{"id":"7aeb68fe-8078-46e2-8be0-b0661635f857","shortId":"q2PJVs","kind":"skill","title":"recipe-task","tagline":"Execute tasks following appropriate rules with rule-advisor metacognition","description":"# Task Execution with Metacognitive Analysis\n\nTask: $ARGUMENTS\n\n## Mandatory Execution Process\n\n**Step 1: Rule Selection via rule-advisor (REQUIRED)**\n\nInvoke rule-advisor using Agent tool:\n- `subagent_type`: \"dev-workflows:rule-advisor\"\n- `description`: \"Rule selection\"\n- `prompt`: \"Task: $ARGUMENTS. Select appropriate rules and perform metacognitive analysis.\"\n\n**Step 2: Utilize rule-advisor Output**\n\nAfter receiving rule-advisor's JSON response, proceed with:\n\n1. **Understand Task Essence** (from `taskAnalysis.essence`)\n   - Focus on fundamental purpose, not surface-level work\n   - Distinguish between \"quick fix\" vs \"proper solution\"\n\n2. **Follow Selected Rules** (from `selectedRules`)\n   - Review each selected rule section\n   - Apply concrete procedures and guidelines\n\n3. **Recognize Past Failures** (from `metaCognitiveGuidance.pastFailures`)\n   - Apply countermeasures for known failure patterns\n   - Use suggested alternative approaches\n\n4. **Execute First Action** (from `metaCognitiveGuidance.firstStep`)\n   - Start with recommended action\n   - Use suggested tools first\n\n**Step 3: Create Task List with TaskCreate**\n\nRegister work steps using TaskCreate. Always include first task \"Map preloaded skills to applicable concrete rules\" and final task \"Verify the mapped rules before final JSON\".\n\nBreak down the task based on rule-advisor's guidance:\n- Reflect `taskAnalysis.essence` in task descriptions\n- Apply `metaCognitiveGuidance.firstStep` to first task\n- Restructure tasks considering `warningPatterns`\n- Set priorities based on dependency order and warningPatterns severity\n\n**Step 4: Execute Implementation**\n\nProceed with task execution following:\n- Start with `metaCognitiveGuidance.firstStep` action from rule-advisor\n- Update task structure with TaskUpdate to reflect rule-advisor insights\n- Selected rules from rule-advisor\n- Task structure (managed via TaskCreate/TaskUpdate)\n- Quality standards defined in the selectedRules output from rule-advisor\n- Monitor warningPatterns flags throughout execution and adjust approach when triggered","tags":["recipe","task","claude","code","workflows","shinpr","agent-skills","agentic-ai","ai-agents","automation","claude-code","claude-code-plugin"],"capabilities":["skill","source-shinpr","skill-recipe-task","topic-agent-skills","topic-agentic-ai","topic-ai-agents","topic-automation","topic-claude-code","topic-claude-code-plugin","topic-code-quality","topic-developer-tools","topic-development-workflow","topic-llm-orchestration","topic-productivity","topic-prompt-engineering"],"categories":["claude-code-workflows"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/shinpr/claude-code-workflows/recipe-task","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add shinpr/claude-code-workflows","source_repo":"https://github.com/shinpr/claude-code-workflows","install_from":"skills.sh"}},"qualityScore":"0.613","qualityRationale":"deterministic score 0.61 from registry signals: · indexed on github topic:agent-skills · 327 github stars · SKILL.md body (2,071 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":"2026-05-02T18:53:53.118Z","embedding":null,"createdAt":"2026-04-18T22:03:16.824Z","updatedAt":"2026-05-02T18:53:53.118Z","lastSeenAt":"2026-05-02T18:53:53.118Z","tsv":"'1':25,78 '2':62,100 '3':116,147 '4':132,214 'action':135,141,225 'adjust':269 'advisor':12,31,36,47,66,72,187,229,239,246,262 'agent':38 'altern':130 'alway':158 'analysi':18,60 'appli':111,122,195 'applic':166 'approach':131,270 'appropri':7,55 'argument':20,53 'base':183,206 'break':179 'concret':112,167 'consid':202 'countermeasur':123 'creat':148 'defin':254 'depend':208 'descript':48,194 'dev':43 'dev-workflow':42 'distinguish':93 'essenc':81 'execut':4,15,22,133,215,220,267 'failur':119,126 'final':170,177 'first':134,145,160,198 'fix':96 'flag':265 'focus':84 'follow':6,101,221 'fundament':86 'guidanc':189 'guidelin':115 'implement':216 'includ':159 'insight':240 'invok':33 'json':74,178 'known':125 'level':91 'list':150 'manag':249 'mandatori':21 'map':162,174 'metacognit':13,17,59 'metacognitiveguidance.firststep':137,196,224 'metacognitiveguidance.pastfailures':121 'monitor':263 'order':209 'output':67,258 'past':118 'pattern':127 'perform':58 'preload':163 'prioriti':205 'procedur':113 'proceed':76,217 'process':23 'prompt':51 'proper':98 'purpos':87 'qualiti':252 'quick':95 'receiv':69 'recip':2 'recipe-task':1 'recogn':117 'recommend':140 'reflect':190,236 'regist':153 'requir':32 'respons':75 'restructur':200 'review':106 'rule':8,11,26,30,35,46,49,56,65,71,103,109,168,175,186,228,238,242,245,261 'rule-advisor':10,29,34,45,64,70,185,227,237,244,260 'section':110 'select':27,50,54,102,108,241 'selectedrul':105,257 'set':204 'sever':212 'skill':164 'skill-recipe-task' 'solut':99 'source-shinpr' 'standard':253 'start':138,222 'step':24,61,146,155,213 'structur':232,248 'subag':40 'suggest':129,143 'surfac':90 'surface-level':89 'task':3,5,14,19,52,80,149,161,171,182,193,199,201,219,231,247 'taskanalysis.essence':83,191 'taskcreat':152,157 'taskcreate/taskupdate':251 'taskupd':234 'throughout':266 'tool':39,144 'topic-agent-skills' 'topic-agentic-ai' 'topic-ai-agents' 'topic-automation' 'topic-claude-code' 'topic-claude-code-plugin' 'topic-code-quality' 'topic-developer-tools' 'topic-development-workflow' 'topic-llm-orchestration' 'topic-productivity' 'topic-prompt-engineering' 'trigger':272 'type':41 'understand':79 'updat':230 'use':37,128,142,156 'util':63 'verifi':172 'via':28,250 'vs':97 'warningpattern':203,211,264 'work':92,154 'workflow':44","prices":[{"id":"5ee84f4e-3eab-45d9-8d96-893bcad6214f","listingId":"7aeb68fe-8078-46e2-8be0-b0661635f857","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"shinpr","category":"claude-code-workflows","install_from":"skills.sh"},"createdAt":"2026-04-18T22:03:16.824Z"}],"sources":[{"listingId":"7aeb68fe-8078-46e2-8be0-b0661635f857","source":"github","sourceId":"shinpr/claude-code-workflows/recipe-task","sourceUrl":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-task","isPrimary":false,"firstSeenAt":"2026-04-18T22:03:16.824Z","lastSeenAt":"2026-05-02T18:53:53.118Z"}],"details":{"listingId":"7aeb68fe-8078-46e2-8be0-b0661635f857","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"shinpr","slug":"recipe-task","github":{"repo":"shinpr/claude-code-workflows","stars":327,"topics":["agent-skills","agentic-ai","ai-agents","automation","claude-code","claude-code-plugin","code-quality","developer-tools","development-workflow","llm-orchestration","productivity","prompt-engineering","skills"],"license":"mit","html_url":"https://github.com/shinpr/claude-code-workflows","pushed_at":"2026-05-02T15:39:17Z","description":"Production-ready development workflows for Claude Code, powered by specialized AI agents.","skill_md_sha":"2f9ed5095b25f99937c83cdf6b1823ee97c408b3","skill_md_path":"skills/recipe-task/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/shinpr/claude-code-workflows/tree/main/skills/recipe-task"},"layout":"multi","source":"github","category":"claude-code-workflows","frontmatter":{"name":"recipe-task","description":"Execute tasks following appropriate rules with rule-advisor metacognition"},"skills_sh_url":"https://skills.sh/shinpr/claude-code-workflows/recipe-task"},"updatedAt":"2026-05-02T18:53:53.118Z"}}