{"id":"56fa7e1a-922d-4c7f-a0d1-6938118654a7","shortId":"FcPAc6","kind":"skill","title":"issue-driven-workflow","tagline":"Break down complex tasks into a structured plan and trackable Issue CSV, then execute autonomously. Use when a task has multiple steps, needs research before starting, requires status tracking, or benefits from a structured breakdown before execution.","description":"# Issue-Driven Workflow\n\n## Philosophy\n\nThe plan and Issue CSV are a **work amplifier**. Front-load the thinking so the agent has a full plate of actionable work to execute autonomously — more rows means more useful work per run.\n\n1. **Planning (interactive)** — search the web, read docs, ask questions, gather context. A thorough plan means more work the agent can do without stopping.\n2. **Execution (autonomous)** — be proactive, not passive. Work through the CSV end-to-end. Maximize useful work per run — don't wait for permission on routine decisions.\n\nThe quality bar: every CSV row should be completable, testable, and markable DONE without further clarification.\n\n## E2E loop\n\nplan → issues → implement → test → review\n\n## Planning (interactive)\n\n1. Restate the task and assumptions.\n2. **Gather context** — search the web, read project files, inspect dependencies. Make every plan section concrete, not aspirational.\n3. Ask up to 2 clarification questions if unclear, then proceed with stated assumptions.\n4. Draft the plan in chat using `assets/_template.md`. Choose complexity (`simple|medium|complex`).\n5. Ask: \"Reply CONFIRM to write the plan file.\"\n6. On confirmation:\n   ```bash\n   python3 .codex/skills/issue-driven-workflow/scripts/create_plan.py \\\n     --task \"<title>\" --complexity <simple|medium|complex>\n   ```\n7. Do not edit code while planning.\n\n## Creating the CSV (interactive)\n\n1. Generate after the plan is approved.\n2. Break the plan into granular, independently actionable rows.\n3. Fill **all** required columns — see `references/issue-csv-spec.md`.\n4. Order by dependency chain. Set `Dependencies` so execution order is unambiguous.\n5. Validate:\n   ```bash\n   python3 .codex/skills/issue-driven-workflow/scripts/validate_issues_csv.py <issues.csv>\n   ```\n\n## Executing the CSV (autonomous)\n\nThe CSV is your execution state. Read it to know where you are, update it as you work, keep driving forward.\n\n1. Read the CSV. Find the next `TODO` row in dependency order.\n2. Set `Dev_Status = DOING`. Start working.\n3. Complete the row — search, read, write, test, whatever it requires.\n4. When `Acceptance` is met and `Test_Method` passes, set `Dev_Status = DONE`.\n5. Self-review. Mark `Review1_Status = DONE`.\n6. **Immediately move to the next row.** Read the CSV again, pick the next `TODO`, keep going.\n7. After all rows are `DONE`, regression check. Mark `Regression_Status = DONE` per row.\n8. Report progress briefly as you complete rows.\n9. Only stop for genuinely blocking unknowns that affect correctness, safety, or irreversible actions.\n\nIf a row is too large, split it. If a row fails, fix it or flag it. If in a git repo, commit at natural boundaries. Edit the CSV directly — re-validate after edits.\n\n## Scripts\n\n| Script | Purpose |\n|---|---|\n| `create_plan.py` | Create a plan file with YAML frontmatter under `plan/` |\n| `list_plans.py` | List existing plans (supports `--query`, `--json`) |\n| `validate_issues_csv.py` | Validate Issue CSV schema and status values |\n\nRun with `--help` first. Scripts live in `scripts/` relative to this skill.\n\n## Naming\n\nPlans: `plan/YYYY-MM-DD_HH-mm-ss-<slug>.md` — Issue CSVs: `issues/YYYY-MM-DD_HH-mm-ss-<slug>.csv` — same timestamp/slug.\n\n## References\n\n- [Issue CSV spec](references/issue-csv-spec.md) — **read when creating or validating CSVs**\n- [Testing policy](references/testing-policy.md) — **read when filling `Test_Method`**\n- [Plan template](assets/_template.md) — structure with complexity tiers\n- [CSV template](assets/_template.csv) — example rows with plan-to-CSV mapping","tags":["issue","driven","workflow","agent","designer","appautomaton","agent-skills","agentic-workflows","ai-agents","ai-coding-assistant","claude-code","claude-skills"],"capabilities":["skill","source-appautomaton","skill-issue-driven-workflow","topic-agent-skills","topic-agentic-workflows","topic-ai-agents","topic-ai-coding-assistant","topic-claude-code","topic-claude-skills","topic-codex","topic-gemini-cli","topic-mcp"],"categories":["agent-designer"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/appautomaton/agent-designer/issue-driven-workflow","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add appautomaton/agent-designer","source_repo":"https://github.com/appautomaton/agent-designer","install_from":"skills.sh"}},"qualityScore":"0.506","qualityRationale":"deterministic score 0.51 from registry signals: · indexed on github topic:agent-skills · 113 github stars · SKILL.md body (3,565 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":"2026-05-18T18:56:19.539Z","embedding":null,"createdAt":"2026-05-06T00:55:54.731Z","updatedAt":"2026-05-18T18:56:19.539Z","lastSeenAt":"2026-05-18T18:56:19.539Z","tsv":"'1':82,159,241,306 '2':106,165,187,248,318 '3':183,257,325 '4':197,264,336 '5':210,276,349 '6':219,357 '7':230,374 '8':388 '9':396 'accept':338 'action':69,255,409 'affect':404 'agent':63,101 'amplifi':55 'approv':247 'ask':90,184,211 'aspir':182 'assets/_template.csv':523 'assets/_template.md':204,516 'assumpt':164,196 'autonom':19,73,108,284 'bar':136 'bash':222,278 'benefit':35 'block':401 'boundari':435 'break':5,249 'breakdown':39 'briefli':391 'chain':268 'chat':202 'check':381 'choos':205 'clarif':149,188 'code':234 'codex/skills/issue-driven-workflow/scripts/create_plan.py':224 'codex/skills/issue-driven-workflow/scripts/validate_issues_csv.py':280 'column':261 'commit':432 'complet':142,326,394 'complex':7,206,209,226,229,519 'concret':180 'confirm':213,221 'context':93,167 'correct':405 'creat':237,449,502 'create_plan.py':448 'csv':16,51,116,138,239,283,286,309,366,438,468,492,497,521,530 'csvs':490,505 'decis':133 'depend':175,267,270,316 'dev':320,346 'direct':439 'doc':89 'done':146,348,356,379,385 'draft':198 'drive':304 'driven':3,44 'e2e':150 'edit':233,436,444 'end':118,120 'end-to-end':117 'everi':137,177 'exampl':524 'execut':18,41,72,107,272,281,289 'exist':460 'fail':421 'file':173,218,452 'fill':258,511 'find':310 'first':476 'fix':422 'flag':425 'forward':305 'front':57 'front-load':56 'frontmatt':455 'full':66 'gather':92,166 'generat':242 'genuin':400 'git':430 'go':373 'granular':253 'help':475 'immedi':358 'implement':154 'independ':254 'inspect':174 'interact':84,158,240 'irrevers':408 'issu':2,15,43,50,153,467,489,496 'issue-driven':42 'issue-driven-workflow':1 'issues/yyyy-mm-dd_hh-mm-ss-':491 'json':464 'keep':303,372 'know':294 'larg':415 'list':459 'list_plans.py':458 'live':478 'load':58 'loop':151 'make':176 'map':531 'mark':353,382 'markabl':145 'maxim':121 'md':488 'mean':76,97 'medium':208,228 'met':340 'method':343,513 'move':359 'multipl':25 'name':485 'natur':434 'need':27 'next':312,362,370 'order':265,273,317 'pass':344 'passiv':112 'per':80,124,386 'permiss':130 'philosophi':46 'pick':368 'plan':12,48,83,96,152,157,178,200,217,236,245,251,451,457,461,486,514,528 'plan-to-csv':527 'plan/yyyy-mm-dd_hh-mm-ss-':487 'plate':67 'polici':507 'proactiv':110 'proceed':193 'progress':390 'project':172 'purpos':447 'python3':223,279 'qualiti':135 'queri':463 'question':91,189 're':441 're-valid':440 'read':88,171,291,307,330,364,500,509 'refer':495 'references/issue-csv-spec.md':263,499 'references/testing-policy.md':508 'regress':380,383 'relat':481 'repli':212 'repo':431 'report':389 'requir':31,260,335 'research':28 'restat':160 'review':156,352 'review1':354 'routin':132 'row':75,139,256,314,328,363,377,387,395,412,420,525 'run':81,125,473 'safeti':406 'schema':469 'script':445,446,477,480 'search':85,168,329 'section':179 'see':262 'self':351 'self-review':350 'set':269,319,345 'simpl':207,227 'skill':484 'skill-issue-driven-workflow' 'source-appautomaton' 'spec':498 'split':416 'start':30,323 'state':195,290 'status':32,321,347,355,384,471 'step':26 'stop':105,398 'structur':11,38,517 'support':462 'task':8,23,162,225 'templat':515,522 'test':155,332,342,506,512 'testabl':143 'think':60 'thorough':95 'tier':520 'timestamp/slug':494 'todo':313,371 'topic-agent-skills' 'topic-agentic-workflows' 'topic-ai-agents' 'topic-ai-coding-assistant' 'topic-claude-code' 'topic-claude-skills' 'topic-codex' 'topic-gemini-cli' 'topic-mcp' 'track':33 'trackabl':14 'unambigu':275 'unclear':191 'unknown':402 'updat':298 'use':20,78,122,203 'valid':277,442,466,504 'validate_issues_csv.py':465 'valu':472 'wait':128 'web':87,170 'whatev':333 'without':104,147 'work':54,70,79,99,113,123,302,324 'workflow':4,45 'write':215,331 'yaml':454","prices":[{"id":"b667ab8f-ef29-4170-8e8f-b5715663c635","listingId":"56fa7e1a-922d-4c7f-a0d1-6938118654a7","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"appautomaton","category":"agent-designer","install_from":"skills.sh"},"createdAt":"2026-05-06T00:55:54.731Z"}],"sources":[{"listingId":"56fa7e1a-922d-4c7f-a0d1-6938118654a7","source":"github","sourceId":"appautomaton/agent-designer/issue-driven-workflow","sourceUrl":"https://github.com/appautomaton/agent-designer/tree/main/skills/issue-driven-workflow","isPrimary":false,"firstSeenAt":"2026-05-06T00:55:54.731Z","lastSeenAt":"2026-05-18T18:56:19.539Z"}],"details":{"listingId":"56fa7e1a-922d-4c7f-a0d1-6938118654a7","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"appautomaton","slug":"issue-driven-workflow","github":{"repo":"appautomaton/agent-designer","stars":113,"topics":["agent-skills","agentic-workflows","ai-agents","ai-coding-assistant","claude-code","claude-skills","codex","gemini-cli","mcp"],"license":null,"html_url":"https://github.com/appautomaton/agent-designer","pushed_at":"2026-04-06T19:03:10Z","description":"Portable SKILLs workspace for Claude Code, Codex, and Gemini — issue-driven workflows and cross-agent collaboration via bridge scripts with session continuity.","skill_md_sha":"01eef99af7250d35b9d9775bcfa276ceeb556603","skill_md_path":"skills/issue-driven-workflow/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/appautomaton/agent-designer/tree/main/skills/issue-driven-workflow"},"layout":"multi","source":"github","category":"agent-designer","frontmatter":{"name":"issue-driven-workflow","description":"Break down complex tasks into a structured plan and trackable Issue CSV, then execute autonomously. Use when a task has multiple steps, needs research before starting, requires status tracking, or benefits from a structured breakdown before execution."},"skills_sh_url":"https://skills.sh/appautomaton/agent-designer/issue-driven-workflow"},"updatedAt":"2026-05-18T18:56:19.539Z"}}