[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEN8PYR0JYA2KH26GVGVCC":3,"skill-same:01M6MEN8PYR0JYA2KH26GVGVCC":94},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":42,"linkOnly":43,"markdownContent":44,"markdownBody":45,"frontMatter":46,"refName":71,"commitSha":72,"skillDirectory":73,"forksCount":74,"repositoryHtmlUrl":75,"repositoryHomepageUrl":76,"ownerHtmlUrl":77,"ownerBlogUrl":78,"ownerDescription":79,"updatedAt":80,"install":81,"resources":93},"01M6MEN8PYR0JYA2KH26GVGVCC","agy-native",null,"Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1559,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fagy-native\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41],"native","agy","agy native","by name","result","when","contract","true","session","collect","runtime","gemini","evidence","fallback","context","canonical","start","run","fresh","team","design","headless","never","2026-11-10 10:12:30",false,"---\nname: agy-native\ndescription: 'Run a supplied task in headless AGY (Antigravity, Gemini) and collect its result. Use when: AGY, Antigravity or Gemini is requested by name; never a fallback.'\npractices: [team-topologies, design-by-contract]\nhexagonal_role: driving-adapter\nconsumes: [explicit-packet]\nproduces: [agy-run-evidence]\ncontext_rel:\n- kind: separate-ways\n  with: codex-exec\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  tier: cross-vendor\n  dependencies: []\n  capabilities: [dispatch_explicit_packet, provide_fresh_context]\n  effects: [start_agy_session]\n  canonical_status: canonical\n  disposition: keep_optional_adapter\noutput_contract: AGY runtime evidence\n---\n\n# AGY Native\n\nRun a supplied packet in AGY (Antigravity) only when the caller explicitly\nselects that runtime. Scope the run to the supplied workspace and packet,\nreturn runtime evidence, and stop. It worked when the command passes an\nexplicit `--print-timeout`, the posture is disclosed, and the result says\nwhether the turn finished instead of reading exit 0 as proof.\n\n## Before launch\n\n1. **Read the live surface.** The CLI changes faster than skill text.\n   Re-checked on 2026-10-25 against AGY 1.4.7.\n   Run `agy --help` for flags, `agy changelog` for behavior the help omits,\n   and `agy models` for ids. That list includes Claude and GPT-OSS: a Gemini\n   or cross-family run needs a `gemini-*` id.\n2. **Absent means stop.** If `agy` is missing or its help cannot be read,\n   report the absence and stop. Never fall back silently to Codex, Claude or\n   any other runtime. A fallback the caller named, in advance or after that\n   report, runs only after it, through [claude-exec](..\u002Fclaude-exec\u002FSKILL.md)\n   or [codex-exec](..\u002Fcodex-exec\u002FSKILL.md) with its own bound, labelled\n   \"not an AGY result\". Nothing routes work to AGY on its own either.\n3. **Set an explicit bound.** Print mode (`agy -p` \u002F `--print`) is the headless\n   path, and it has no built-in limit: `--print-timeout` defaults to `0`, which\n   waits until the turn completes. Pass `--print-timeout` from the caller's\n   remaining deadline and hold the same bound outside the process. A run\n   stopped at the bound is a timeout, not a result.\n4. **Keep author and validator apart.** A validator is a new run in a new\n   conversation, never `-c`\u002F`--continue` or `--conversation \u003Cauthor-id>`, so\n   its judgment stays fresh. Validators stay read-only and hand judgment to\n   Validate; they never write the core verdict.\n\n## Permission posture (disclose it; never assume it)\n\nName the posture before launch: the flags plus the user and project\n`settings.json` permissions, which headless runs honor (disclose those or say\nnot inspected). No flag makes file access read-only.\n\n- No posture flag: workspace reads are granted; other actions needing approval\n  are denied and listed in the JSON `denied_actions`. With settings that allow\n  no writes, this is the validator posture.\n- `--sandbox` restricts terminal commands only. `--mode accept-edits` approves\n  edits and `--mode auto` edits and safe commands; `--mode plan` is not\n  documented as read-only, and headless runs pass plan review on their own.\n- `--dangerously-skip-permissions` approves every tool call. It and the\n  approving modes need declared effects and caller authorization covering\n  that blast radius.\n\nBefore and after the run, take `git status --porcelain` and\n`git diff HEAD | shasum` in `$WORKSPACE`, and list the packet directory\n`$PKT` after; a validator's write is out of authority. These miss edits\ninside untracked or ignored files and under other `--add-dir` paths: report\nthose unchecked.\n\n## Command\n\nIn an AgentOps source checkout, review runs use `REVIEWER=agy` (the id in\n`REVIEWER_MODEL`) with `codex_exec_guarded` from `scripts\u002Flib\u002Fcodex-exec.sh`\n(call shape in [codex-exec](..\u002Fcodex-exec\u002FSKILL.md#run-it)). It adds echo,\nstall and output-cap handling. Its posture, to disclose, is\n`--sandbox --dangerously-skip-permissions` with `--add-dir` on its own\nprivate `mktemp -d` packet directory: every tool call is approved over the\nworkspace and that directory, so it is not read-only. An installed skill\nlacks that library; use this block.\nThe caller supplies `$MODEL`, `$POSTURE`, `DEADLINE_EPOCH` and absolute\n`$WORKSPACE`, `$PROMPT_FILE`, `$OUT` and `$ERR` paths, the last three outside\n`$WORKSPACE`.\nThis block passes the packet by path, not inline: a short `-p` pointer plus\n`--add-dir` on the packet's own directory only, because a large inline prompt\ncan be dropped while the run still looks scoped. That drop is an earlier-run\nobservation, not in the 1.4.7 help or changelog. Would verify: a run with an\ninline `-p` prompt over ~100 KB that asks for a marker from its end.\n\n```bash\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout: not launching\" >&2; exit 2; }\n[ -n \"$MODEL\" ] || { echo \"MODEL unset: pick an id from agy models\" >&2; exit 2; }\n# DEADLINE_EPOCH: absolute Unix time fixed once by the caller; a later run gets what is left.\ncase \"$DEADLINE_EPOCH\" in ''|*[!0-9]*) echo \"no deadline: not launching\" >&2; exit 2;; esac\nfor p in \"$WORKSPACE\" \"$PROMPT_FILE\" \"$OUT\" \"$ERR\"; do case \"$p\" in \u002F*) ;; *) echo \"not absolute: '$p'\" >&2; exit 2;; esac; done\nremaining=$(( DEADLINE_EPOCH - $(date +%s) ))\npt=$(( remaining - 15 ))  # AGY's bound fires first; 0 would mean no limit\n[ \"$pt\" -gt 0 ] || { echo \"deadline too close; not launched\" >&2; exit 124; }\nPKT=$(mktemp -d) && cp \"$PROMPT_FILE\" \"$PKT\u002Fpacket.md\" || exit 2  # not $TMPDIR itself\ncd \"$WORKSPACE\" || exit 2\n# POSTURE: Bash array of the flags chosen above; empty is the default posture.\nset -o pipefail  # bash and zsh: $? is the failing stage, not head's\nstart=$(date +%s)\n\"$TO\" -k 10 \"$remaining\" \\\n  agy --print-timeout \"${pt}s\" --model \"$MODEL\" --output-format json \\\n  \"${POSTURE[@]}\" --add-dir \"$PKT\" \\\n  -p \"Read the task packet at $PKT\u002Fpacket.md and do what it describes.\" \\\n  \u003C\u002Fdev\u002Fnull 2>\"$ERR\" | head -c 10485760 >\"$OUT\"\nrc=$?; elapsed=$(( $(date +%s) - start )); echo \"exit=$rc elapsed=${elapsed}s pt=${pt}s\"\n```\n\nFlags after `-p \u003Cprompt>` are parsed (1.4.7: a bad value there exits 2).\n`--print-timeout` needs a unit such as `300s`; a bare number or an\nunknown flag exits 2. If the host shell tool's cap is under\n`remaining` plus 10 s, handle it as [claude-exec](..\u002Fclaude-exec\u002FSKILL.md#run) does.\n\n**Did it finish?** Exit 0 is not proof: an expired `--print-timeout` returns\npartial output, exits 0 and warns on stderr. The 1.4.11 changelog adds a JSON\n`finished_reason` (`print_timeout`, `interrupted` or `error`; omitted for a\nfinished turn); 1.4.7 lacks it. There, exit 0 with `elapsed` under `pt` was\nnot cut by that bound; at `pt` or later it is that timeout or a finished turn\nwhose background tasks held the run to the bound, so read `$ERR`. Judge a\nfinished turn by the expected artifact and the workspace snapshots, else say\nunknown. Exit 3 with an `AGY_ERROR:` line is a model or agent error; other\nnon-zero is a failed run; 124, or 137 after the grace, is the outer bound.\nOutput repeating the packet or pointer is an echo. An `$OUT` of exactly\n10 MiB was cut; its status is the closed pipe.\n\n## Return\n\n```text\ncommand:        exact argv (prompt by reference)\nposture:        flags used; settings permissions, or \"settings not inspected\"\nmodel:          requested id; observed model if AGY reported one, else unknown\nconversation:   id AGY reported, else unknown\nbound:          --print-timeout value, the outer deadline and elapsed seconds\noutcome:        exit status; finished | timed out (which bound) | echo | unknown | not run\ndenied_actions: list from the JSON output, else none reported\nartifacts:      output path, bytes, truncated yes|no; changed-file paths\n```\n\nInstallation, plugin mutation and recurring scheduling need separate explicit\nauthorization.\n","# AGY Native\n\nRun a supplied packet in AGY (Antigravity) only when the caller explicitly\nselects that runtime. Scope the run to the supplied workspace and packet,\nreturn runtime evidence, and stop. It worked when the command passes an\nexplicit `--print-timeout`, the posture is disclosed, and the result says\nwhether the turn finished instead of reading exit 0 as proof.\n\n## Before launch\n\n1. **Read the live surface.** The CLI changes faster than skill text.\n   Re-checked on 2026-10-25 against AGY 1.4.7.\n   Run `agy --help` for flags, `agy changelog` for behavior the help omits,\n   and `agy models` for ids. That list includes Claude and GPT-OSS: a Gemini\n   or cross-family run needs a `gemini-*` id.\n2. **Absent means stop.** If `agy` is missing or its help cannot be read,\n   report the absence and stop. Never fall back silently to Codex, Claude or\n   any other runtime. A fallback the caller named, in advance or after that\n   report, runs only after it, through [claude-exec](..\u002Fclaude-exec\u002FSKILL.md)\n   or [codex-exec](..\u002Fcodex-exec\u002FSKILL.md) with its own bound, labelled\n   \"not an AGY result\". Nothing routes work to AGY on its own either.\n3. **Set an explicit bound.** Print mode (`agy -p` \u002F `--print`) is the headless\n   path, and it has no built-in limit: `--print-timeout` defaults to `0`, which\n   waits until the turn completes. Pass `--print-timeout` from the caller's\n   remaining deadline and hold the same bound outside the process. A run\n   stopped at the bound is a timeout, not a result.\n4. **Keep author and validator apart.** A validator is a new run in a new\n   conversation, never `-c`\u002F`--continue` or `--conversation \u003Cauthor-id>`, so\n   its judgment stays fresh. Validators stay read-only and hand judgment to\n   Validate; they never write the core verdict.\n\n## Permission posture (disclose it; never assume it)\n\nName the posture before launch: the flags plus the user and project\n`settings.json` permissions, which headless runs honor (disclose those or say\nnot inspected). No flag makes file access read-only.\n\n- No posture flag: workspace reads are granted; other actions needing approval\n  are denied and listed in the JSON `denied_actions`. With settings that allow\n  no writes, this is the validator posture.\n- `--sandbox` restricts terminal commands only. `--mode accept-edits` approves\n  edits and `--mode auto` edits and safe commands; `--mode plan` is not\n  documented as read-only, and headless runs pass plan review on their own.\n- `--dangerously-skip-permissions` approves every tool call. It and the\n  approving modes need declared effects and caller authorization covering\n  that blast radius.\n\nBefore and after the run, take `git status --porcelain` and\n`git diff HEAD | shasum` in `$WORKSPACE`, and list the packet directory\n`$PKT` after; a validator's write is out of authority. These miss edits\ninside untracked or ignored files and under other `--add-dir` paths: report\nthose unchecked.\n\n## Command\n\nIn an AgentOps source checkout, review runs use `REVIEWER=agy` (the id in\n`REVIEWER_MODEL`) with `codex_exec_guarded` from `scripts\u002Flib\u002Fcodex-exec.sh`\n(call shape in [codex-exec](..\u002Fcodex-exec\u002FSKILL.md#run-it)). It adds echo,\nstall and output-cap handling. Its posture, to disclose, is\n`--sandbox --dangerously-skip-permissions` with `--add-dir` on its own\nprivate `mktemp -d` packet directory: every tool call is approved over the\nworkspace and that directory, so it is not read-only. An installed skill\nlacks that library; use this block.\nThe caller supplies `$MODEL`, `$POSTURE`, `DEADLINE_EPOCH` and absolute\n`$WORKSPACE`, `$PROMPT_FILE`, `$OUT` and `$ERR` paths, the last three outside\n`$WORKSPACE`.\nThis block passes the packet by path, not inline: a short `-p` pointer plus\n`--add-dir` on the packet's own directory only, because a large inline prompt\ncan be dropped while the run still looks scoped. That drop is an earlier-run\nobservation, not in the 1.4.7 help or changelog. Would verify: a run with an\ninline `-p` prompt over ~100 KB that asks for a marker from its end.\n\n```bash\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout: not launching\" >&2; exit 2; }\n[ -n \"$MODEL\" ] || { echo \"MODEL unset: pick an id from agy models\" >&2; exit 2; }\n# DEADLINE_EPOCH: absolute Unix time fixed once by the caller; a later run gets what is left.\ncase \"$DEADLINE_EPOCH\" in ''|*[!0-9]*) echo \"no deadline: not launching\" >&2; exit 2;; esac\nfor p in \"$WORKSPACE\" \"$PROMPT_FILE\" \"$OUT\" \"$ERR\"; do case \"$p\" in \u002F*) ;; *) echo \"not absolute: '$p'\" >&2; exit 2;; esac; done\nremaining=$(( DEADLINE_EPOCH - $(date +%s) ))\npt=$(( remaining - 15 ))  # AGY's bound fires first; 0 would mean no limit\n[ \"$pt\" -gt 0 ] || { echo \"deadline too close; not launched\" >&2; exit 124; }\nPKT=$(mktemp -d) && cp \"$PROMPT_FILE\" \"$PKT\u002Fpacket.md\" || exit 2  # not $TMPDIR itself\ncd \"$WORKSPACE\" || exit 2\n# POSTURE: Bash array of the flags chosen above; empty is the default posture.\nset -o pipefail  # bash and zsh: $? is the failing stage, not head's\nstart=$(date +%s)\n\"$TO\" -k 10 \"$remaining\" \\\n  agy --print-timeout \"${pt}s\" --model \"$MODEL\" --output-format json \\\n  \"${POSTURE[@]}\" --add-dir \"$PKT\" \\\n  -p \"Read the task packet at $PKT\u002Fpacket.md and do what it describes.\" \\\n  \u003C\u002Fdev\u002Fnull 2>\"$ERR\" | head -c 10485760 >\"$OUT\"\nrc=$?; elapsed=$(( $(date +%s) - start )); echo \"exit=$rc elapsed=${elapsed}s pt=${pt}s\"\n```\n\nFlags after `-p \u003Cprompt>` are parsed (1.4.7: a bad value there exits 2).\n`--print-timeout` needs a unit such as `300s`; a bare number or an\nunknown flag exits 2. If the host shell tool's cap is under\n`remaining` plus 10 s, handle it as [claude-exec](..\u002Fclaude-exec\u002FSKILL.md#run) does.\n\n**Did it finish?** Exit 0 is not proof: an expired `--print-timeout` returns\npartial output, exits 0 and warns on stderr. The 1.4.11 changelog adds a JSON\n`finished_reason` (`print_timeout`, `interrupted` or `error`; omitted for a\nfinished turn); 1.4.7 lacks it. There, exit 0 with `elapsed` under `pt` was\nnot cut by that bound; at `pt` or later it is that timeout or a finished turn\nwhose background tasks held the run to the bound, so read `$ERR`. Judge a\nfinished turn by the expected artifact and the workspace snapshots, else say\nunknown. Exit 3 with an `AGY_ERROR:` line is a model or agent error; other\nnon-zero is a failed run; 124, or 137 after the grace, is the outer bound.\nOutput repeating the packet or pointer is an echo. An `$OUT` of exactly\n10 MiB was cut; its status is the closed pipe.\n\n## Return\n\n```text\ncommand:        exact argv (prompt by reference)\nposture:        flags used; settings permissions, or \"settings not inspected\"\nmodel:          requested id; observed model if AGY reported one, else unknown\nconversation:   id AGY reported, else unknown\nbound:          --print-timeout value, the outer deadline and elapsed seconds\noutcome:        exit status; finished | timed out (which bound) | echo | unknown | not run\ndenied_actions: list from the JSON output, else none reported\nartifacts:      output path, bytes, truncated yes|no; changed-file paths\n```\n\nInstallation, plugin mutation and recurring scheduling need separate explicit\nauthorization.\n",{"name":5,"consumes":47,"metadata":49,"produces":58,"practices":60,"context_rel":63,"description":7,"hexagonal_role":67,"user-invocable":68,"output_contract":69,"skill_api_version":70},[48],"explicit-packet",{"tier":50,"effects":51,"disposition":53,"capabilities":54,"dependencies":57,"canonical_status":34},"cross-vendor",[52],"start_agy_session","keep_optional_adapter",[55,56],"dispatch_explicit_packet","provide_fresh_context",[],[59],"agy-run-evidence",[61,62],"team-topologies","design-by-contract",[64],{"kind":65,"with":66},"separate-ways","codex-exec","driving-adapter",true,"AGY runtime evidence",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fagy-native",474,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-11 14:40:14",{"source":8,"skillName":5,"commands":82,"prompt":92,"zipAvailable":68},[83,86,89],{"tool":84,"command":85},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agy-native",{"tool":87,"command":88},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agy-native",{"tool":90,"command":91},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill agy-native","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fagy-native\u002FSKILL.md",[],[95,103,110,117,141,165],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":102},"01M746ZWACVKMZ1BJXJZHYJSSX","migrate-to-e2e","Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, with the old suite running beside the new one until each ported test is proven. Keeps a MIGRATION.md progress file so any later session resumes where the last stopped. Optionally plants a defect to show both suites catch it. Use for \u002Fmigrate-to-e2e, \"migrate our tests to e2e\", \"port these Maestro flows\", \"move our TesterArmy tests\", or when a project has an e2e config and an older suite still running.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fmigrate-to-e2e\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":102},"01M746ZPTAX1Q0FBKAB1CYND7E","e2e","Writes, runs, and debugs end-to-end tests for web and mobile apps with e2e, the agentic test runner, which mixes agent.act goals with exact locator assertions on a Playwright browser or an iOS or Android device. Also drives a project's running app live over the e2e MCP server to look at a screen, check a UI change, take a screenshot or record a video, and try a locator; and runs bug bashes, parallel e2e explore runs with each bug proven by a repro test. Use when a project depends on e2e or has an e2e.config.ts, when asked for end-to-end, browser, mobile, or agentic UI tests, to check a change in the running app, to QA or bug bash an app or branch, or when an e2e run fails.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fe2e\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":102},"01M746ZJN784HVHMDP9MQGCSGG","create-verification-skill","Generate a project-local verify-\u003Capp> skill on top of e2e, so any coding agent can launch the app, check it is worth driving, exercise a feature the way a user does, keep evidence, and bug bash it. Writes the skill, a feature map with one explore charter per feature, and proves it once. Use for \u002Fcreate-verification-skill, \"make a verification skill for this repo\", or when a project has no scripted way to prove UI behavior.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftester-army\u002Fe2e\u002Fskills\u002Fcreate-verification-skill\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":42},"01M716A6ETNB9B1SQ3GXZC75VR","deja-search","deja-vu memory — search the user's past AI coding sessions with the deja CLI. Holds what they already settled and never wrote into the repo (naming rules, banned or already-tried tools, required checks before merge, preferred values, who owns what). Use before your first edit in a task, before you call a change done or ready to merge, before you recommend a tool, library, design or reviewer, before re-debugging an error that may already be solved, when they say 'didn't we fix this before', 'what did we decide about X' or 'I already have that', and before telling them something on this machine does not exist.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-search\u002FSKILL.md",[],[124,125,41,126,127,128,129,130,131,39,132,24,133,134,135,136,137,138,139,140],"search","deja search","error","ready","memory","re","decide","fix","debugging","you","done","reviewer","io","change","cli","merge","past",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":42},"01M716A3J2W5SENSE9VGMXB375","deja-reflect","End-of-session reflection and memory curation with deja-vu. Review what was decided, what commands broke and what repaired them, and record durable project rules or decisions with deja remember so the next session starts with them.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fvshulcz\u002Fdeja-vu\u002Fskills\u002Fdeja-reflect\u002FSKILL.md",[],[148,149,150,136,151,152,153,154,155,156,157,158,159,160,128,161,162,27,163,164],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","end","reflection",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":182,"publishedAt":42},"01M715T3RR4BAYSR57HPPTJ0PF","revid","Make, edit, export and post AI videos with Revid (revid.ai) through the Revid MCP server. Use whenever the user wants a short-form or long-form video made (from an idea, a script, a URL, an article, a PDF, a tweet, a product page, their own clips, or a song), wants to find what is going viral on TikTok, YouTube, Instagram or X before making something, wants to edit or re-export an existing Revid project, generate a standalone AI image or clip, make a series episode, or publish and schedule a finished video to connected social accounts. Covers setup (hosted MCP with OAuth, or an API key), the 36 tools, credits, polling and the rules for publishing. Routes to the more specific revid-* skills when one fits.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Ftmakersas\u002Frevid-skills\u002Fskills\u002Frevid\u002FSKILL.md",[171,176,179],{"categoryNo":172,"categoryName":173,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":177,"categoryName":178,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":180,"categoryName":181,"taxonomyType":174,"taxonomyTypeDesc":175},"01JBSEEDCAT000000000000010","后端与接口",[167,183,184,185,186,187,188,162,189,129,190,191,192,193,24,194,195,196,197,198],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]