{"id":"738ed431-fe6d-411d-9431-235f22e9ee8f","shortId":"hgwvnK","kind":"skill","title":"utility-pm-release-conductor","tagline":"Walk the guided release runbook (6 gates G0/G1/G2/G2.5/G3/G4) via the pm-release-conductor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-release-conductor with native chain composition to pm-skill-auditor at G0 and pm-changelog-curator","description":"<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->\n# PM Release Conductor (Dispatch Skill)\n\nCross-client dispatch wrapper for the `pm-release-conductor` sub-agent. Detects runtime; dispatches to the native sub-agent on Claude Code; reads `subagents/pm-release-conductor.md` and inlines chain composition on non-Claude clients via \"reference + execute inline\" pattern.\n\n> **Status summary (v2.16.0):** PRODUCTION on Claude Code (native sub-agent path). DRY-RUN VALIDATED on Codex CLI 2026-05-17 per [`gate-test-results_2026-05-17_codex.md`](../../docs/internal/release-plans/v2.16.0/gate-test-results_2026-05-17_codex.md); LIVE release on Codex CLI is NOT independently exercised, so use with caution and run `--dry-run` first as a rehearsal. EXPERIMENTAL on Cursor / Windsurf / Copilot CLI / Gemini CLI (UNTESTED at v2.16.0 ship).\n>\n> See [Sub-Agent Compatibility Matrix](../../docs/reference/sub-agent-compatibility.md) for the canonical safe-usage matrix + what-was-validated detail + v2.17 expansion plan. For live release on a non-Claude client, ideally re-run the harness at [`maintainer-gate-testing-codex.md`](../../docs/internal/release-plans/v2.16.0/maintainer-gate-testing-codex.md) on that specific client first.\n\n## When to Use\n\n- You are running a pm-skills release on a non-Claude client (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI)\n- You want the same 6-gate discipline that pm-release-conductor enforces on Claude Code, with auditor + curator behaviors inlined at the relevant gates\n- You explicitly want skill-invocation semantics over sub-agent semantics on Claude Code (rare; the native sub-agent is preferred on Claude Code)\n\n## When NOT to Use\n\n- You only need to review a PM artifact -> use `utility-pm-critic`\n- You only need a governance audit (not a release) -> use `utility-pm-skill-auditor`\n- You only need a CHANGELOG draft (not a release) -> use `utility-pm-changelog-curator`\n- You want to perform release operations WITHOUT explicit gate confirmation -> the conductor refuses bypass; manual release outside the conductor is the right path\n\n## Instructions\n\n**Runtime detection step.** Determine which AI client is invoking this skill.\n\n### If you are running in Claude Code with the pm-skills plugin installed\n\nInvoke `@agent-pm-release-conductor` with the user's target version + optional flags from `$ARGUMENTS`. The native sub-agent walks the 6 gates and natively chains to `pm-skill-auditor` (G0, G2.5) and `pm-changelog-curator` (G2) via the Agent tool. Return the conductor's gate-by-gate output to the user.\n\n### If you are running in any other AI client\n\nCodex CLI, Cursor, Windsurf, Copilot, Gemini CLI, or any other client without native pm-skills plugin sub-agent support:\n\n1. Read the canonical sub-agent definition at `subagents/pm-release-conductor.md`\n2. Read the canonical runbook at `docs/contributing/release-runbook.md` (the conductor's referential source for gate definitions)\n3. Execute the system prompt body as your operating instructions\n4. Walk the 6 gates inline. At gates that require chain composition:\n   - **G0 (Pre-tag readiness):** instead of chaining to pm-skill-auditor, read `subagents/pm-skill-auditor.md` and execute the auditor's 4-step audit flow inline. Capture the layered output (full findings + Status Summary + Status YAML). Treat the Status YAML as your G0 sub-check 5 input.\n   - **G2 (Version bump + CHANGELOG prep):** instead of chaining to pm-changelog-curator, read `subagents/pm-changelog-curator.md` and execute the curator's 8-step drafting flow inline. Capture the layered output. Treat the Status YAML as your G2 sub-check 3 input.\n   - **G2.5 (Re-verify):** re-execute the inlined auditor at sub-check 5 against the new HEAD.\n5. Pause at each gate boundary for explicit maintainer confirmation\n6. Refuse bypass attempts; respect refusal protocols\n7. Tag only the G2.5-captured SHA at G3 per D22\n8. Return gate-by-gate output throughout the flow\n\nThe \"reference + execute inline\" pattern is what enables cross-client compatibility for chain composition. Phase 2 GATE C sub-spike validates that this pattern is reliable.\n\n## Critical Caveats for Non-Claude Inline Execution\n\nBecause non-Claude clients cannot natively chain, the auditor and curator behaviors run in the SAME context window as the conductor on non-Claude clients. This has implications:\n\n1. **Context budget.** The combined token budget (conductor + inlined auditor + inlined curator + their child reads) may approach context limits on long releases. Plan accordingly.\n2. **Tool authorization.** The conductor's tool list includes Bash, Read, Edit, Grep, Glob, Agent. The auditor needs Bash + Read + Grep + Glob. The curator needs Bash + Read + Grep. Inline execution on non-Claude clients should have access to ALL of these (i.e., not be running in a Read-only mode).\n3. **Refusal cascade.** If the inlined auditor refuses (e.g., validators not invocable), the conductor's G0 sub-check 5 fails and the gate pauses. Same for the curator at G2.\n\n## Reference Files\n\n- Canonical sub-agent definition: [`subagents/pm-release-conductor.md`](../../subagents/pm-release-conductor.md)\n- Canonical runbook: [`docs/contributing/release-runbook.md`](../../docs/contributing/release-runbook.md)\n- Behavioral spec: [`docs/internal/release-plans/v2.16.0/spec_pm-release-conductor.md`](../../docs/internal/release-plans/v2.16.0/spec_pm-release-conductor.md)\n- Chain child (inlined at G0 + G2.5): [`subagents/pm-skill-auditor.md`](../../subagents/pm-skill-auditor.md)\n- Chain child (inlined at G2): [`subagents/pm-changelog-curator.md`](../../subagents/pm-changelog-curator.md)\n- Pre-tag validator bundle: `scripts/pre-tag-validate.{sh,ps1}`\n- Runtime components catalog: [`docs/reference/runtime-components.md`](../../docs/reference/runtime-components.md)\n- Output template: `references/TEMPLATE.md`\n- Worked example: `references/EXAMPLE.md`","tags":["utility","release","conductor","skills","product-on-purpose","agent-skills","ai-skills","claude-code","claude-desktop","design-sprint","foundation-sprint","openskills"],"capabilities":["skill","source-product-on-purpose","skill-utility-pm-release-conductor","topic-agent-skills","topic-ai-skills","topic-claude-code","topic-claude-desktop","topic-design-sprint","topic-foundation-sprint","topic-openskills","topic-product-management","topic-skill-families","topic-triple-diamond"],"categories":["pm-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/product-on-purpose/pm-skills/utility-pm-release-conductor","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add product-on-purpose/pm-skills","source_repo":"https://github.com/product-on-purpose/pm-skills","install_from":"skills.sh"}},"qualityScore":"0.560","qualityRationale":"deterministic score 0.56 from registry signals: · indexed on github topic:agent-skills · 221 github stars · SKILL.md body (5,915 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":"2026-05-18T18:55:01.780Z","embedding":null,"createdAt":"2026-05-17T18:54:31.472Z","updatedAt":"2026-05-18T18:55:01.780Z","lastSeenAt":"2026-05-18T18:55:01.780Z","tsv":"'-05':123 '-17':124 '/../docs/contributing/release-runbook.md':841 '/../docs/internal/release-plans/v2.16.0/gate-test-results_2026-05-17_codex.md':127 '/../docs/internal/release-plans/v2.16.0/maintainer-gate-testing-codex.md':201 '/../docs/internal/release-plans/v2.16.0/spec_pm-release-conductor.md':845 '/../docs/reference/runtime-components.md':873 '/../docs/reference/sub-agent-compatibility.md':168 '/../subagents/pm-changelog-curator.md':860 '/../subagents/pm-release-conductor.md':837 '/../subagents/pm-skill-auditor.md':853 '1':465,722 '2':475,672,746 '2026':122 '3':490,598,798 '4':500,532 '5':557,614,619,817 '6':11,235,401,503,629 '7':636 '8':579,646 'access':783 'accord':745 'agent':22,36,74,83,113,165,266,276,380,398,421,463,471,760,834 'agent-pm-release-conductor':35,379 'ai':358,442 'approach':738 'argument':393 'artifact':293 'attempt':632 'audit':304,534 'auditor':48,248,313,410,524,530,609,701,731,762,804 'author':748 'bash':755,764,771 'behavior':250,704,842 'bodi':495 'boundari':624 'budget':724,728 'bump':561 'bundl':865 'bypass':342,631 'c':674 'cannot':697 'canon':171,468,478,831,838 'captur':537,584 'cascad':800 'catalog':871 'caution':140 'caveat':685 'chain':42,91,405,510,519,566,669,699,846,854 'changelog':54,318,327,416,562,570 'check':556,597,613,816 'child':735,847,855 'claud':26,85,96,108,191,222,245,269,280,369,689,695,717,779 'cli':121,132,155,157,225,230,445,450 'client':63,97,192,205,223,359,443,454,666,696,718,780 'code':27,86,109,246,270,281,370 'codex':120,131,224,444 'combin':726 'compat':166,667 'compon':870 'composit':43,92,511,670 'conductor':5,19,39,58,71,242,340,347,383,425,483,713,729,750,811 'confirm':338,628 'context':709,723,739 'copilot':154,228,448 'critic':298,684 'cross':62,665 'cross-client':61,664 'curat':55,249,328,417,571,577,703,733,769,826 'cursor':152,226,446 'd22':645 'definit':472,489,835 'detail':180 'detect':75,354 'determin':356 'disciplin':237 'dispatch':23,59,64,77 'docs/contributing/release-runbook.md':481,840 'docs/internal/release-plans/v2.16.0/spec_pm-release-conductor.md':844 'docs/reference/runtime-components.md':872 'draft':319,581 'dri':116,144 'dry-run':115,143 'e.g':806 'edit':757 'enabl':663 'enforc':243 'exampl':878 'execut':100,491,528,575,606,658,691,775 'exercis':136 'expans':182 'experiment':150 'explicit':257,336,626 'fail':818 'file':830 'find':542 'first':146,206 'flag':391 'flow':535,582,655 'full':541 'g0':50,411,512,553,813,850 'g0/g1/g2/g2.5/g3/g4':13 'g2':418,559,594,828,858 'g2.5':412,600,851 'g2.5-captured':640 'g3':643 'gate':12,236,255,337,402,428,430,488,504,507,623,649,651,673,821 'gate-by-g':427,648 'gate-test-results_2026-05-17_codex.md':126 'gemini':156,229,449 'glob':759,767 'govern':303 'grep':758,766,773 'guid':8 'har':198 'head':618 'i.e':788 'ideal':193 'implic':721 'includ':754 'independ':135 'inlin':90,101,251,505,536,583,608,659,690,730,732,774,803,848,856 'input':558,599 'instal':377 'instead':517,564 'instruct':352,499 'invoc':261,809 'invok':34,361,378 'layer':539,586 'limit':740 'list':753 'live':128,185 'long':742 'maintain':627 'maintainer-gate-testing-codex.md':200 'manual':343 'matrix':167,175 'may':737 'mode':797 'nativ':24,41,80,110,273,395,404,456,698 'need':288,301,316,763,770 'new':617 'non':95,190,221,688,694,716,778 'non-claud':94,189,220,687,693,715,777 'oper':334,498 'option':390 'output':431,540,587,652,874 'outsid':345 'path':114,351 'pattern':102,660,681 'paus':620,822 'per':125,644 'perform':332 'phase':671 'plan':183,744 'plugin':33,376,460 'pm':3,17,31,37,46,53,56,69,215,240,292,297,311,326,374,381,408,415,458,522,569 'pm-changelog-cur':52,414,568 'pm-release-conductor':16,68,239 'pm-skill':30,214,373,457 'pm-skill-auditor':45,407,521 'pre':514,862 'pre-tag':513,861 'prefer':278 'prep':563 'product':106 'prompt':494 'protocol':635 'ps1':868 'rare':271 're':195,602,605 're-execut':604 're-run':194 're-verifi':601 'read':87,466,476,525,572,736,756,765,772,795 'read-on':794 'readi':516 'refer':99,657,829 'references/example.md':879 'references/template.md':876 'referenti':485 'refus':341,630,634,799,805 'rehears':149 'releas':4,9,18,38,57,70,129,186,217,241,307,322,333,344,382,743 'relev':254 'reliabl':683 'requir':509 'respect':633 'return':423,647 'review':290 'right':350 'run':117,142,145,196,212,367,438,705,791 'runbook':10,479,839 'runtim':76,353,869 'safe':173 'safe-usag':172 'scripts/pre-tag-validate':866 'see':162 'semant':262,267 'sh':867 'sha':641 'ship':161 'skill':32,47,60,216,260,312,363,375,409,459,523 'skill-invoc':259 'skill-utility-pm-release-conductor' 'sourc':486 'source-product-on-purpose' 'spec':843 'specif':204 'spike':677 'status':103,543,545,549,590 'step':355,533,580 'sub':21,73,82,112,164,265,275,397,462,470,555,596,612,676,815,833 'sub-ag':20,72,81,111,163,264,274,396,461,469,832 'sub-check':554,595,611,814 'sub-spik':675 'subagents/pm-changelog-curator.md':573,859 'subagents/pm-release-conductor.md':88,474,836 'subagents/pm-skill-auditor.md':526,852 'summari':104,544 'support':464 'system':493 'tag':515,637,863 'target':388 'templat':875 'throughout':653 'token':727 'tool':422,747,752 'topic-agent-skills' 'topic-ai-skills' 'topic-claude-code' 'topic-claude-desktop' 'topic-design-sprint' 'topic-foundation-sprint' 'topic-openskills' 'topic-product-management' 'topic-skill-families' 'topic-triple-diamond' 'treat':547,588 'untest':158 'usag':174 'use':138,209,285,294,308,323 'user':386,434 'util':2,296,310,325 'utility-pm-changelog-cur':324 'utility-pm-crit':295 'utility-pm-release-conductor':1 'utility-pm-skill-auditor':309 'v2.16.0':105,160 'v2.17':181 'valid':118,179,678,807,864 'verifi':603 'version':389,560 'via':14,98,419 'walk':6,399,501 'want':232,258,330 'what-was-valid':176 'window':710 'windsurf':153,227,447 'without':335,455 'work':877 'wrapper':65 'yaml':546,550,591","prices":[{"id":"50649522-a97d-4d7d-9860-ead85ec8ef42","listingId":"738ed431-fe6d-411d-9431-235f22e9ee8f","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"product-on-purpose","category":"pm-skills","install_from":"skills.sh"},"createdAt":"2026-05-17T18:54:31.472Z"}],"sources":[{"listingId":"738ed431-fe6d-411d-9431-235f22e9ee8f","source":"github","sourceId":"product-on-purpose/pm-skills/utility-pm-release-conductor","sourceUrl":"https://github.com/product-on-purpose/pm-skills/tree/main/skills/utility-pm-release-conductor","isPrimary":false,"firstSeenAt":"2026-05-17T18:54:31.472Z","lastSeenAt":"2026-05-18T18:55:01.780Z"}],"details":{"listingId":"738ed431-fe6d-411d-9431-235f22e9ee8f","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"product-on-purpose","slug":"utility-pm-release-conductor","github":{"repo":"product-on-purpose/pm-skills","stars":221,"topics":["agent-skills","ai-skills","claude-code","claude-desktop","design-sprint","foundation-sprint","openskills","product-management","skill-families","triple-diamond"],"license":"apache-2.0","html_url":"https://github.com/product-on-purpose/pm-skills","pushed_at":"2026-05-18T18:13:01Z","description":"55 plug-and-play PM skills for AI agents: 26 Triple Diamond phase + 8 foundation (persona, OKR writer, meeting family, lean canvas) + 6 utility (skill lifecycle) + 15 tool implementing canonical Foundation Sprint + Design Sprint methodologies. Templates, workflows, samples, CI-enforced family contracts. Apache 2.0.","skill_md_sha":"06d7e85d634ea25f9988bb9b11fa2e6d5e440797","skill_md_path":"skills/utility-pm-release-conductor/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/product-on-purpose/pm-skills/tree/main/skills/utility-pm-release-conductor"},"layout":"multi","source":"github","category":"pm-skills","frontmatter":{"name":"utility-pm-release-conductor","license":"Apache-2.0","description":"Walk the guided release runbook (6 gates G0/G1/G2/G2.5/G3/G4) via the pm-release-conductor sub-agent. Dispatches natively on Claude Code with the pm-skills plugin (invokes @agent-pm-release-conductor with native chain composition to pm-skill-auditor at G0 and pm-changelog-curator at G2); on non-Claude clients (Codex CLI, Cursor, Windsurf, Copilot, Gemini CLI) reads subagents/pm-release-conductor.md and inlines auditor + curator behaviors at G0 + G2 via reference-and-execute-inline pattern (because non-Claude clients cannot natively chain to other sub-agents). Returns gate-by-gate output with explicit confirmation pauses, refuses bypass attempts, tags only the G2.5-captured SHA per master plan D22."},"skills_sh_url":"https://skills.sh/product-on-purpose/pm-skills/utility-pm-release-conductor"},"updatedAt":"2026-05-18T18:55:01.780Z"}}