @@ -0,0 +1,33 @@ +# 01 - Todo + +Categorize the user prompt into independent todos, implement each in parallel, report. + +## Inputs + +User's requirement. + +## Outputs + +```markdown +| Category | Launched | Output | +| -------- | -------- | ------ | +``` + +## Process + +1. **Read.** Take `prompt` from `$ARGUMENTS`; if empty, use the latest user message. +2. **Categorize.** Split the prompt into distinct, independent todos (category + task). Inline, no agent, using template. +3. **Launch.** Spawn one `implementer` agent per todo, all in parallel (one message, multiple Task calls). Each agent prompt mandates, in order: + ```markdown + 1. Refine the todo first - discover at runtime a skill whose description covers refining or clarifying a request (never a hardcoded plugin name) and run it on the todo. + 2. Implement the refined todo. + 3. Return a one-line output summary. + ``` +4. **Report.** Print exactly one table, nothing else: + +## Test + +- Every todo is one row in the table. +- Agents were spawned in a single parallel batch. +- Each agent ran a refine step before implementing. +- No output besides the table. From d24b459551d487af5cfff7076ea79c540b5ea84d Mon Sep 17 00:00:00 2001 From: Alex <8973343+alexsoyes@users.noreply.github.com> Date: Mon, 15 Jun 2026 08:40:53 +0200 Subject: [PATCH 2/2] Update plugins/aidd-dev/skills/10-todo/actions/01-todo.md Co-authored-by: Baptiste LAFOURCADE <119650761+blafourcade@users.noreply.github.com> --- plugins/aidd-dev/skills/10-todo/actions/01-todo.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/plugins/aidd-dev/skills/10-todo/actions/01-todo.md b/plugins/aidd-dev/skills/10-todo/actions/01-todo.md index 64fe4e9a..d918c682 100644 --- a/plugins/aidd-dev/skills/10-todo/actions/01-todo.md +++ b/plugins/aidd-dev/skills/10-todo/actions/01-todo.md @@ -15,7 +15,7 @@ User's requirement. ## Process -1. **Read.** Take `prompt` from `$ARGUMENTS`; if empty, use the latest user message. +1. **Read.** Take `prompt` from `$ARGUMENTS`; if empty, ask the user. 2. **Categorize.** Split the prompt into distinct, independent todos (category + task). Inline, no agent, using template. 3. **Launch.** Spawn one `implementer` agent per todo, all in parallel (one message, multiple Task calls). Each agent prompt mandates, in order: ```markdown