{"id":"f9176d37-ba8b-48c1-a6f0-cc23ce78b2c3","shortId":"CEpNN5","kind":"skill","title":"authoring","tagline":"Use when writing, completing, improving, or adapting SKILL.md and agents/*.md in a bundle-plugin — integrating external skills, filling scaffolded stubs, or rewriting for better triggering and token efficiency","description":"# Authoring Skill Content\n\n## Overview\n\nGuide the authoring of effective SKILL.md files, agent definitions (`agents/*.md`), and supporting resources within a bundle-plugin. Good content is the difference between skills that agents consistently find and follow — and ones that get ignored or misinterpreted.\n\n**Core principle:** Write for the agent's experience. Every instruction should be discoverable (good description), loadable (right size), and followable (clear, motivated instructions). Skills are the first-class source of truth in a bundle-plugin — docs and README must not contradict skill content (see `bundles-forge:auditing` — `references/source-of-truth-policy.md`).\n\n**Skill type:** Hybrid — follow the execution flow rigidly (Entry Detection → Path steps → Validation), but apply writing guidance flexibly based on context. The process is discipline-enforcing; the content decisions are pattern-based.\n\n**Announce at start:** \"I'm using the authoring skill to help [write / complete / improve / adapt] [skill / agent] content.\"\n\n## Entry Detection\n\nDetermine the authoring path from context:\n\n| Context | Path |\n|---------|------|\n| `skill-inventory` from blueprinting, or user requests writing new SKILL.md / agent definition from scratch | **Path 1: New Content** |\n| User provides an existing/external skill to add into a project, or asks to adapt a skill to match project conventions | **Path 2: Integrate Content** |\n| `scaffold-output` directories exist but SKILL.md body has < 10 non-empty lines | **Path 3: Complete Content** |\n| User provides existing in-project `skill-md` to improve, or `optimization-spec` from optimizing with specific changes | **Path 4: Improve Content** |\n\nWhen the target is an agent definition (`agents/*.md`) rather than a skill, follow the same path logic but use the agent authoring conventions from `references/agent-authoring-guide.md`.\n\n## Step 0: Project Context (all paths)\n\nBefore writing any content, verify scope and detect the project context:\n\n0. **Triage: should this be a skill?** — Before writing, verify the content warrants a skill:\n   - One-off, project-specific conventions → belongs in CLAUDE.md / AGENTS.md, not a skill\n   - Mechanically enforceable constraints (regex, schema validation) → automate with scripts, not documentation\n   - Standard practices well-documented by the platform → don't duplicate, cross-reference instead\n   - Skip this check when arriving from `bundles-forge:blueprinting` (triage already done during design)\n1. **Detect project root** — look for `skills/` directory + `package.json` above the target\n2. **If project exists**, read 2-3 existing SKILL.md files to extract the project's conventions:\n   - Description style (verb form after \"Use when\", scoping patterns)\n   - Section structure (which headings, in what order)\n   - Cross-reference format (`project:skill-name` prefix)\n   - Token efficiency patterns (use of `references/`, line counts)\n3. **If no project** (standalone authoring), use the conventions from `references/skill-writing-guide.md` directly\n\n## Path 1: New Content\n\nWrite skill or agent content from scratch.\n\n1. **Gather requirements** — from `skill-inventory` and design document context (blueprinting), user description, or conversation context. Identify: skill purpose, triggering scenarios, expected inputs/outputs, relationship to other skills. When a design document is available, leverage its project overview, target users, and use cases to write more targeted descriptions and overviews\n2. **Load writing guide** — read `references/skill-writing-guide.md` (frontmatter conventions, description rules, instruction style)\n3. **Write frontmatter** — `name` (kebab-case matching directory), `description` (start with \"Use when...\", under 250 chars, triggering conditions only)\n4. **Write Overview** — 1-3 sentences: what the skill does, core principle, skill type declaration (rigid / flexible / hybrid)\n5. **Write the process** — step-by-step execution flow. Use imperative form. Explain why, not just what. Include at least one concrete example per key instruction\n6. **Write Common Mistakes** — table of pitfalls and fixes (at least 3 entries)\n7. **Write Inputs / Outputs / Integration** — declare artifact IDs, calling relationships, and pairing skills\n8. **Check external dependencies:**\n   - **Declaration syntax** — if the skill references MCP tools or CLI commands, read `references/skill-writing-guide.md` \"External Tool References\" section for `allowed-tools` declaration, fallback patterns, and CLI vs MCP guidance\n   - **Prerequisites section** — if `allowed-tools` declares external CLI tools (not `git`, `python`, `node`, `npm`, `npx`, `bash`, or paths under `bin/`/`scripts/`), confirm the body includes a `## Prerequisites` section with a Tool/Check/Install table. Read `references/skill-writing-guide.md` \"Prerequisites Writing\" for the standard format\n9. **Evaluate token budget** — if body exceeds 300 lines, extract heavy sections to `references/`. Front-load critical instructions in the first ~5,000 tokens — after context compaction, only this portion survives\n10. **Run validation** (see Post-Action Validation below)\n\n## Path 2: Integrate Content\n\nAdapt an existing/external skill to fit a project's conventions and workflow.\n\n1. **Read the incoming skill** — understand its purpose, triggering scenarios, and current structure\n2. **Read project conventions** (from Step 0) — identify gaps between the incoming skill and project patterns\n3. **Load writing guide** — read `references/skill-writing-guide.md` (frontmatter conventions, description rules, instruction style)\n4. **Adapt frontmatter** — rewrite `description` to match project style (verb form, scoping), ensure `name` follows project kebab-case convention\n5. **Adapt body structure** — restructure sections to match project patterns (Overview, Process, Common Mistakes, Inputs/Outputs/Integration)\n6. **Wire Integration section** — add cross-references to existing project skills, declare Inputs/Outputs that connect to the project's workflow graph\n7. **Adapt instruction style** — align with project conventions (imperative form, reasoning over directives, example density)\n8. **Evaluate token budget** — ensure the adapted skill fits project token norms\n9. **Run validation** (see Post-Action Validation below)\n\n## Path 3: Complete Content\n\nFill in scaffolded skill stubs with substantive content.\n\n1. **Read scaffold structure** — identify which directories and stub files exist\n2. **Read project conventions** (from Step 0) — match the style of already-completed skills\n3. **Load writing guide** — read `references/skill-writing-guide.md` (frontmatter conventions, description rules, instruction style)\n4. **Complete frontmatter** — fill in `description` (triggering conditions, \"Use when...\", under 250 chars). If `name` is already set, verify it matches directory name\n5. **Write Overview** — core principle + skill type declaration\n6. **Write the process** — step-by-step flow based on the skill's intended purpose from the design document or user context\n7. **Write remaining sections** — Common Mistakes, Inputs/Outputs/Integration\n8. **Create supporting resources** if needed — `references/` for heavy content, `assets/` for templates. Read `references/skill-writing-guide.md` \"Supporting Resources\" section for thresholds. Front-load critical instructions in the first ~5,000 tokens — after context compaction, only this portion survives\n9. **Run validation** (see Post-Action Validation below)\n\n## Path 4: Improve Content\n\nEnhance existing in-project content based on user feedback or optimization specs.\n\n1. **Read existing content** — understand current structure, strengths, and gaps\n2. **Identify improvement targets** — from user request, `optimization-spec`, or self-diagnosis:\n   - Description not triggering reliably → rewrite following description rules\n   - Token budget exceeded → extract to `references/`, cut redundancy, front-load critical instructions in the first ~5,000 tokens\n   - Missing sections → add Overview, Common Mistakes, Inputs/Outputs\n   - Instruction style issues → reframe directives as reasoning, add examples\n3. **Load writing guide** if needed — read `references/skill-writing-guide.md` (frontmatter conventions, description rules, instruction style)\n4. **Apply changes** — make targeted improvements. Preserve what works; don't rewrite content that already follows conventions\n5. **Verify Integration section** — ensure cross-references still resolve after changes, artifact IDs match consuming skills\n6. **Run validation** (see Post-Action Validation below)\n\n## Post-Action Validation\n\nAfter completing any path, validate the authored content:\n\n1. **Run lint** — `bundles-forge audit-skill <skill-directory>` on each authored/modified skill\n   - **If audit script is unavailable:** review against `references/quality-checklist.md` manually\n2. **Act on findings** — fix Critical immediately, fix Warning if straightforward, report Info as suggestions\n3. **Report results** — tell the user/calling skill what was validated and any remaining warnings\n\n## Common Mistakes\n\n| Mistake | Fix |\n|---------|-----|\n| Description summarizes workflow | Describe triggering conditions only — agents shortcut to description |\n| Piling on MUST/ALWAYS/NEVER | Explain why the rule exists — understanding beats compliance |\n| Putting everything in SKILL.md | Extract heavy content (100+ lines) to `references/`; keep body under 500 lines |\n| No examples, only abstract rules | Add at least one concrete example per key instruction |\n| Writing for humans, not agents | Use imperative form, clear structure, explicit output formats |\n| Description too narrow | Be pushy — list related scenarios, edge cases, alternative phrasings |\n| Description too broad | Scope to the right context (e.g., \"bundle-plugins\" not just \"any project\") |\n| Skipping project conventions | Always read existing skills first when working in an established project |\n| Not wiring Integration section | Every skill needs Called by / Calls / Pairs with to connect to the workflow graph |\n| No defensive instructions for rigid skills | For rigid/hybrid skills, add explicit loophole closers, rationalization tables, and red-flag lists — see Defensive Writing in `references/skill-writing-guide.md` |\n| Forgetting validation | Always run `bundles-forge audit-skill` after authoring — catches issues before they propagate |\n\n## Inputs\n\n- `skill-inventory` (optional) — list of skills and agent definitions to write, from `bundles-forge:blueprinting` design document\n- `scaffold-output` (optional) — scaffolded skill directories needing content (from blueprinting pipeline or standalone scaffolding)\n- `skill-md` (optional) — existing SKILL.md or agent definition to improve, complete, or adapt\n- `optimization-spec` (optional) — specific content changes requested by `bundles-forge:optimizing` (e.g., rewrite description, reduce tokens, restructure sections)\n\n## Outputs\n\n- `skill-content` — completed or improved SKILL.md files following authoring conventions (frontmatter, description, body structure, token efficiency)\n- `agent-content` (optional) — completed `agents/*.md` definitions following agent authoring conventions\n\n## Integration\n\n**Called by:**\n- **bundles-forge:blueprinting** — dispatched as Phase 2 (content writing) in the blueprinting pipeline (write all skills + agent definitions)\n- **bundles-forge:optimizing** — content rewriting for description, token, and structural improvements\n- User directly — for standalone SKILL.md or agent definition authoring\n\n**Pairs with:**\n- **bundles-forge:scaffolding** — scaffolding generates directory structure, authoring fills it with content\n- **bundles-forge:auditing** — auditing validates authored content for quality, cross-references, and security","tags":["authoring","bundles","forge","odradekai","agent-skills","bundle-plugin","claude-code","claude-plugin","claude-skills","cursor-plugin"],"capabilities":["skill","source-odradekai","skill-authoring","topic-agent-skills","topic-bundle-plugin","topic-claude-code","topic-claude-plugin","topic-claude-skills","topic-cursor-plugin"],"categories":["bundles-forge"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/OdradekAI/bundles-forge/authoring","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add OdradekAI/bundles-forge","source_repo":"https://github.com/OdradekAI/bundles-forge","install_from":"skills.sh"}},"qualityScore":"0.554","qualityRationale":"deterministic score 0.55 from registry signals: · indexed on github topic:agent-skills · 208 github stars · SKILL.md body (11,826 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":"2026-05-02T12:54:05.609Z","embedding":null,"createdAt":"2026-04-18T22:12:11.071Z","updatedAt":"2026-05-02T12:54:05.609Z","lastSeenAt":"2026-05-02T12:54:05.609Z","tsv":"'-3':404,556 '0':300,316,773,917 '000':720,1028,1112 '1':204,386,460,470,555,754,900,1063,1199 '10':240,729 '100':1283 '2':228,398,403,520,739,767,911,1073,1221,1530 '250':547,949 '3':246,447,532,608,783,889,926,1130,1236 '300':704 '4':270,552,795,938,1047,1144 '5':570,719,815,961,1027,1111,1161 '500':1290 '6':597,830,969,1178 '7':610,852,992 '8':623,867,999 '9':697,879,1037 'abstract':1295 'act':1222 'action':735,885,1043,1184,1189 'adapt':8,174,220,742,796,816,853,873,1469 'add':213,834,1116,1128,1297,1388 'agent':11,43,45,63,80,176,199,278,280,294,466,1261,1310,1430,1463,1509,1513,1517,1540,1560 'agent-cont':1508 'agents.md':341 'align':856 'allow':646,660 'allowed-tool':645,659 'alreadi':382,923,954,1158 'already-complet':922 'altern':1329 'alway':1350,1406 'announc':160 'appli':140,1145 'arriv':375 'artifact':616,1173 'ask':218 'asset':1009 'audit':124,1206,1213,1412,1581,1582 'audit-skil':1205,1411 'author':1,32,38,167,182,295,452,1197,1415,1500,1518,1562,1573,1584 'authored/modified':1210 'autom':351 'avail':503 'base':144,159,978,1056 'bash':672 'beat':1274 'belong':338 'better':27 'bin':676 'blueprint':192,380,481,1438,1451,1526,1535 'bodi':238,680,702,817,1288,1504 'broad':1333 'budget':700,870,1096 'bundl':16,53,110,122,378,1203,1341,1409,1436,1480,1524,1543,1566,1579 'bundle-plugin':15,52,109,1340 'bundles-forg':121,377,1202,1408,1435,1479,1523,1542,1565,1578 'call':618,1368,1370,1521 'case':512,538,813,1328 'catch':1416 'chang':268,1146,1172,1476 'char':548,950 'check':373,624 'class':103 'claude.md':340 'clear':95,1314 'cli':636,652,664 'closer':1391 'command':637 'common':599,827,996,1118,1250 'compact':724,1032 'complet':5,172,247,890,924,939,1192,1467,1494,1512 'complianc':1275 'concret':592,1301 'condit':550,945,1259 'confirm':678 'connect':845,1374 'consist':64 'constraint':347 'consum':1176 'content':34,56,119,154,177,206,230,248,272,308,327,462,467,741,891,899,1008,1049,1055,1066,1156,1198,1282,1449,1475,1493,1510,1531,1546,1577,1585 'context':146,185,186,302,315,480,486,723,991,1031,1338 'contradict':117 'convent':226,296,337,413,455,527,751,770,790,814,859,914,933,1139,1160,1349,1501,1519 'convers':485 'core':75,562,964 'count':446 'creat':1000 'critic':714,1022,1106,1226 'cross':368,431,836,1167,1589 'cross-refer':367,430,835,1166,1588 'current':765,1068 'cut':1101 'decis':155 'declar':566,615,627,648,662,842,968 'defens':1380,1400 'definit':44,200,279,1431,1464,1515,1541,1561 'densiti':866 'depend':626 'describ':1257 'descript':89,414,483,517,528,541,791,799,934,943,1087,1093,1140,1254,1264,1319,1331,1485,1503,1549 'design':385,478,500,987,1439 'detect':135,179,312,387 'determin':180 'diagnosi':1086 'differ':59 'direct':458,864,1125,1555 'directori':234,393,540,906,959,1447,1571 'disciplin':151 'discipline-enforc':150 'discover':87 'dispatch':1527 'doc':112 'document':355,360,479,501,988,1440 'done':383 'duplic':366 'e.g':1339,1483 'edg':1327 'effect':40 'effici':31,440,1507 'empti':243 'enforc':152,346 'enhanc':1050 'ensur':807,871,1165 'entri':134,178,609 'establish':1359 'evalu':698,868 'everi':83,1365 'everyth':1277 'exampl':593,865,1129,1293,1302 'exceed':703,1097 'execut':131,578 'exist':235,251,401,405,839,910,1051,1065,1272,1352,1460 'existing/external':210,744 'expect':492 'experi':82 'explain':583,1268 'explicit':1316,1389 'extern':19,625,640,663 'extract':409,706,1098,1280 'fallback':649 'feedback':1059 'file':42,407,909,1498 'fill':21,892,941,1574 'find':65,1224 'first':102,718,1026,1110,1354 'first-class':101 'fit':747,875 'fix':605,1225,1228,1253 'flag':1397 'flexibl':143,568 'flow':132,579,977 'follow':67,94,129,286,809,1092,1159,1499,1516 'forg':123,379,1204,1410,1437,1481,1525,1544,1567,1580 'forget':1404 'form':417,582,805,861,1313 'format':433,696,1318 'front':712,1020,1104 'front-load':711,1019,1103 'frontmatt':526,534,789,797,932,940,1138,1502 'gap':775,1072 'gather':471 'generat':1570 'get':71 'git':667 'good':55,88 'graph':851,1378 'guid':36,523,786,929,1133 'guidanc':142,655 'head':426 'heavi':707,1007,1281 'help':170 'human':1308 'hybrid':128,569 'id':617,1174 'identifi':487,774,904,1074 'ignor':72 'immedi':1227 'imper':581,860,1312 'improv':6,173,259,271,1048,1075,1149,1466,1496,1553 'in-project':252,1052 'includ':588,681 'incom':757,778 'info':1233 'input':612,1421 'inputs/outputs':493,843,1120 'inputs/outputs/integration':829,998 'instead':370 'instruct':84,97,530,596,715,793,854,936,1023,1107,1121,1142,1305,1381 'integr':18,229,614,740,832,1163,1363,1520 'intend':983 'inventori':190,476,1424 'issu':1123,1417 'kebab':537,812 'kebab-cas':536,811 'keep':1287 'key':595,1304 'least':590,607,1299 'leverag':504 'line':244,445,705,1284,1291 'lint':1201 'list':1324,1398,1426 'load':521,713,784,927,1021,1105,1131 'loadabl':90 'logic':290 'look':390 'loophol':1390 'm':164 'make':1147 'manual':1220 'match':224,539,801,822,918,958,1175 'mcp':633,654 'md':12,46,257,281,1458,1514 'mechan':345 'misinterpret':74 'miss':1114 'mistak':600,828,997,1119,1251,1252 'motiv':96 'must':115 'must/always/never':1267 'name':437,535,808,952,960 'narrow':1321 'need':1004,1135,1367,1448 'new':197,205,461 'node':669 'non':242 'non-empti':241 'norm':878 'npm':670 'npx':671 'one':69,332,591,1300 'one-off':331 'optim':262,265,1061,1081,1471,1482,1545 'optimization-spec':261,1080,1470 'option':1425,1444,1459,1473,1511 'order':429 'output':233,613,1317,1443,1490 'overview':35,507,519,554,825,963,1117 'package.json':394 'pair':621,1371,1563 'path':136,183,187,203,227,245,269,289,304,459,674,738,888,1046,1194 'pattern':158,422,441,650,782,824 'pattern-bas':157 'per':594,1303 'phase':1529 'phrase':1330 'pile':1265 'pipelin':1452,1536 'pitfal':603 'platform':363 'plugin':17,54,111,1342 'portion':727,1035 'post':734,884,1042,1183,1188 'post-act':733,883,1041,1182,1187 'practic':357 'prefix':438 'prerequisit':656,683,691 'preserv':1150 'principl':76,563,965 'process':148,573,826,972 'project':216,225,254,301,314,335,388,400,411,434,450,506,749,769,781,802,810,823,840,848,858,876,913,1054,1346,1348,1360 'project-specif':334 'propag':1420 'provid':208,250 'purpos':489,761,984 'pushi':1323 'put':1276 'python':668 'qualiti':1587 'rather':282 'ration':1392 'read':402,524,638,689,755,768,787,901,912,930,1012,1064,1136,1351 'readm':114 'reason':862,1127 'red':1396 'red-flag':1395 'reduc':1486 'redund':1102 'refer':369,432,444,632,642,710,837,1005,1100,1168,1286,1590 'references/agent-authoring-guide.md':298 'references/quality-checklist.md':1219 'references/skill-writing-guide.md':457,525,639,690,788,931,1013,1137,1403 'references/source-of-truth-policy.md':125 'refram':1124 'regex':348 'relat':1325 'relationship':494,619 'reliabl':1090 'remain':994,1248 'report':1232,1237 'request':195,1079,1477 'requir':472 'resolv':1170 'resourc':49,1002,1015 'restructur':819,1488 'result':1238 'review':1217 'rewrit':25,798,1091,1155,1484,1547 'right':91,1337 'rigid':133,567,1383 'rigid/hybrid':1386 'root':389 'rule':529,792,935,1094,1141,1271,1296 'run':730,880,1038,1179,1200,1407 'scaffold':22,232,894,902,1442,1445,1455,1568,1569 'scaffold-output':231,1441 'scenario':491,763,1326 'schema':349 'scope':310,421,806,1334 'scratch':202,469 'script':353,677,1214 'section':423,643,657,684,708,820,833,995,1016,1115,1164,1364,1489 'secur':1592 'see':120,732,882,1040,1181,1399 'self':1085 'self-diagnosi':1084 'sentenc':557 'set':955 'shortcut':1262 'size':92 'skill':20,33,61,98,118,126,168,175,189,211,222,256,285,322,330,344,392,436,464,475,488,497,560,564,622,631,745,758,779,841,874,895,925,966,981,1177,1207,1211,1242,1353,1366,1384,1387,1413,1423,1428,1446,1457,1492,1539 'skill-authoring' 'skill-cont':1491 'skill-inventori':188,474,1422 'skill-md':255,1456 'skill-nam':435 'skill.md':9,41,198,237,406,1279,1461,1497,1558 'skip':371,1347 'sourc':104 'source-odradekai' 'spec':263,1062,1082,1472 'specif':267,336,1474 'standalon':451,1454,1557 'standard':356,695 'start':162,542 'step':137,299,575,577,772,916,974,976 'step-by-step':574,973 'still':1169 'straightforward':1231 'strength':1070 'structur':424,766,818,903,1069,1315,1505,1552,1572 'stub':23,896,908 'style':415,531,794,803,855,920,937,1122,1143 'substant':898 'suggest':1235 'summar':1255 'support':48,1001,1014 'surviv':728,1036 'syntax':628 'tabl':601,688,1393 'target':275,397,508,516,1076,1148 'tell':1239 'templat':1011 'threshold':1018 'token':30,439,699,721,869,877,1029,1095,1113,1487,1506,1550 'tool':634,641,647,661,665 'tool/check/install':687 'topic-agent-skills' 'topic-bundle-plugin' 'topic-claude-code' 'topic-claude-plugin' 'topic-claude-skills' 'topic-cursor-plugin' 'triag':317,381 'trigger':28,490,549,762,944,1089,1258 'truth':106 'type':127,565,967 'unavail':1216 'understand':759,1067,1273 'use':2,165,292,419,442,453,511,544,580,946,1311 'user':194,207,249,482,509,990,1058,1078,1554 'user/calling':1241 'valid':138,350,731,736,881,886,1039,1044,1180,1185,1190,1195,1245,1405,1583 'verb':416,804 'verifi':309,325,956,1162 'vs':653 'warn':1229,1249 'warrant':328 'well':359 'well-docu':358 'wire':831,1362 'within':50 'work':1152,1356 'workflow':753,850,1256,1377 'write':4,77,141,171,196,306,324,463,514,522,533,553,571,598,611,692,785,928,962,970,993,1132,1306,1401,1433,1532,1537","prices":[{"id":"f5c0a02b-1154-4932-b106-814c6da82a15","listingId":"f9176d37-ba8b-48c1-a6f0-cc23ce78b2c3","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"OdradekAI","category":"bundles-forge","install_from":"skills.sh"},"createdAt":"2026-04-18T22:12:11.071Z"}],"sources":[{"listingId":"f9176d37-ba8b-48c1-a6f0-cc23ce78b2c3","source":"github","sourceId":"OdradekAI/bundles-forge/authoring","sourceUrl":"https://github.com/OdradekAI/bundles-forge/tree/main/skills/authoring","isPrimary":false,"firstSeenAt":"2026-04-18T22:12:11.071Z","lastSeenAt":"2026-05-02T12:54:05.609Z"}],"details":{"listingId":"f9176d37-ba8b-48c1-a6f0-cc23ce78b2c3","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"OdradekAI","slug":"authoring","github":{"repo":"OdradekAI/bundles-forge","stars":208,"topics":["agent-skills","bundle-plugin","claude-code","claude-plugin","claude-skills","cursor-plugin"],"license":"apache-2.0","html_url":"https://github.com/OdradekAI/bundles-forge","pushed_at":"2026-04-27T02:13:58Z","description":"An agentic skills framework & bundle-plugin engineering toolkit that works.","skill_md_sha":"08f68eecac18056defc7aaf1d282cfd4b02ee699","skill_md_path":"skills/authoring/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/OdradekAI/bundles-forge/tree/main/skills/authoring"},"layout":"multi","source":"github","category":"bundles-forge","frontmatter":{"name":"authoring","description":"Use when writing, completing, improving, or adapting SKILL.md and agents/*.md in a bundle-plugin — integrating external skills, filling scaffolded stubs, or rewriting for better triggering and token efficiency"},"skills_sh_url":"https://skills.sh/OdradekAI/bundles-forge/authoring"},"updatedAt":"2026-05-02T12:54:05.609Z"}}