{"id":"f2b8e582-a72b-439d-9ce3-4308e51efa73","shortId":"HtgUDP","kind":"skill","title":"utility-pm-skill-iterate","tagline":"Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback.","description":"# PM Skill Iterate\n\nThis skill improves an existing pm-skills skill by applying targeted changes\nbased on input you provide. It reads the current skill files, proposes\nchanges as before/after previews grouped by file, and writes them on your\nconfirmation. After applying changes, it suggests a version bump class and\noffers to update HISTORY.md.\n\nThe iterator accepts any of these as input:\n- A validation report from `/pm-skill-validate`\n- Direct feedback (\"the template is missing section X\")\n- A convention change (\"all skills now need a Limitations section\")\n- A general improvement request (\"make the example more realistic\")\n\n## When to Use\n\n- After running `/pm-skill-validate` and getting a report with findings\n- When you have specific feedback on a skill and want to apply it\n- When a repo convention changes and a skill needs to conform\n- When a skill's example, template, or instructions need improvement\n- When iterating on a skill before a release\n\n## When NOT to Use\n\n- To create a new skill from scratch -> use `/pm-skill-builder`\n- To audit a skill before making changes -> use `/pm-skill-validate` first\n- To make bulk convention changes across many skills -> run `/pm-skill-validate --all` first to triage, then iterate one skill at a time\n\n## Instructions\n\nWhen asked to iterate on a skill, follow these steps:\n\n### Step 1: Identify the Target Skill\n\nAccept the skill name in any form:\n- Directory name: `deliver-prd`\n- Full path: `skills/deliver-prd/SKILL.md`\n- Slash command: `/prd`\n\nResolve to the canonical directory path: `skills/{name}/`.\n\nIf the skill directory does not exist, stop and report: \"Skill directory\n`skills/{name}/` does not exist. Use `/pm-skill-builder` to create it.\"\n\n### Step 2: Read Current Skill Files\n\nRead all files in the skill directory:\n\n| File | Required | Purpose |\n|------|----------|---------|\n| `SKILL.md` | yes | Frontmatter + instructions (the primary edit target) |\n| `references/TEMPLATE.md` | yes | Output template |\n| `references/EXAMPLE.md` | yes | Worked example |\n| `HISTORY.md` | no | Version history (needed for Step 7) |\n\nRecord the exact content of each file at this point. You will compare\nagainst this content before writing in Step 5 (stale-preview guard).\n\nIf reading files is not possible (MCP/embedded environment), ask the user\nto paste the relevant file contents before proceeding (see Degraded Mode).\n\n### Step 3: Normalize Input into Intended Changes\n\nRegardless of input type, extract a structured list of intended changes\nbefore generating any edits. This normalization step is what makes the\nunified flow work consistently across all input types.\n\n**If the input is a validation report** (from `/pm-skill-validate`):\n- Check for `Report schema: v1` in the header. If absent or a different\n  schema version, warn: \"This report uses an unrecognized schema. I'll\n  do my best but may miss structured fields.\"\n- Parse the `## Recommendations` section.\n- Split each recommendation line on `|` to extract:\n  - Position 1: severity (FAIL, WARN, INFO)\n  - Position 2: check ID\n  - After `Target:`: file path\n  - After `Action:` (next line): what to change\n- Build the intended changes list from these fields.\n\n**If the input is free text** (feedback, convention change, improvement request):\n- Read the input and identify what needs to change.\n- Map each change to a specific target file and section.\n- If the input is vague, ask ONE clarifying question before proceeding.\n\nPresent the normalized list for user confirmation:\n\n```\nIntended changes:\n1. Target: skills/{name}/SKILL.md -> {section}\n   Change: {what will change}\n   Source: {validation report check ID | user feedback | convention change}\n2. Target: skills/{name}/references/EXAMPLE.md -> {section}\n   Change: {what will change}\n   Source: {source}\n```\n\nIf the user wants to modify the list (add, remove, or change items),\nadjust and re-present before proceeding.\n\n### Step 4: Preview Proposed Changes\n\nFor each intended change, generate the proposed edit and present it as\na before/after block grouped by file:\n\n```\n### skills/{name}/SKILL.md\n\n**{Section name} -- before:**\n> {exact current content of the section being changed}\n\n**{Section name} -- after:**\n> {proposed new content for this section}\n\n### skills/{name}/references/EXAMPLE.md\n\n**{Section name} -- before:**\n> {exact current content}\n\n**{Section name} -- after:**\n> {proposed new content}\n```\n\n**Preview rules:**\n- Group all changes by file. Show each file once, with all its changes.\n- Show enough surrounding context for the user to understand the change.\n- For small edits (a few lines), show the full section before and after.\n- For large edits (rewriting most of a section), show the section header\n  and the first/last few lines of before, then the full after.\n- Do NOT show files that are not being changed.\n\nAsk: \"Apply these changes? [yes / no]\"\n\nIf the user says no, ask what to adjust and return to Step 3 or Step 4.\n\n### Step 5: Apply Changes (with Stale-Preview Guard)\n\n**Before writing any file**, re-read each target file and compare its\ncontent to what you recorded in Step 2.\n\n**If any target file has changed since Step 2:**\n- Do NOT write any files.\n- Report: \"File `{path}` has changed since the preview was generated.\n  Regenerating preview with current content.\"\n- Return to Step 2 with the same intended changes list.\n\n**If all target files match:**\n- Write the changes to each target file.\n- Update the `updated` field in SKILL.md frontmatter to today's date.\n  (The `updated` field tracks when the file was last modified, regardless\n  of whether a version bump is accepted.)\n- Report what was written: list each file and a one-line summary of\n  what changed.\n\n### Step 6: Suggest Version Bump\n\nAfter changes are applied, classify the overall change and suggest a\nversion bump class. Do NOT auto-write the version number.\n\n**Classification rules** (from `docs/internal/skill-versioning.md`):\n\n| Change type | Bump class | Examples |\n|------------|------------|---------|\n| Wording clarified, examples improved, typos fixed | **patch** | Reworded checklist item, better example scenario, description expanded |\n| New optional capability or section added | **minor** | New optional output section, handles more scenarios, new quality check |\n| Required contract changed, interaction pattern breaks | **major** | Command renamed, required section removed, \"done\" definition narrowed |\n\n**Tie-breaker:** If a user must do something new to stay compliant with\nthe skill's required contract, classify as major. If the new behavior is\nadditive or optional, classify as minor. If the required behavior is\nunchanged and only clarified, classify as patch.\n\nPresent the suggestion:\n\n```\nSuggested bump: {class} ({reason}).\nCurrent version: {current}.\nBump to {suggested}? [yes / override / skip]\n```\n\n- **yes**: Write the new version to SKILL.md frontmatter.\n- **override**: Ask for the desired version, validate it's valid SemVer\n  and higher than current, then write it.\n- **skip**: Leave the version unchanged. The user may bump it later\n  during release prep.\n\n### Step 7: Offer HISTORY.md Update\n\nAfter the version decision, produce a change summary and handle\nHISTORY.md based on the current state:\n\n**If HISTORY.md exists and version was bumped:**\n1. Read HISTORY.md and validate its format:\n   - Has a summary table with `| Version | Date | Release | ...` header\n   - Versions are newest-first in the table\n   - Each table version has a corresponding `## X.Y.Z` section below\n2. **If format is valid**: offer to append.\n   \"Would you like me to add this version to HISTORY.md? [yes / no]\"\n   On yes: add a new row to the summary table (newest-first) and a new\n   `## X.Y.Z` section with the change summary.\n3. **If format is invalid**: warn and show the proposed content without\n   writing. \"HISTORY.md doesn't follow the expected format. Here's what\n   I would add -- you can paste it manually:\"\n   Then show the proposed table row and version section.\n\n**If HISTORY.md does not exist and this is the skill's second version:**\nOffer to create it. \"This is the second version of this skill. Would you\nlike me to create HISTORY.md with entries for both versions? [yes / no]\"\nOn yes: create HISTORY.md with the format from `docs/internal/skill-versioning.md`,\nincluding entries for both the original version (from release history or\neffort brief) and the new version.\n\n**If HISTORY.md does not exist and version was not bumped:**\nNo offer. HISTORY.md is premature until the skill has shipped a second version.\n\n**If HISTORY.md exists but version was not bumped (skip):**\nNo offer. The change summary is available in the conversation for the user\nto use at their discretion.\n\n### Step 8: Report Summary\n\nPresent a final summary:\n\n```\n## Iteration Complete: {skill-name}\n\n**Files changed:**\n- skills/{name}/SKILL.md -- {summary}\n- skills/{name}/references/EXAMPLE.md -- {summary}\n\n**Version:** {current} -> {new} ({class}) | or: unchanged (skipped)\n**HISTORY.md:** updated | created | skipped | not applicable\n\n**Next steps:**\n- Run `/pm-skill-validate {name}` to verify the changes pass\n- Run local CI: `bash scripts/lint-skills-frontmatter.sh`\n- If satisfied, commit the changes\n```\n\n## Degraded Mode\n\nIf you cannot read skill files directly (e.g., running via MCP or in an\nembedded environment without file system access):\n\n1. **Validation-report-driven iteration** is preferred in this mode.\n   The report carries the context (check IDs, target paths, actions).\n2. For free-text iteration, ask the user to paste the content of each\n   relevant file before proposing changes.\n3. The stale-preview guard (Step 5) cannot run -- note in the summary:\n   \"Applied without stale-preview check (file system not available).\"\n4. HISTORY.md operations require the user to paste the current file\n   content or confirm it does not exist.\n\n## Output Contract\n\nThe iterator MUST:\n- Normalize input into a structured intended-changes list before editing\n- Present all proposed changes as before/after previews grouped by file\n- Require explicit user confirmation before writing any file\n- Re-read target files before writing to guard against stale previews\n- Update the `updated` frontmatter field on every apply\n- Suggest a version bump class without auto-writing the version number\n- Handle HISTORY.md according to the rules in Step 7\n\nThe iterator MUST NOT:\n- Write files without showing a preview first\n- Write files without user confirmation\n- Auto-increment the version number without explicit confirmation\n- Create HISTORY.md for a skill still on its first version\n- Append to HISTORY.md without validating its format first\n\n## Quality Checklist\n\nBefore completing the iteration, verify:\n\n- [ ] Input was normalized into an intended-changes list before editing\n- [ ] All proposed changes were shown as before/after previews\n- [ ] User confirmed before any files were written\n- [ ] Stale-preview guard ran before writing (or noted as unavailable)\n- [ ] `updated` date was set to today in SKILL.md frontmatter\n- [ ] Version bump class was suggested with correct reasoning\n- [ ] Version was only written after explicit user confirmation\n- [ ] HISTORY.md was handled correctly per Step 7 rules\n- [ ] Final summary was presented with next steps\n\n## Examples\n\nSee `references/EXAMPLE.md` for a completed iteration demonstrating\na validation-report-driven improvement to a real shipped skill.","tags":["utility","skill","iterate","skills","product-on-purpose","agent-skills","ai-skills","claude-code","claude-desktop","openskills","product-management","skill-families"],"capabilities":["skill","source-product-on-purpose","skill-utility-pm-skill-iterate","topic-agent-skills","topic-ai-skills","topic-claude-code","topic-claude-desktop","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-skill-iterate","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":"0.538","qualityRationale":"deterministic score 0.54 from registry signals: · indexed on github topic:agent-skills · 176 github stars · SKILL.md body (11,400 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":"2026-05-02T12:54:13.495Z","embedding":null,"createdAt":"2026-04-18T22:09:31.758Z","updatedAt":"2026-05-02T12:54:13.495Z","lastSeenAt":"2026-05-02T12:54:13.495Z","tsv":"'/pm-skill-builder':208,301 '/pm-skill-validate':114,147,217,228,437,1373 '/prd':274 '/references/example.md':583,659,1355 '/skill.md':564,636,1351 '1':252,482,560,1104,1412 '2':306,488,579,795,804,828,1137,1433 '3':393,762,1179,1453 '4':612,765,1477 '5':365,767,1460 '6':893 '7':344,1077,1569,1688 '8':1335 'absent':447 'accept':104,257,875 'access':1411 'accord':1563 'across':224,425 'action':496,1432 'ad':948 'add':599,1150,1159,1204 'addit':1002 'adjust':604,757 'append':1144,1605 'appli':6,60,89,165,744,768,900,1467,1548 'applic':1369 'ask':242,378,545,743,754,1045,1439 'audit':210 'auto':914,1556,1587 'auto-incr':1586 'auto-writ':913,1555 'avail':1322,1476 'base':16,63,1092 'bash':1383 'before/after':77,629,1516,1637 'behavior':1000,1011 'best':464 'better':938 'block':630 'break':965 'breaker':977 'brief':1279 'build':502 'bulk':221 'bump':37,95,873,896,909,925,1024,1030,1070,1103,1293,1314,1552,1667 'cannot':1394,1461 'canon':278 'capabl':945 'carri':1425 'chang':23,29,62,75,90,125,171,215,223,398,409,501,505,518,529,532,559,566,569,578,585,588,602,615,619,647,676,686,697,742,746,769,801,814,833,842,891,898,904,923,962,1087,1177,1319,1348,1378,1389,1452,1507,1514,1627,1633 'check':438,489,573,959,1428,1472 'checklist':936,1614 'ci':1382 'clarifi':547,929,1016 'class':96,910,926,1025,1360,1553,1668 'classif':919 'classifi':901,994,1005,1017 'command':273,967 'commit':1387 'compar':357,786 'complet':1343,1616,1702 'compliant':987 'confirm':32,87,557,1490,1524,1585,1594,1640,1681 'conform':177 'consist':424 'content':348,360,386,642,653,665,671,788,824,1189,1445,1488 'context':690,1427 'contract':961,993,1496 'convent':22,124,170,222,517,577 'convers':1325 'correct':1672,1685 'correspond':1133 'creat':201,303,1234,1249,1260,1366,1595 'current':25,71,308,641,664,823,1027,1029,1058,1095,1358,1486 'date':857,1117,1658 'decis':1084 'definit':973 'degrad':390,1390 'deliv':267 'deliver-prd':266 'demonstr':1704 'descript':941 'desir':1048 'differ':450 'direct':115,1398 'directori':264,279,286,294,317 'discret':1333 'docs/internal/skill-versioning.md':922,1266 'doesn':1193 'done':972 'driven':1416,1709 'e.g':1399 'edit':327,413,623,700,713,1510,1630 'effort':1278 'embed':1406 'enough':688 'entri':1252,1268 'environ':377,1407 'everi':1547 'exact':347,640,663 'exampl':139,182,336,927,930,939,1697 'exist':11,54,289,299,1099,1223,1288,1309,1494 'expand':942 'expect':1197 'explicit':1522,1593,1679 'extract':403,480 'fail':484 'feedback':18,46,116,158,516,576 'field':469,509,850,860,1545 'file':26,73,81,310,313,318,351,372,385,493,537,633,678,681,737,778,784,799,809,811,838,846,864,882,1347,1397,1409,1449,1473,1487,1520,1528,1533,1575,1582,1643 'final':1340,1690 'find':153 'first':218,230,1124,1169,1580,1603,1612 'first/last':725 'fix':933 'flow':422 'follow':248,1195 'form':263 'format':1110,1139,1181,1198,1264,1611 'free':514,1436 'free-text':1435 'frontmatt':323,853,1043,1544,1665 'full':269,706,732 'general':134 'generat':411,620,819 'get':149 'group':79,631,674,1518 'guard':369,774,1458,1537,1649 'handl':954,1090,1561,1684 'header':445,722,1119 'higher':1056 'histori':340,1276 'history.md':101,337,1079,1091,1098,1106,1154,1192,1220,1250,1261,1285,1296,1308,1364,1478,1562,1596,1607,1682 'id':490,574,1429 'identifi':253,525 'improv':8,40,52,135,187,519,931,1710 'includ':1267 'increment':1588 'info':486 'input':65,109,395,401,427,431,512,523,542,1501,1620 'instruct':185,240,324 'intend':397,408,504,558,618,832,1506,1626 'intended-chang':1505,1625 'interact':963 'invalid':1183 'item':603,937 'iter':5,49,103,189,234,244,1342,1417,1438,1498,1571,1618,1703 'larg':712 'last':866 'later':1072 'leav':1063 'like':1147,1246 'limit':131 'line':477,498,703,727,887 'list':406,506,554,598,834,880,1508,1628 'll':461 'local':1381 'major':966,996 'make':137,214,220,419 'mani':225 'manual':1209 'map':530 'match':839 'may':466,1069 'mcp':1402 'mcp/embedded':376 'minor':949,1007 'miss':120,467 'mode':391,1391,1422 'modifi':596,867 'must':981,1499,1572 'name':260,265,282,296,563,582,635,638,649,658,661,667,1346,1350,1354,1374 'narrow':974 'need':129,175,186,341,527 'new':203,652,670,943,950,957,984,999,1039,1161,1172,1282,1359 'newest':1123,1168 'newest-first':1122,1167 'next':497,1370,1695 'normal':394,415,553,1500,1622 'note':1463,1654 'number':918,1560,1591 'offer':98,1078,1142,1232,1295,1317 'one':235,546,886 'one-lin':885 'oper':1479 'option':944,951,1004 'origin':1272 'output':331,952,1495 'overal':903 'overrid':1034,1044 'pars':470 'pass':1379 'past':382,1207,1443,1484 'patch':934,1019 'path':270,280,494,812,1431 'pattern':964 'per':1686 'pm':3,13,47,56 'pm-skill':12,55 'point':354 'posit':481,487 'possibl':375 'prd':268 'prefer':1419 'prematur':1298 'prep':1075 'present':551,608,625,1020,1338,1511,1693 'preview':27,78,368,613,672,773,817,821,1457,1471,1517,1540,1579,1638,1648 'primari':326 'proceed':388,550,610 'produc':1085 'propos':28,74,614,622,651,669,1188,1213,1451,1513,1632 'provid':67 'purpos':320 'qualiti':958,1613 'question':548 'ran':1650 're':607,780,1530 're-pres':606 're-read':779,1529 'read':24,69,307,311,371,521,781,1105,1395,1531 'real':1713 'realist':141 'reason':1026,1673 'recommend':472,476 'record':345,792 'references/example.md':333,1699 'references/template.md':329 'regardless':399,868 'regener':820 'releas':195,1074,1118,1275 'relev':384,1448 'remov':600,971 'renam':968 'repo':169 'report':20,112,151,292,435,440,455,572,810,876,1336,1415,1424,1708 'request':136,520 'requir':319,960,969,992,1010,1480,1521 'resolv':275 'return':759,825 'reword':935 'rewrit':714 'row':1162,1215 'rule':673,920,1566,1689 'run':146,227,1372,1380,1400,1462 'satisfi':1386 'say':752 'scenario':940,956 'schema':441,451,459 'scratch':206 'scripts/lint-skills-frontmatter.sh':1384 'second':1230,1239,1305 'section':121,132,473,539,565,584,637,645,648,656,660,666,707,718,721,947,953,970,1135,1174,1218 'see':389,1698 'semver':1054 'set':1660 'sever':483 'ship':1303,1714 'show':679,687,704,719,736,1186,1211,1577 'shown':1635 'sinc':802,815 'skill':4,14,15,42,48,51,57,58,72,127,161,174,180,192,204,212,226,236,247,256,259,281,285,293,295,309,316,562,581,634,657,990,1228,1243,1301,1345,1349,1353,1396,1599,1715 'skill-nam':1344 'skill-utility-pm-skill-iterate' 'skill.md':321,852,1042,1664 'skills/deliver-prd/skill.md':271 'skip':1035,1062,1315,1363,1367 'slash':272 'small':699 'someth':983 'sourc':570,589,590 'source-product-on-purpose' 'specif':157,535 'split':474 'stale':367,772,1456,1470,1539,1647 'stale-preview':366,771,1455,1469,1646 'state':1096 'stay':986 'step':250,251,305,343,364,392,416,611,761,764,766,794,803,827,892,1076,1334,1371,1459,1568,1687,1696 'still':1600 'stop':290 'structur':405,468,1504 'suggest':34,92,894,906,1022,1023,1032,1549,1670 'summari':888,1088,1113,1165,1178,1320,1337,1341,1352,1356,1466,1691 'surround':689 'system':1410,1474 'tabl':1114,1127,1129,1166,1214 'target':7,61,255,328,492,536,561,580,783,798,837,845,1430,1532 'templat':118,183,332 'text':515,1437 'tie':976 'tie-break':975 'time':239 'today':855,1662 'topic-agent-skills' 'topic-ai-skills' 'topic-claude-code' 'topic-claude-desktop' 'topic-openskills' 'topic-product-management' 'topic-skill-families' 'topic-triple-diamond' 'track':861 'triag':232 'type':402,428,924 'typo':932 'unavail':1656 'unchang':1013,1066,1362 'understand':695 'unifi':421 'unrecogn':458 'updat':100,847,849,859,1080,1365,1541,1543,1657 'use':38,144,199,207,216,300,456,1330 'user':380,556,575,593,693,751,980,1068,1328,1441,1482,1523,1584,1639,1680 'util':2 'utility-pm-skill-iter':1 'v1':442 'vagu':544 'valid':19,44,111,434,571,1050,1053,1108,1141,1414,1609,1707 'validation-report-driven':1413,1706 'verifi':1376,1619 'version':36,94,339,452,872,895,908,917,1028,1040,1049,1065,1083,1101,1116,1120,1130,1152,1217,1231,1240,1255,1273,1283,1290,1306,1311,1357,1551,1559,1590,1604,1666,1674 'via':1401 'want':163,594 'warn':453,485,1184 'whether':870 'without':1190,1408,1468,1554,1576,1583,1592,1608 'word':928 'work':335,423 'would':1145,1203,1244 'write':30,83,362,776,807,840,915,1037,1060,1191,1526,1535,1557,1574,1581,1652 'written':879,1645,1677 'x':122 'x.y.z':1134,1173 'yes':322,330,334,747,1033,1036,1155,1158,1256,1259","prices":[{"id":"448805fe-b5a6-4328-80b2-53ab0745d10d","listingId":"f2b8e582-a72b-439d-9ce3-4308e51efa73","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":"2026-04-18T22:09:31.758Z"}],"sources":[{"listingId":"f2b8e582-a72b-439d-9ce3-4308e51efa73","source":"github","sourceId":"product-on-purpose/pm-skills/utility-pm-skill-iterate","sourceUrl":"https://github.com/product-on-purpose/pm-skills/tree/main/skills/utility-pm-skill-iterate","isPrimary":false,"firstSeenAt":"2026-04-18T22:09:31.758Z","lastSeenAt":"2026-05-02T12:54:13.495Z"}],"details":{"listingId":"f2b8e582-a72b-439d-9ce3-4308e51efa73","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"product-on-purpose","slug":"utility-pm-skill-iterate","github":{"repo":"product-on-purpose/pm-skills","stars":176,"topics":["agent-skills","ai-skills","claude-code","claude-desktop","openskills","product-management","skill-families","triple-diamond"],"license":"apache-2.0","html_url":"https://github.com/product-on-purpose/pm-skills","pushed_at":"2026-04-24T22:54:13Z","description":"Curated, plug-and-play product management skills for AI agents. 38 skills across Triple Diamond phases plus foundation (lean canvas, persona, meeting lifecycle family) and utility (create, validate, iterate). Templates, workflows, thread-aligned samples, CI-enforced skill-family contracts. Apache 2.0.","skill_md_sha":"1964ade14b26658a2b45ac3e5e765305e0a78bf4","skill_md_path":"skills/utility-pm-skill-iterate/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/product-on-purpose/pm-skills/tree/main/skills/utility-pm-skill-iterate"},"layout":"multi","source":"github","category":"pm-skills","frontmatter":{"name":"utility-pm-skill-iterate","license":"Apache-2.0","description":"Applies targeted improvements to an existing pm-skills skill based on feedback, validation reports, or convention changes. Reads current files, previews proposed changes, writes on confirmation, and suggests a version bump. Use when improving a skill after validation or feedback."},"skills_sh_url":"https://skills.sh/product-on-purpose/pm-skills/utility-pm-skill-iterate"},"updatedAt":"2026-05-02T12:54:13.495Z"}}