{"id":"ddf7a7ae-f8f8-47c2-9232-73f8d8831b31","shortId":"e32EFh","kind":"skill","title":"pick-next-shell","tagline":"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\".","description":"# Pick Next Shell\n\nPick the next shell from `.turbo/shells/` whose dependencies are satisfied, then carry it through the planning pipeline: expand → refine → self-improve → halt.\n\n## Task Tracking\n\nAt the start, use `TaskCreate` to create a task for each step:\n\n1. Scan shells and pick next\n2. Run `/expand-shell` skill\n3. Run `/refine-plan` skill\n4. Run `/self-improve` skill\n5. Mark plan ready\n6. Halt with next-step instructions\n\n## Step 1: Scan Shells and Pick Next\n\nCheck terminal conditions first:\n\n- **No shells and no plans** — tell the user to run `/turboplan` for a new task and stop\n- **No shells, but plans exist with `status: done` for all** — report the project is complete and stop\n- **No shells, but plans exist with a non-`done` status** — suggest running `/implement-plan` to finish the remaining plans and stop\n\nIf 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.\n\n- **Candidates** — shells whose `depends_on` are all satisfied\n- **Blocked** — shells with one or more unsatisfied `depends_on`\n\nIf there are no candidates (everything is blocked), report which shells are blocked and which dependencies they're waiting on, then stop.\n\nIf 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.\n\nState the picked shell path and its dependencies before continuing.\n\n## Step 2: Run `/expand-shell` Skill\n\nRun the `/expand-shell` skill, passing the shell file path. Capture the resulting plan path for Step 3.\n\n## Step 3: Run `/refine-plan` Skill\n\nRun the `/refine-plan` skill with the plan path from Step 2. Loops until the plan stabilizes.\n\n## Step 4: Run `/self-improve` Skill\n\nRun the `/self-improve` skill to compound planning learnings.\n\n## Step 5: Mark Plan Ready\n\nUpdate the plan's YAML frontmatter to `status: ready`.\n\n## Step 6: Halt with Next-Step Instructions\n\nHalt with this message:\n\n> Plan ready at `<plan path>`.\n>\n> 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.\n\n## Rules\n\n- Do not edit plan files directly. Revisions go through `/refine-plan`.\n- Never modify the spec file.\n- Do not attempt to auto-implement. The user drives implementation with `/implement-plan` in a fresh session.\n- If a shell file is missing or has invalid frontmatter, halt and report.","tags":["pick","next","shell","turbo","tobihagemann","agent-skills","claude-code","claude-skills","developer-tools","skills"],"capabilities":["skill","source-tobihagemann","skill-pick-next-shell","topic-agent-skills","topic-claude-code","topic-claude-skills","topic-developer-tools","topic-skills"],"categories":["turbo"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/tobihagemann/turbo/pick-next-shell","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add tobihagemann/turbo","source_repo":"https://github.com/tobihagemann/turbo","install_from":"skills.sh"}},"qualityScore":"0.590","qualityRationale":"deterministic score 0.59 from registry signals: · indexed on github topic:agent-skills · 280 github stars · SKILL.md body (2,653 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-04-22T00:54:10.933Z","embedding":null,"createdAt":"2026-04-18T22:03:56.370Z","updatedAt":"2026-04-22T00:54:10.933Z","lastSeenAt":"2026-04-22T00:54:10.933Z","tsv":"'/clear':393 '/draft-shells':270 '/expand-shell':96,296,300 '/implement-plan':174,395,435 '/pick-next-shell':401 '/refine-plan':100,318,322,417 '/self-improve':104,339,343 '/turboplan':138 '1':88,118 '2':94,294,330 '3':98,314,316 '4':102,337 '5':106,350 '6':110,364 'ambigu':275 'ask':28 'askuserquest':277 'attempt':425 'auto':428 'auto-impl':427 'block':223,239,244 'candid':215,236,256 'captur':307 'carri':14,62 'check':124 'choos':282 'complet':159 'compound':346 'comprehens':387 'condit':126 'context':379 'continu':35,44,292,390 'creat':82 'depend':10,58,200,218,230,247,290 'direct':413 'done':152,170,211 'drive':432 'edit':410 'enough':388 'entri':202 'everyth':237 'exist':149,166,184,208,257 'expand':18,68 'file':193,273,305,412,422,443 'finish':176 'first':127 'fresh':391,438 'frontmatt':196,214,359,449 'full':382 'give':271 'glob':187 'go':415 'halt':23,73,111,365,371,450 'implement':41,397,429,433 'improv':22,72 'instruct':116,370 'invalid':448 'learn':348 'let':279 'like':381 'loop':331 'lowest':263 'mark':107,351 'md':189,207 'messag':374 'miss':445 'modifi':419 'multipl':255 'never':418 'new':141 'next':3,7,31,33,39,40,49,53,93,114,123,368,405 'next-step':113,367 'nn':268 'non':169 'number':265 'one':226,260 'pass':302 'path':287,306,311,327 'pick':2,5,30,48,51,92,122,258,285 'pick-next-shel':1 'pipelin':67 'plan':17,47,66,108,132,148,165,179,310,326,334,347,352,356,375,378,385,411 'prefix':269 'project':36,157 're':249 'read':191 'readi':109,353,362,376 'refin':19,69 'remain':178 'report':155,240,452 'result':309 'revis':414 'rule':407 'run':95,99,103,137,173,295,298,317,320,338,341,392,400 'satisfi':12,60,204,222 'scan':89,119 'self':21,71 'self-improv':20,70 'session':439 'shell':4,8,32,34,50,54,90,120,129,146,163,183,198,216,224,242,264,286,304,406,442 'skill':97,101,105,297,301,319,323,340,344 'skill-pick-next-shell' 'source-tobihagemann' 'spec':421 'stabil':335 'start':78 'state':283 'status':151,171,210,361 'step':42,87,115,117,293,313,315,329,336,349,363,369 'stop':144,161,181,253 'suggest':172 'task':74,84,142 'taskcreat':80 'tell':133 'termin':125 'topic-agent-skills' 'topic-claude-code' 'topic-claude-skills' 'topic-developer-tools' 'topic-skills' 'track':75 'turbo/plans':206 'turbo/shells':56,186,188 'unsatisfi':229 'updat':354 'use':24,79,276 'user':27,135,281,431 'wait':250 'whose':9,57,217 'yaml':195,358","prices":[{"id":"d70d30d9-6af0-42bb-9653-fa5c0d8e7942","listingId":"ddf7a7ae-f8f8-47c2-9232-73f8d8831b31","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"tobihagemann","category":"turbo","install_from":"skills.sh"},"createdAt":"2026-04-18T22:03:56.370Z"}],"sources":[{"listingId":"ddf7a7ae-f8f8-47c2-9232-73f8d8831b31","source":"github","sourceId":"tobihagemann/turbo/pick-next-shell","sourceUrl":"https://github.com/tobihagemann/turbo/tree/main/skills/pick-next-shell","isPrimary":false,"firstSeenAt":"2026-04-18T22:03:56.370Z","lastSeenAt":"2026-04-22T00:54:10.933Z"}],"details":{"listingId":"ddf7a7ae-f8f8-47c2-9232-73f8d8831b31","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"tobihagemann","slug":"pick-next-shell","github":{"repo":"tobihagemann/turbo","stars":280,"topics":["agent-skills","claude-code","claude-skills","developer-tools","skills"],"license":"mit","html_url":"https://github.com/tobihagemann/turbo","pushed_at":"2026-04-21T12:22:12Z","description":"A composable dev process for Claude Code, packaged as modular skills.","skill_md_sha":"b9d14941e08bdf41a8a2d159e201195ec3946005","skill_md_path":"skills/pick-next-shell/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/tobihagemann/turbo/tree/main/skills/pick-next-shell"},"layout":"multi","source":"github","category":"turbo","frontmatter":{"name":"pick-next-shell","description":"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\"."},"skills_sh_url":"https://skills.sh/tobihagemann/turbo/pick-next-shell"},"updatedAt":"2026-04-22T00:54:10.933Z"}}