{"id":"8a2c521e-7226-4772-95f9-fafec8dc610c","shortId":"3fqsuw","kind":"skill","title":"skill-optimizer","tagline":"Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent.","description":"## When to Use This Skill\n\n- Use when skills are not triggering as expected or seem broken\n- Use when you want to audit and improve your skill library's quality\n- Use when you want to understand which skills are underperforming or wasting context tokens\n\n## Rules\n\n- **Read-only**: never modify skill files. Only output report.\n- **All 8 dimensions**: do not skip any. If data is insufficient, report \"N/A — insufficient session data\" rather than omitting.\n- **Quantify**: \"you had 12 research tasks last week but the skill never triggered\" beats \"you often do research\".\n- **Suggest, don't prescribe**: give specific wording suggestions for description improvements, but frame as suggestions.\n- **Show evidence**: for undertrigger claims, quote the actual user message that should have triggered the skill.\n- **Evidence-based suggestions**: when suggesting description rewrites, cite the specific research finding that motivates the change (e.g., \"front-load trigger keywords — MCP study shows 3.6x selection rate improvement\").\n\n## Overview\n\nAnalyze skills using **historical session data + static quality checks**, output a diagnostic report with P0/P1/P2 prioritized fixes. Scores each skill on a 5-point composite scale across 8 dimensions.\n\nCSO (Claude/Agent Search Optimization) = writing skill descriptions so agents select the right skill at the right time. This skill checks for CSO violations.\n\n## Usage\n\n- `/optimize-skill` → scan all skills\n- `/optimize-skill my-skill` → single skill\n- `/optimize-skill skill-a skill-b` → multiple specified skills\n\n## Data Sources\n\nAuto-detect the current agent platform and scan the corresponding paths:\n\n| Source | Claude Code | Codex | Shared |\n|--------|------------|-------|--------|\n| Session transcripts | `~/.claude/projects/**/*.jsonl` | `~/.codex/sessions/**/*.jsonl` | — |\n| Skill files | `~/.claude/skills/*/SKILL.md` | `~/.codex/skills/*/SKILL.md` | `~/.agents/skills/*/SKILL.md` |\n\n**Platform detection:** Check which directories exist. Scan all available sources — a user may have both Claude Code and Codex installed.\n\n## Workflow\n\n```\nIdentify target skills\n        ↓\nCollect session data (python3 scripts scan JSONL transcripts)\n        ↓\nRun 8 analysis dimensions\n        ↓\nCompute composite scores\n        ↓\nOutput report with P0/P1/P2\n```\n\n### Step 1: Identify Target Skills\n\nScan skill directories in order: `~/.claude/skills/`, `~/.codex/skills/`, `~/.agents/skills/`. Deduplicate by skill name (same name in multiple locations = same skill). For each, read `SKILL.md` and extract:\n- name, description (from YAML frontmatter)\n- trigger keywords (from description field)\n- defined workflow steps (Step 1/2/3... or ### sections under Workflow)\n- word count\n\nIf user specified skill names, filter to only those.\n\n### Step 2: Collect Session Data\n\nUse python3 scripts via Bash to scan session JSONL files. Extract:\n\n**Claude Code sessions** (`~/.claude/projects/**/*.jsonl`):\n- `Skill` tool_use calls (which skills were invoked)\n- User messages (full text)\n- Assistant messages after skill invocation (for workflow tracking)\n- User messages after skill invocation (for reaction analysis)\n\n**Codex sessions** (`~/.codex/sessions/**/*.jsonl`):\n- `session_meta` events → extract `base_instructions` for skill loading evidence\n- `response_item` events → assistant outputs (workflow tracking)\n- `event_msg` events → tool execution and skill-related events\n- User messages from `turn_context` events (for reaction analysis)\n\n**Note:** Codex injects skills via context rather than explicit `Skill` tool calls. Skill loading (present in `base_instructions`) does NOT equal active invocation. To detect actual use, search for skill-specific workflow markers (step headers, output formats) in `response_item` content within that session. A skill is \"invoked\" only if the agent produced output following the skill's defined workflow.\n\n**Aggregated:**\n- Per-skill: invocation count, trigger keyword match count\n- Per-skill: user reaction sentiment after invocation\n- Per-skill: workflow step completion markers\n\n### Step 3: Run 8 Analysis Dimensions\n\n**You MUST run ALL 8 dimensions.** The baseline behavior without this skill is to skip dimensions 4.2, 4.3, 4.5b, and 4.8. These are the most valuable dimensions — do not skip them.\n\n#### 4.1 Trigger Rate\n\nCount how many times each skill was actually invoked vs how many times its trigger keywords appeared in user messages.\n\n**Claude Code:** count `Skill` tool_use calls in transcripts.\n**Codex:** count sessions where the agent produced output following the skill's workflow markers (not merely loaded in context).\n\n**Diagnose:**\n- Never triggered → skill may be useless or trigger words wrong\n- Keywords match >> actual invocations → undertrigger problem, description needs work\n- High frequency → core skill, worth optimizing\n\n#### 4.2 Post-Invocation User Reaction\n\n**This dimension is critical and easy to skip. Do not skip it.**\n\nAfter a skill is invoked in a session, read the user's next 3 messages. Classify:\n- **Negative**: \"no\", \"wrong\", \"never mind\", \"not what I wanted\", user interrupts\n- **Correction**: user re-describes their intent, manually overrides skill output\n- **Positive**: \"good\", \"ok\", \"continue\", \"nice\", user follows the workflow\n- **Silent switch**: user changes topic entirely (likely false positive trigger)\n\nReport per-skill satisfaction rate.\n\n#### 4.3 Workflow Completion Rate\n\n**This dimension is critical and easy to skip. Do not skip it.**\n\nFor each skill invocation found in session data:\n1. Extract the skill's defined steps from SKILL.md\n2. Search the assistant messages in that session for step markers (Step N, specific output formats defined in the skill)\n3. Calculate: how far did execution get?\n\nReport: `{skill-name} (N steps): avg completed Step X/N (Y%)`\n\nIf a specific step is frequently where execution stops, flag it.\n\n#### 4.4 Static Quality Analysis\n\nCheck each SKILL.md against these 14 rules:\n\n| Check | Pass Criteria |\n|-------|--------------|\n| Frontmatter format | Only `name` + `description`, total < 1024 chars |\n| Name format | Letters, numbers, hyphens only |\n| Description trigger | Starts with \"Use when...\" or has explicit trigger conditions |\n| Description workflow leak | Description does NOT summarize the skill's workflow steps (CSO violation) |\n| Description pushiness | Description actively claims scenarios where it should be used, not just passive |\n| Overview section | Present |\n| Rules section | Present |\n| MUST/NEVER density | Count ALL-CAPS directive words; >5 per 100 words = flag |\n| Word count | < 500 words (flag if over) |\n| Narrative anti-pattern | No \"In session X, we found...\" storytelling |\n| YAML quoting safety | description containing `: ` must be wrapped in double quotes |\n| Critical info position | Core trigger conditions and primary actions must be in the first 20% of SKILL.md |\n| Description 250-char check | Primary trigger keywords must appear within the first 250 characters of description |\n| Trigger condition count | ≤ 2 trigger conditions in description is ideal |\n\n#### 4.5a False Positive Rate (Overtrigger)\n\nSkill was invoked but user immediately rejected or ignored it.\n\n#### 4.5b Undertrigger Detection\n\n**This is the highest-value dimension.** For each skill, extract its **capability keywords** (not just trigger keywords — what the skill CAN do). Then scan user messages for tasks that match those capabilities but where the skill was NOT invoked.\n\nReport: which user messages SHOULD have triggered the skill but didn't, and suggest description improvements.\n\n**Compounding Risk Assessment:**\nFor skills with chronic undertriggering (0 triggers across 5+ sessions where relevant tasks appeared), flag as \"compounding risk\" — undertriggered skills cannot self-improve through usage feedback, causing the gap to widen over time. Recommend immediate description rewrite as P0.\n\n#### 4.6 Cross-Skill Conflicts\n\nCompare all skill pairs:\n- Trigger keyword overlap (same keywords in two descriptions)\n- Workflow overlap (two skills teach similar processes)\n- Contradictory guidance\n\n#### 4.7 Environment Consistency\n\nFor each skill, extract referenced:\n- File paths → check if they exist (`test -e`)\n- CLI tools → check if installed (`which`)\n- Directories → check if they exist\n\nFlag any broken references.\n\n#### 4.8 Token Economics\n\n**This dimension is critical and easy to skip. Do not skip it.**\n\nFor each skill:\n- Word count (from Step 1)\n- Trigger frequency (from 4.1)\n- Cost-effectiveness = trigger count / word count\n- Flag: large + never-triggered skills as candidates for removal or compression\n\n**Progressive Disclosure Tier Check:**\nEvaluate each skill against the 3-tier loading model:\n- Tier 1 (frontmatter): ~100 tokens. Check: is description ≤ 1024 chars?\n- Tier 2 (SKILL.md body): <500 lines recommended. Check: word count.\n- Tier 3 (reference files): loaded on demand. Check: does skill use reference files for detailed content, or cram everything into SKILL.md?\n\nFlag skills that put 500+ words in SKILL.md without using reference files as \"poor progressive disclosure\".\n\n### Step 4: Composite Score\n\nRate each skill on a 5-point scale:\n\n| Score | Meaning |\n|-------|---------|\n| 5 | Healthy: high trigger rate, positive reactions, complete workflows, clean static |\n| 4 | Good: minor issues in 1-2 dimensions |\n| 3 | Needs attention: significant gap in 1 dimension or minor gaps in 3+ |\n| 2 | Problematic: never triggered, or negative user reactions, or major static issues |\n| 1 | Broken: doesn't work, references missing, or fundamentally misaligned |\n\n**Scored dimensions** (weighted average):\n- Trigger rate: 25%\n- User reaction: 20%\n- Workflow completion: 15%\n- Static quality: 15%\n- Undertrigger: 15%\n- Token economics: 10%\n\n**Qualitative dimensions** (reported but not scored):\n- 4.5a Overtrigger: reported as count + examples\n- 4.6 Cross-Skill Conflicts: reported as conflict pairs\n- 4.7 Environment Consistency: reported as pass/fail per reference\n\n## Report Format\n\n```markdown\n# Skill Optimization Report\n**Date**: {date}\n**Scope**: {all / specified skills}\n**Session data**: {N} sessions, {date range}\n\n## Overview\n| Skill | Triggers | Reaction | Completion | Static | Undertrigger | Token | Score |\n|-------|----------|----------|------------|--------|--------------|-------|-------|\n| example-skill | 2 | 100% | 86% | B+ | 1 miss | 486w | 4/5 |\n\n## P0 Fixes (blocking usage)\n1. ...\n\n## P1 Improvements (better experience)\n1. ...\n\n## P2 Optional Optimizations\n1. ...\n\n## Per-Skill Diagnostics\n### {skill-name}\n#### 4.1 Trigger Rate\n...\n#### 4.2 User Reaction\n...\n(all 8 dimensions)\n```\n\n## Research Background\n\nThe analysis dimensions in this report are grounded in the following research:\n- **Undertrigger detection**: Memento-Skills (arXiv:2603.18743) — skills as structured files require accurate routing; unrouted skills cannot self-improve via the read-write learning loop\n- **Description quality**: MCP Description Quality (arXiv:2602.18914) — well-written descriptions achieve 72% tool selection rate vs. 20% random baseline (3.6x improvement)\n- **Information position**: Lost in the Middle (Liu et al., TACL 2024) — U-shaped LLM attention curve\n- **Format impact**: He et al. (arXiv:2411.10541) — format changes alone can cause 9-40% performance variance\n- **Instruction compliance**: IFEval (arXiv:2311.07911) — LLMs struggle with multi-constraint prompts\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.","tags":["skill","optimizer","antigravity","awesome","skills","sickn33","agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows"],"capabilities":["skill","source-sickn33","skill-skill-optimizer","topic-agent-skills","topic-agentic-skills","topic-ai-agent-skills","topic-ai-agents","topic-ai-coding","topic-ai-workflows","topic-antigravity","topic-antigravity-skills","topic-claude-code","topic-claude-code-skills","topic-codex-cli","topic-codex-skills"],"categories":["antigravity-awesome-skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-optimizer","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add sickn33/antigravity-awesome-skills","source_repo":"https://github.com/sickn33/antigravity-awesome-skills","install_from":"skills.sh"}},"qualityScore":"0.700","qualityRationale":"deterministic score 0.70 from registry signals: · indexed on github topic:agent-skills · 34515 github stars · SKILL.md body (11,730 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":"2026-04-22T12:51:47.041Z","embedding":null,"createdAt":"2026-04-18T21:45:00.471Z","updatedAt":"2026-04-22T12:51:47.041Z","lastSeenAt":"2026-04-22T12:51:47.041Z","tsv":"'-2':1329 '-40':1579 '/.agents/skills':290,347 '/.claude/projects':280,414 '/.claude/skills':286,345 '/.codex/sessions':282,446 '/.codex/skills':288,346 '/optimize-skill':239,243,249 '/skill.md':287,289,291 '0':1090 '1':336,790,1204,1242,1328,1337,1356,1451,1459,1464,1468 '1/2/3':379 '10':1386 '100':931,1244,1448 '1024':868,1249 '12':108 '14':857 '15':1378,1381,1383 '2':396,799,999,1252,1344,1447 '20':977,1375,1543 '2024':1559 '2311.07911':1586 '2411.10541':1572 '25':1372 '250':981,992 '2602.18914':1532 '2603.18743':1505 '3':571,716,819,1237,1262,1331,1343 '3.6':180,1546 '4':1299,1323 '4.1':608,1208,1476 '4.2':592,685,1479 '4.3':593,766 '4.4':848 '4.5':594,1006,1022,1393 '4.6':1125,1400 '4.7':1151,1409 '4.8':597,1182 '4/5':1454 '486w':1453 '5':208,929,1093,1307,1312 '500':936,1255,1286 '72':1538 '8':87,213,325,573,580,1483 '86':1449 '9':1578 'accur':1511 'achiev':1537 'across':212,1092 'action':971 'activ':505,904 'actual':145,509,618,672 'agent':7,27,31,223,266,536,645 'aggreg':545 'al':1557,1570 'all-cap':924 'alon':1575 'analysi':19,326,443,483,574,851,1488 'analyz':186 'anti':943 'anti-pattern':942 'appear':627,988,1098 'arxiv':1504,1531,1571,1585 'ask':1627 'assess':1084 'assist':428,461,802 'attent':1333,1564 'audit':53 'auto':262 'auto-detect':261 'avail':300 'averag':1369 'avg':832 'b':255,595,1023,1450 'back':17 'background':1486 'base':156,452,500 'baselin':583,1545 'bash':404 'beat':118 'behavior':584 'better':1462 'block':1457 'bodi':1254 'boundari':1635 'broken':47,1180,1357 'calcul':820 'call':419,495,637 'candid':1223 'cannot':1105,1515 'cap':926 'capabl':1038,1058 'caus':1112,1577 'chang':170,753,1574 'char':869,982,1250 'charact':993 'check':194,234,294,852,859,983,1161,1169,1174,1231,1246,1258,1268 'chronic':1088 'cite':162 'claim':142,905 'clarif':1629 'classifi':718 'claud':22,274,307,411,631 'claude/agent':216 'clean':1321 'clear':1602 'cli':1167 'code':23,275,308,412,632 'codex':24,276,310,444,485,640 'collect':316,397 'compar':1130 'compat':30 'complet':568,768,833,1319,1377,1439 'complianc':1583 'composit':210,329,1300 'compound':1082,1101 'compress':1227 'comput':328 'condit':886,968,997,1001 'conflict':1129,1404,1407 'consist':1153,1411 'constraint':1592 'contain':956 'content':525,1276 'context':73,479,489,658 'continu':744 'contradictori':1149 'core':681,966 'correct':730 'correspond':271 'cost':1210 'cost-effect':1209 'count':385,550,554,611,633,641,923,935,998,1201,1213,1215,1260,1398 'cram':1278 'criteria':861,1638 'critic':694,773,963,1188 'cross':1127,1402 'cross-skil':1126,1401 'cso':215,236,899 'current':265 'curv':1565 'data':13,94,101,191,259,318,399,789,1430 'date':1423,1424,1433 'dedupl':348 'defin':375,543,795,815 'demand':1267 'densiti':922 'describ':734,1606 'descript':132,160,221,366,373,676,866,876,887,890,901,903,955,980,995,1003,1080,1121,1141,1248,1526,1529,1536 'detail':1275 'detect':263,293,508,1025,1500 'diagnos':4,659 'diagnost':197,1472 'didn':1076 'dimens':88,214,327,575,581,591,603,692,771,1032,1186,1330,1338,1367,1388,1484,1489 'direct':927 'directori':296,342,1173 'disclosur':1229,1297 'doesn':1358 'doubl':961 'e':1166 'e.g':171 'easi':696,775,1190 'econom':1184,1385 'effect':1211 'entir':755 'environ':1152,1410,1618 'environment-specif':1617 'equal':504 'et':1556,1569 'evalu':1232 'event':450,460,465,467,474,480 'everyth':1279 'evid':139,155,457 'evidence-bas':154 'exampl':1399,1445 'example-skil':1444 'execut':469,824,844 'exist':297,1164,1177 'expect':44 'experi':1463 'expert':1623 'explicit':492,884 'extract':364,410,451,791,1036,1157 'fals':757,1008 'far':822 'feedback':1111 'field':374 'file':82,285,409,1159,1264,1273,1293,1509 'filter':391 'find':166 'first':976,991 'fix':202,1456 'flag':846,933,938,1099,1178,1216,1282 'follow':539,648,747,1497 'format':521,814,863,871,1418,1566,1573 'found':786,950 'frame':135 'frequenc':680,1206 'frequent':842 'front':173 'front-load':172 'frontmatt':369,862,1243 'full':426 'fundament':1364 'gap':1114,1335,1341 'get':825 'give':127 'good':742,1324 'ground':1494 'guidanc':1150 'header':519 'healthi':1313 'high':679,1314 'highest':1030 'highest-valu':1029 'histor':189 'hyphen':874 'ideal':1005 'identifi':313,337 'ifev':1584 'ignor':1020 'immedi':1017,1120 'impact':1567 'improv':55,133,184,1081,1108,1461,1518,1548 'info':964 'inform':1549 'inject':486 'input':1632 'instal':311,1171 'instruct':453,501,1582 'insuffici':96,99 'intent':736 'interrupt':729 'invoc':432,440,506,549,562,673,688,785 'invok':423,532,619,707,1014,1065 'issu':1326,1355 'item':459,524 'jsonl':281,283,322,408,415,447 'keyword':176,371,552,626,670,986,1039,1043,1135,1138 'larg':1217 'last':111 'leak':889 'learn':1524 'letter':872 'librari':58 'like':756 'limit':1594 'line':1256 'liu':1555 'llm':1563 'llms':1587 'load':174,456,497,656,1239,1265 'locat':356 'loop':1525 'lost':1551 'major':1353 'mani':613,622 'manual':737 'markdown':1419 'marker':517,569,653,809 'match':553,671,1056,1603 'may':304,663 'mcp':177,1528 'mean':1311 'memento':1502 'memento-skil':1501 'mere':655 'messag':147,425,429,437,476,630,717,803,1052,1069 'meta':449 'middl':1554 'mind':723 'minor':1325,1340 'misalign':1365 'miss':1362,1452,1640 'model':1240 'modifi':80 'motiv':168 'msg':466 'multi':1591 'multi-constraint':1590 'multipl':256,355 'must':577,957,972,987 'must/never':921 'my-skil':244 'n':811,830,1431 'n/a':98 'name':351,353,365,390,829,865,870,1475 'narrat':941 'need':677,1332 'negat':719,1349 'never':79,116,660,722,1219,1346 'never-trigg':1218 'next':715 'nice':745 'note':484 'number':873 'often':120 'ok':743 'omit':104 'optim':3,6,218,684,1421,1467 'option':1466 'order':344 'output':84,195,331,462,520,538,647,740,813,1612 'overlap':1136,1143 'overrid':738 'overtrigg':1011,1395 'overview':185,915,1435 'p0':1124,1455 'p0/p1/p2':200,334 'p1':1460 'p2':1465 'pair':1133,1408 'pass':860 'pass/fail':1414 'passiv':914 'path':272,1160 'pattern':944 'per':547,556,564,762,930,1415,1470 'per-skil':546,555,563,761,1469 'perform':1580 'permiss':1633 'platform':267,292 'point':209,1308 'poor':1295 'posit':741,758,965,1009,1317,1550 'post':687 'post-invoc':686 'prescrib':126 'present':498,917,920 'primari':970,984 'priorit':201 'problem':675 'problemat':1345 'process':1148 'produc':537,646 'progress':1228,1296 'prompt':1593 'pushi':902 'put':1285 'python3':319,401 'qualit':1387 'qualiti':60,193,850,1380,1527,1530 'quantifi':105 'quot':143,953,962 'random':1544 'rang':1434 'rate':183,610,765,769,1010,1302,1316,1371,1478,1541 'rather':102,490 're':733 're-describ':732 'reaction':442,482,559,690,1318,1351,1374,1438,1481 'read':77,361,711,1522 'read-on':76 'read-writ':1521 'real':11 'recommend':1119,1257 'refer':1181,1263,1272,1292,1361,1416 'referenc':1158 'reject':1018 'relat':473 'relev':1096 'remov':1225 'report':85,97,198,332,760,826,1066,1389,1396,1405,1412,1417,1422,1492 'requir':1510,1631 'research':16,109,122,165,1485,1498 'research-back':15 'respons':458,523 'review':1624 'rewrit':161,1122 'right':226,230 'risk':1083,1102 'rout':1512 'rule':75,858,918 'run':324,572,578 'safeti':954,1634 'satisfact':764 'scale':211,1309 'scan':240,269,298,321,340,406,1050 'scenario':906 'scope':1425,1605 'score':203,330,1301,1310,1366,1392,1443 'script':320,402 'search':217,511,800 'section':381,916,919 'seem':46 'select':182,224,1540 'self':1107,1517 'self-improv':1106,1516 'sentiment':560 'session':12,100,190,278,317,398,407,413,445,448,528,642,710,788,806,947,1094,1429,1432 'shape':1562 'share':277 'show':138,179 'signific':1334 'silent':750 'similar':1147 'singl':247 'skill':2,8,29,36,39,57,68,81,115,153,187,205,220,227,233,242,246,248,251,254,258,284,315,339,341,350,358,389,416,421,431,439,455,472,487,493,496,514,530,541,548,557,565,587,616,634,650,662,682,705,739,763,784,793,818,828,895,1012,1035,1046,1062,1074,1086,1104,1128,1132,1145,1156,1199,1221,1234,1270,1283,1304,1403,1420,1428,1436,1446,1471,1474,1503,1506,1514,1597 'skill-a':250 'skill-b':253 'skill-nam':827,1473 'skill-optim':1 'skill-rel':471 'skill-skill-optimizer' 'skill-specif':513 'skill.md':9,362,798,854,979,1253,1281,1289 'skills-compat':28 'skip':91,590,606,698,701,777,780,1192,1195 'sourc':260,273,301 'source-sickn33' 'specif':128,164,515,812,839,1619 'specifi':257,388,1427 'start':878 'static':18,192,849,1322,1354,1379,1440 'step':335,377,378,395,518,567,570,796,808,810,831,834,840,898,1203,1298 'stop':845,1625 'storytel':951 'structur':1508 'struggl':1588 'studi':178 'substitut':1615 'success':1637 'suggest':123,130,137,157,159,1079 'summar':893 'switch':751 'tacl':1558 'target':314,338 'task':110,1054,1097,1601 'teach':1146 'test':1165,1621 'text':427 'tier':1230,1238,1241,1251,1261 'time':231,614,623,1118 'token':74,1183,1245,1384,1442 'tool':417,468,494,635,1168,1539 'topic':754 'topic-agent-skills' 'topic-agentic-skills' 'topic-ai-agent-skills' 'topic-ai-agents' 'topic-ai-coding' 'topic-ai-workflows' 'topic-antigravity' 'topic-antigravity-skills' 'topic-claude-code' 'topic-claude-code-skills' 'topic-codex-cli' 'topic-codex-skills' 'total':867 'track':435,464 'transcript':279,323,639 'treat':1610 'trigger':42,117,151,175,370,551,609,625,661,667,759,877,885,967,985,996,1000,1042,1072,1091,1134,1205,1212,1220,1315,1347,1370,1437,1477 'turn':478 'two':1140,1144 'u':1561 'u-shap':1560 'underperform':70 'understand':66 'undertrigg':141,674,1024,1089,1103,1382,1441,1499 'unrout':1513 'usag':238,1110,1458 'use':34,37,48,61,188,400,418,510,636,880,911,1271,1291,1595 'useless':665 'user':146,303,387,424,436,475,558,629,689,713,728,731,746,752,1016,1051,1068,1350,1373,1480 'valid':1620 'valu':1031 'valuabl':602 'varianc':1581 'via':403,488,1519 'violat':237,900 'vs':620,1542 'want':51,64,727 'wast':72 'week':112 'weight':1368 'well':1534 'well-written':1533 'widen':1116 'within':526,989 'without':585,1290 'word':129,384,668,928,932,934,937,1200,1214,1259,1287 'work':20,678,1360 'workflow':312,376,383,434,463,516,544,566,652,749,767,888,897,1142,1320,1376 'worth':683 'wrap':959 'write':219,1523 'written':1535 'wrong':669,721 'x':181,948,1547 'x/n':835 'y':836 'yaml':368,952","prices":[{"id":"2ab5ba29-049d-4988-b3b6-28325d13c59a","listingId":"8a2c521e-7226-4772-95f9-fafec8dc610c","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"sickn33","category":"antigravity-awesome-skills","install_from":"skills.sh"},"createdAt":"2026-04-18T21:45:00.471Z"}],"sources":[{"listingId":"8a2c521e-7226-4772-95f9-fafec8dc610c","source":"github","sourceId":"sickn33/antigravity-awesome-skills/skill-optimizer","sourceUrl":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-optimizer","isPrimary":false,"firstSeenAt":"2026-04-18T21:45:00.471Z","lastSeenAt":"2026-04-22T12:51:47.041Z"}],"details":{"listingId":"8a2c521e-7226-4772-95f9-fafec8dc610c","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"sickn33","slug":"skill-optimizer","github":{"repo":"sickn33/antigravity-awesome-skills","stars":34515,"topics":["agent-skills","agentic-skills","ai-agent-skills","ai-agents","ai-coding","ai-workflows","antigravity","antigravity-skills","claude-code","claude-code-skills","codex-cli","codex-skills","cursor","cursor-skills","developer-tools","gemini-cli","gemini-skills","kiro","mcp","skill-library"],"license":"mit","html_url":"https://github.com/sickn33/antigravity-awesome-skills","pushed_at":"2026-04-22T06:40:00Z","description":"Installable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.","skill_md_sha":"015758bd1497e2a51f6d1bd7c52ca98c73047038","skill_md_path":"skills/skill-optimizer/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/skill-optimizer"},"layout":"multi","source":"github","category":"antigravity-awesome-skills","frontmatter":{"name":"skill-optimizer","description":"Diagnose and optimize Agent Skills (SKILL.md) with real session data and research-backed static analysis. Works with Claude Code, Codex, and any Agent Skills-compatible agent."},"skills_sh_url":"https://skills.sh/sickn33/antigravity-awesome-skills/skill-optimizer"},"updatedAt":"2026-04-22T12:51:47.041Z"}}