pick-next-shell

Name: pick-next-shell
Author: tobihagemann

4installs29forks

How to install pick-next-shell?

tobihagemann/turbo/pick-next-shell

$npx -y skills add tobihagemann/turbo --skill pick-next-shell

Installs into the current project.

Summary

Pick the next shell whose dependencies are satisfied and carry it through planning: expand, refine, self-improve, halt. Use when the user asks to \"pick next shell\", \"next shell\", \"continue project\", \"what's next\", \"next implementation step\", or \"continue with the plan\

Files · 1

View on GitHub

SKILL.md

1	# Pick Next Shell
2
3	Pick the next shell from `.turbo/shells/` whose dependencies are satisfied, then carry it through the planning pipeline: expand → refine → self-improve → halt.
4
5	## Task Tracking
6
7	At the start, use `TaskCreate` to create a task for each step:
8
9	1. Scan shells and pick next
10	2. Run `/expand-shell` skill
11	3. Run `/refine-plan` skill
12	4. Run `/self-improve` skill
13	5. Mark plan ready
14	6. Summarize and halt
15
16	## Step 1: Scan Shells and Pick Next
17
18	Check terminal conditions first:
19
20	- No shells and no plans — nothing to pick; stop
21	- No shells, but plans exist with `status: done` for all — the project is complete; stop
22	- No shells, but plans exist with a non-`done` status — there are unfinished plans; stop
23
24	If shells exist in `.turbo/shells/`, glob `.turbo/shells/*.md` and read each file's YAML frontmatter. A shell's `depends_on` entry is satisfied when `.turbo/plans/<dep-slug>.md` exists with `status: done` in its frontmatter.
25
26	- Candidates — shells whose `depends_on` are all satisfied
27	- Blocked — shells with one or more unsatisfied `depends_on`
28
29	If there are no candidates (everything is blocked), report which shells are blocked and which dependencies they're waiting on, then stop.
30
31	If multiple candidates exist, pick the one with the lowest shell number (from the `NN-` prefix `/draft-shells` gives each file). If ambiguous, use `AskUserQuestion` to let the user choose.
32
33	State the picked shell path and its dependencies before continuing.
34
35	## Step 2: Run `/expand-shell` Skill
36
37	Run the `/expand-shell` skill, passing the shell file path. Capture the resulting plan path for Step 3.
38
39	## Step 3: Run `/refine-plan` Skill
40
41	Run the `/refine-plan` skill with the plan path from Step 2.
42
43	## Step 4: Run `/self-improve` Skill
44
45	Run the `/self-improve` skill to compound planning learnings.
46
47	## Step 5: Mark Plan Ready
48
49	Update the plan's YAML frontmatter to `status: ready`.
50
51	## Step 6: Summarize and Halt
52
53	Present a brief summary of the finished plan: the essence of what it builds and the key decisions behind it, short enough to read at a glance so the user does not have to open the full plan file. When the plan delivers value to a user, developer, or operator, also present a short list of stories capturing what that person gains, in the form "As a <persona>, I want <capability> so that <outcome>". Skip the stories only when no beneficiary or outcome can be named, such as a purely mechanical refactor. Fit both to the plan rather than a fixed template.
54
55	Then halt with this message:
56
57	> Plan ready at `<plan path>`.
58	>
59	> Planning context is likely full, and the plan is comprehensive enough to continue fresh. Run `/clear`, then `/implement-plan <slug>` to implement. After that, run `/pick-next-shell` again for the next shell.
60
61	## Rules
62
63	- Do not edit plan files directly. Revisions go through `/refine-plan`.
64	- Never modify the spec file.
65	- Do not attempt to auto-implement. The user drives implementation with `/implement-plan` in a fresh session.
66	- If a shell file is missing or has invalid frontmatter, halt and report.

People who liked this also viewed

6 picks

Type

pick-next-shell

4installs29forks

View on GitHub

How to install pick-next-shell?

tobihagemann/turbo/pick-next-shell

$npx -y skills add tobihagemann/turbo --skill pick-next-shell

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Pick Next Shell
2
3	Pick the next shell from `.turbo/shells/` whose dependencies are satisfied, then carry it through the planning pipeline: expand → refine → self-improve → halt.
4
5	## Task Tracking
6
7	At the start, use `TaskCreate` to create a task for each step:
8
9	1. Scan shells and pick next
10	2. Run `/expand-shell` skill
11	3. Run `/refine-plan` skill
12	4. Run `/self-improve` skill
13	5. Mark plan ready
14	6. Summarize and halt
15
16	## Step 1: Scan Shells and Pick Next
17
18	Check terminal conditions first:
19
20	- No shells and no plans — nothing to pick; stop
21	- No shells, but plans exist with `status: done` for all — the project is complete; stop
22	- No shells, but plans exist with a non-`done` status — there are unfinished plans; stop
23
24	If shells exist in `.turbo/shells/`, glob `.turbo/shells/*.md` and read each file's YAML frontmatter. A shell's `depends_on` entry is satisfied when `.turbo/plans/<dep-slug>.md` exists with `status: done` in its frontmatter.
25
26	- Candidates — shells whose `depends_on` are all satisfied
27	- Blocked — shells with one or more unsatisfied `depends_on`
28
29	If there are no candidates (everything is blocked), report which shells are blocked and which dependencies they're waiting on, then stop.
30
31	If multiple candidates exist, pick the one with the lowest shell number (from the `NN-` prefix `/draft-shells` gives each file). If ambiguous, use `AskUserQuestion` to let the user choose.
32
33	State the picked shell path and its dependencies before continuing.
34
35	## Step 2: Run `/expand-shell` Skill
36
37	Run the `/expand-shell` skill, passing the shell file path. Capture the resulting plan path for Step 3.
38
39	## Step 3: Run `/refine-plan` Skill
40
41	Run the `/refine-plan` skill with the plan path from Step 2.
42
43	## Step 4: Run `/self-improve` Skill
44
45	Run the `/self-improve` skill to compound planning learnings.
46
47	## Step 5: Mark Plan Ready
48
49	Update the plan's YAML frontmatter to `status: ready`.
50
51	## Step 6: Summarize and Halt
52
53	Present a brief summary of the finished plan: the essence of what it builds and the key decisions behind it, short enough to read at a glance so the user does not have to open the full plan file. When the plan delivers value to a user, developer, or operator, also present a short list of stories capturing what that person gains, in the form "As a <persona>, I want <capability> so that <outcome>". Skip the stories only when no beneficiary or outcome can be named, such as a purely mechanical refactor. Fit both to the plan rather than a fixed template.
54
55	Then halt with this message:
56
57	> Plan ready at `<plan path>`.
58	>
59	> Planning context is likely full, and the plan is comprehensive enough to continue fresh. Run `/clear`, then `/implement-plan <slug>` to implement. After that, run `/pick-next-shell` again for the next shell.
60
61	## Rules
62
63	- Do not edit plan files directly. Revisions go through `/refine-plan`.
64	- Never modify the spec file.
65	- Do not attempt to auto-implement. The user drives implementation with `/implement-plan` in a fresh session.
66	- If a shell file is missing or has invalid frontmatter, halt and report.

People who liked this also viewed

6 picks

Type