{"id":"23b53332-a290-4620-b033-5d9fe4d84b03","shortId":"wNdTT4","kind":"skill","title":"executing-plans","tagline":"Use when you have a written implementation plan to execute in a separate session with review checkpoints. Triggers on: \"execute the plan\", \"implement the tasks\", \"start building\", any plan execution request. Loads plan, reviews critically, executes tasks in batches with checkpoin","description":"# Executing Plans\n\n## Overview\n\nLoad plan, review critically, execute tasks in batches, report for review between batches.\n\n**Core principle:** Batch execution with checkpoints for architect review.\n\n**Announce at start:** \"I'm using the executing-plans skill to implement this plan.\"\n\n## The Process\n\n### Step 1: Load and Review Plan\n1. Read plan file\n2. Review critically - identify any questions or concerns about the plan\n3. If concerns: Raise them with your human partner before starting\n4. If no concerns: Create TodoWrite and proceed\n\n### Step 2: Execute Batch\n**Default: First 3 tasks**\n\nFor each task:\n1. Mark as in_progress\n2. Follow each step exactly (plan has bite-sized steps)\n3. Run verifications as specified\n4. Mark as completed\n\n### Step 3: Report\nWhen batch complete:\n- Show what was implemented\n- Show verification output\n- Say: \"Ready for feedback.\"\n\n### Step 4: Continue\nBased on feedback:\n- Apply changes if needed\n- Execute next batch\n- Repeat until complete\n\n### Step 5: Complete Development\n\nAfter all tasks complete and verified:\n- Announce: \"I'm using the finishing-a-development-branch skill to complete this work.\"\n- **REQUIRED SUB-SKILL:** Use superpowers:finishing-a-development-branch\n- Follow that skill to verify tests, present options, execute choice\n\n## When to Stop and Ask for Help\n\n**STOP executing immediately when:**\n- Hit a blocker mid-batch (missing dependency, test fails, instruction unclear)\n- Plan has critical gaps preventing starting\n- You don't understand an instruction\n- Verification fails repeatedly\n\n**Ask for clarification rather than guessing.**\n\n## When to Revisit Earlier Steps\n\n**Return to Review (Step 1) when:**\n- Partner updates the plan based on your feedback\n- Fundamental approach needs rethinking\n\n**Don't force through blockers** - stop and ask.\n\n## Remember\n- Review plan critically first\n- Follow plan steps exactly\n- Don't skip verifications\n- Reference skills when plan says to\n- Between batches: just report and wait\n- Stop when blocked, don't guess\n- Never start implementation on main/master branch without explicit user consent\n\n## Integration\n\n**Required workflow skills:**\n- **superpowers:using-git-worktrees** - REQUIRED: Set up isolated workspace before starting\n- **superpowers:writing-plans** - Creates the plan this skill executes\n- **superpowers:finishing-a-development-branch** - Complete development after all tasks\n\n## Examples\n\n### Example 1: Batch Execution\nPlan: 6 tasks for dark mode feature\nBatch 1: Tasks 1-3 (toggle component, context, CSS)\nCheckpoint: Review, feedback\nBatch 2: Tasks 4-6 (test, documentation, cleanup)\nCheckpoint: Final review, merge\n\n### Example 2: Blocker Handling\nTask 3: \"Add theme context\" fails because dependency missing\nAction: STOP, ask for clarification\nDon't: Guess and continue\nResult: Get help, resume from Task 3\n\n### Example 3: Plan Revision\nBatch 1 complete, feedback: \"Need to support system preference\"\nAction: Return to Step 1 (Review), update plan\nContinue: Execute revised plan from Task 4\n\n## Troubleshooting\n\n### Issue: Hit a blocker mid-batch\nSolution: STOP immediately. Ask for clarification. Don't guess or skip the task.\n\n### Issue: Plan has gaps or unclear instructions\nSolution: Raise concerns in Step 1 (Review). Don't proceed until clarified.\n\n### Issue: Verification fails repeatedly\nSolution: STOP. Ask for help. Don't attempt workarounds or skip verification.","tags":["executing","plans","synapse","deve1993","agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation","claude-code"],"capabilities":["skill","source-deve1993","skill-executing-plans","topic-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workspace","topic-anti-poisoning","topic-auto-learning-ai","topic-automation","topic-claude-code","topic-code-quality","topic-cursor","topic-developer-tools","topic-devops"],"categories":["Synapse"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/deve1993/Synapse/executing-plans","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add deve1993/Synapse","source_repo":"https://github.com/deve1993/Synapse","install_from":"skills.sh"}},"qualityScore":"0.453","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 7 github stars · SKILL.md body (3,404 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":"2026-05-18T19:14:13.482Z","embedding":null,"createdAt":"2026-05-18T13:21:46.301Z","updatedAt":"2026-05-18T19:14:13.482Z","lastSeenAt":"2026-05-18T19:14:13.482Z","tsv":"'-3':411 '-6':423 '1':88,93,138,295,397,408,410,466,478,522 '2':97,128,143,420,432 '3':108,133,154,164,436,460,462 '4':119,159,181,422,488 '5':197 '6':401 'action':444,474 'add':437 'announc':70,206 'appli':186 'approach':306 'architect':68 'ask':246,280,316,446,500,535 'attempt':540 'base':183,301 'batch':42,55,60,63,130,167,192,258,337,398,407,419,465,496 'bite':151 'bite-s':150 'block':344 'blocker':255,313,433,493 'branch':215,231,353,389 'build':30 'chang':187 'checkpoin':44 'checkpoint':20,66,416,427 'choic':241 'clarif':282,448,502 'clarifi':528 'cleanup':426 'complet':162,168,195,198,203,218,390,467 'compon':413 'concern':104,110,122,519 'consent':357 'context':414,439 'continu':182,453,482 'core':61 'creat':123,378 'critic':38,51,99,267,320 'css':415 'dark':404 'default':131 'depend':260,442 'develop':199,214,230,388,391 'document':425 'earlier':289 'exact':147,325 'exampl':395,396,431,461 'execut':2,13,23,33,39,45,52,64,78,129,190,240,250,383,399,483 'executing-plan':1,77 'explicit':355 'fail':262,278,440,531 'featur':406 'feedback':179,185,304,418,468 'file':96 'final':428 'finish':212,228,386 'finishing-a-development-branch':211,227,385 'first':132,321 'follow':144,232,322 'forc':311 'fundament':305 'gap':268,513 'get':455 'git':365 'guess':285,347,451,505 'handl':434 'help':248,456,537 'hit':253,491 'human':115 'identifi':100 'immedi':251,499 'implement':10,26,82,172,350 'instruct':263,276,516 'integr':358 'isol':370 'issu':490,510,529 'load':35,48,89 'm':74,208 'main/master':352 'mark':139,160 'merg':430 'mid':257,495 'mid-batch':256,494 'miss':259,443 'mode':405 'need':189,307,469 'never':348 'next':191 'option':239 'output':175 'overview':47 'partner':116,297 'plan':3,11,25,32,36,46,49,79,84,92,95,107,148,265,300,319,323,333,377,380,400,463,481,485,511 'prefer':473 'present':238 'prevent':269 'principl':62 'proceed':126,526 'process':86 'progress':142 'question':102 'rais':111,518 'rather':283 'read':94 'readi':177 'refer':330 'rememb':317 'repeat':193,279,532 'report':56,165,339 'request':34 'requir':221,359,367 'result':454 'resum':457 'rethink':308 'return':291,475 'review':19,37,50,58,69,91,98,293,318,417,429,479,523 'revis':464,484 'revisit':288 'run':155 'say':176,334 'separ':16 'session':17 'set':368 'show':169,173 'size':152 'skill':80,216,224,234,331,361,382 'skill-executing-plans' 'skip':328,507,543 'solut':497,517,533 'source-deve1993' 'specifi':158 'start':29,72,118,270,349,373 'step':87,127,146,153,163,180,196,290,294,324,477,521 'stop':244,249,314,342,445,498,534 'sub':223 'sub-skil':222 'superpow':226,362,374,384 'support':471 'system':472 'task':28,40,53,134,137,202,394,402,409,421,435,459,487,509 'test':237,261,424 'theme':438 'todowrit':124 'toggl':412 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workspace' 'topic-anti-poisoning' 'topic-auto-learning-ai' 'topic-automation' 'topic-claude-code' 'topic-code-quality' 'topic-cursor' 'topic-developer-tools' 'topic-devops' 'trigger':21 'troubleshoot':489 'unclear':264,515 'understand':274 'updat':298,480 'use':4,75,209,225,364 'user':356 'using-git-worktre':363 'verif':156,174,277,329,530,544 'verifi':205,236 'wait':341 'without':354 'work':220 'workaround':541 'workflow':360 'workspac':371 'worktre':366 'write':376 'writing-plan':375 'written':9","prices":[{"id":"b93da358-decc-4b8f-94bf-593d9a9ceb72","listingId":"23b53332-a290-4620-b033-5d9fe4d84b03","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"deve1993","category":"Synapse","install_from":"skills.sh"},"createdAt":"2026-05-18T13:21:46.301Z"}],"sources":[{"listingId":"23b53332-a290-4620-b033-5d9fe4d84b03","source":"github","sourceId":"deve1993/Synapse/executing-plans","sourceUrl":"https://github.com/deve1993/Synapse/tree/main/skills/executing-plans","isPrimary":false,"firstSeenAt":"2026-05-18T13:21:46.301Z","lastSeenAt":"2026-05-18T19:14:13.482Z"}],"details":{"listingId":"23b53332-a290-4620-b033-5d9fe4d84b03","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"deve1993","slug":"executing-plans","github":{"repo":"deve1993/Synapse","stars":7,"topics":["agent-skills","ai-agents","ai-coding","ai-workspace","anti-poisoning","auto-learning-ai","automation","claude-code","code-quality","cursor","developer-tools","devops","fullstack-development","multi-agent-systems","nextjs","opencode","persistent-memory","self-improving","telegram-bot"],"license":"other","html_url":"https://github.com/deve1993/Synapse","pushed_at":"2026-05-15T21:34:01Z","description":"Self-improving AI brain for Claude Code & Desktop — 28 MCP tools, 253 skills, collective memory, project tracking, work logs. One server, all your sessions share the same knowledge. Deploy on Coolify in 2 minutes.","skill_md_sha":"1b65a739506fdec49fc497a9c32877a63957cd33","skill_md_path":"skills/executing-plans/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/deve1993/Synapse/tree/main/skills/executing-plans"},"layout":"multi","source":"github","category":"Synapse","frontmatter":{"name":"executing-plans","description":"Use when you have a written implementation plan to execute in a separate session with review checkpoints. Triggers on: \"execute the plan\", \"implement the tasks\", \"start building\", any plan execution request. Loads plan, reviews critically, executes tasks in batches with checkpoints."},"skills_sh_url":"https://skills.sh/deve1993/Synapse/executing-plans"},"updatedAt":"2026-05-18T19:14:13.482Z"}}