[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MENTKK27S2C2PFWDS3Y79M":3,"skill-same:01M6MENTKK27S2C2PFWDS3Y79M":98},{"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":41,"linkOnly":42,"markdownContent":43,"markdownBody":44,"frontMatter":45,"refName":69,"commitSha":70,"skillDirectory":71,"forksCount":72,"repositoryHtmlUrl":73,"repositoryHomepageUrl":74,"ownerHtmlUrl":75,"ownerBlogUrl":76,"ownerDescription":77,"updatedAt":78,"install":79,"resources":91},"01M6MENTKK27S2C2PFWDS3Y79M","codex-exec",null,"Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcodex-exec\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"codex","exec","codex exec","result","when","adapter","exit","true","sandbox","for","canonical","status","network","run","pragmatic","command","artifact","orchestration","effects","retries","ci","headless","2026-11-10 10:12:30",false,"---\nname: codex-exec\ndescription: 'Run one prompt through headless Codex and capture the result. Use when: wanting a one-shot `codex exec` run or CI step. Not for batches or retries.'\nskill_api_version: 1\nuser-invocable: true\nhexagonal_role: driving-adapter\npractices:\n- pragmatic-programmer\nconsumes:\n- codex-command-packet\nproduces:\n- codex-run-output\ncontext_rel:\n- kind: supplier-to\n  with: validate\nmetadata:\n  capabilities: [codex_exec]\n  effects: [run_codex_process, sandbox_tiered_workspace_and_network_effects]\n  canonical_status: canonical\n  disposition: keep_optional_adapter\n  tier: orchestration\n  dependencies: []\n  stability: stable\noutput_contract: process exit status and captured Codex output artifact\n---\n# Codex Exec — one-shot runtime adapter\n\nRun exactly one caller-supplied Codex prompt as one process and capture its\nresult. This skill does not choose work, retry, validate or continue. It worked\nwhen the command closes stdin, uses the sandbox the declared effects need,\nruns under one deadline fixed before the first attempt, and the report names\nthe exit code's meaning instead of calling a timeout a result.\n\n## Rules that change the command\n\n- **Sandbox from declared effects.** `-s read-only` for review or analysis,\n  `workspace-write` only for authorized edits, and network or wider access only\n  when the caller explicitly requires those effects. \"In case it needs it\" is\n  not a declared effect. `-s` limits only Codex's shell commands; the user's\n  `config.toml` still starts its MCP servers. For review and CI add\n  `--ignore-user-config` (auth still loads), or report the inherited MCP\n  servers as undeclared effects. A permission denial inside the run (`EPERM`,\n  \"Operation not permitted\") shows only what the mode blocks, not whether the\n  host or the code would fail. Quote it and list the check under\n  `not_as_briefed` as sandbox-limited: neither a pass nor a failed check. A\n  host-side observation still stands; a host run is the caller's decision.\n- **Persist the transcript a receipt needs.** `--ephemeral` writes no session\n  file under `$CODEX_HOME\u002Fsessions`. A validator whose\n  [judgment receipt](..\u002Fvalidate\u002Freferences\u002Fjudgment-receipts.md) the\n  caller requires runs without `--ephemeral`, and the caller copies that\n  run's `rollout-*.jsonl` into protected evidence storage. Add `--ephemeral`\n  only when no receipt is required.\n- **Close stdin.** `codex exec` reads the prompt from stdin when no prompt\n  argument is given, and appends piped stdin to a prompt argument. A non-TTY run\n  (CI, a script) with an open stdin can wait forever: the **stdin hang**. Feed\n  the prompt on stdin and let it end, or redirect `\u003C\u002Fdev\u002Fnull`.\n- **One deadline, never renewed.** Fix one absolute deadline before the first\n  attempt. Each invocation, including any retry the caller decides to make,\n  gets only the time left before that deadline. A retry never gets a fresh\n  budget: a loop that gives each attempt its own new timeout has silently\n  multiplied the caller's bound. A missing, zero, negative or malformed bound\n  prevents launch; an expired deadline stops before dispatch.\n- **No retry here.** Report a timeout, error or empty output as it is. Another\n  invocation is the caller's decision, under the same deadline.\n- **Capped capture, typed exit.** Capture output to a file under a byte cap and\n  report the exit status. A timeout is not a result.\n\n## Run it\n\nIn an AgentOps source checkout, use the guarded library. It enforces the\ndeadline, the combined output cap (10 MiB default), process-group cleanup and\necho detection:\n\n```bash\n# AGENTOPS_ROOT: the agentops source checkout. DEADLINE_EPOCH: absolute Unix\n# time fixed once by the caller and reused by every invocation in its scope.\n. \"$AGENTOPS_ROOT\u002Fscripts\u002Flib\u002Fcodex-exec.sh\"\nCODEX_EXEC_EXTRA_ARGS=(--ignore-user-config)  # add --ephemeral only when no receipt is required\nCODEX_EXEC_DIR=\"$WORKSPACE\" CODEX_EXEC_SANDBOX=read-only \\\nCODEX_EXEC_PROMPT_FILE=\"$PROMPT_FILE\" CODEX_EXEC_DEADLINE_EPOCH=\"$DEADLINE_EPOCH\" \\\nCODEX_EXEC_MAX_OUTPUT_BYTES=10485760 CODEX_EXEC_OUT_FILE=\"$OUTPUT\" \\\n  codex_exec_guarded \u003C\u002Fdev\u002Fnull\n```\n\nOutside a Git repository add `CODEX_EXEC_SKIP_GIT_CHECK=1`; to keep the final\nmessage outside the cap, add `-o \"$LAST\"` to that array (assigned on its own line).\n\nAn installed skill ships no scripts, so `scripts\u002Flib\u002Fcodex-exec.sh` is absent\noutside a source checkout. Run `codex exec` directly instead, with bash or zsh\n(flags as of codex-cli 0.163.0; confirm with `codex exec --help`; add\n`--skip-git-repo-check` and `-o \u003Cfile>` as above):\n\n```bash\ncase \"${DEADLINE_EPOCH:-}\" in ''|0*|*[!0-9]*) echo \"no valid deadline; not launched\" >&2; exit 2;; esac\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout; not launched\" >&2; exit 2; }\nremaining=$(( DEADLINE_EPOCH - $(date +%s) - 10 ))  # keep the 10 s KILL grace inside\n[ \"$remaining\" -gt 0 ] || { echo \"deadline passed or within 10 s; not launched\" >&2; exit 124; }\nset -o pipefail  # bash and zsh: $? is the failing stage, not head's\n\"$TO\" -k 10 \"$remaining\" \\\n  codex exec --ignore-user-config -C \"$WORKSPACE\" -s read-only - \u003C\"$PROMPT_FILE\" 2>&1 \\\n  | head -c 10485760 >\"$OUTPUT\"\nrc=$?  # 124 timed out, 137 killed after grace, 127 no codex, else codex's status\n```\n\nAn output file exactly at the cap was truncated, and its status reflects the\nclosed pipe, not a review. The fallback has no survivor check or echo\ndetection; report both as not enforced.\n\n## Exit codes (guarded library)\n\n| Exit | Meaning |\n|---|---|\n| 0 | Codex completed and produced output |\n| 2 | precondition: binary missing, bounds invalid or missing, capability unavailable, or cleanup unverified; not a result |\n| 122 | descendants survived Codex's exit; degraded run |\n| 123 | capture or prompt-preparation cap reached; partial evidence kept |\n| 124 | deadline expired, or a clean exit with empty output; a stall, not a result |\n| 125 | output repeats the prompt; not a result |\n| 128+N | cancelled by signal N (129 HUP, 130 INT, 143 TERM) |\n| other | Codex's own nonzero status, preserved |\n\nReserved codes are runtime evidence, never a semantic verdict. A Codex 124 or\n137 returns 124 with the STALL line; a Codex 2, 122, 123, 129, 130 or 143\nreturns with no `codex-exec:` stderr line, so check stderr, the capture and\nelapsed time before reading one as the runner's.\n[Guarded runner internals](references\u002Fguarded-runner.md) covers inputs, host\nrequirements, process supervision and the external sandbox wrapper.\n\n## Report, then stop\n\n```text\ncommand:  exact argv or library call (prompt by reference)\nsandbox:  -s value and the declared effect that needs it\nbound:    absolute deadline and seconds remaining at launch\ncapture:  output path, byte cap, truncated yes\u002Fno\nexit:     status and its meaning from the table\ncleanup:  library result, or \"not enforced\" for the direct fallback\nnot_as_briefed: steps the output reports refused or sandbox-limited, quoted | none reported\n```\n\nA Codex validator follows the\n[judgment receipt convention](..\u002Fvalidate\u002Freferences\u002Fjudgment-receipts.md)\nand the [model-dispatch recipe](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md#association-before-execution):\na requested model flag or the model's own description does not prove which\nmodel ran.\n\n- Use [claude-exec](..\u002Fclaude-exec\u002FSKILL.md) for one headless Claude prompt.\n- Use [agy-native](..\u002Fagy-native\u002FSKILL.md) when AGY is named.\n- Use [orchestrate](..\u002Forchestrate\u002FSKILL.md) for a batch of workers.\n","# Codex Exec — one-shot runtime adapter\n\nRun exactly one caller-supplied Codex prompt as one process and capture its\nresult. This skill does not choose work, retry, validate or continue. It worked\nwhen the command closes stdin, uses the sandbox the declared effects need,\nruns under one deadline fixed before the first attempt, and the report names\nthe exit code's meaning instead of calling a timeout a result.\n\n## Rules that change the command\n\n- **Sandbox from declared effects.** `-s read-only` for review or analysis,\n  `workspace-write` only for authorized edits, and network or wider access only\n  when the caller explicitly requires those effects. \"In case it needs it\" is\n  not a declared effect. `-s` limits only Codex's shell commands; the user's\n  `config.toml` still starts its MCP servers. For review and CI add\n  `--ignore-user-config` (auth still loads), or report the inherited MCP\n  servers as undeclared effects. A permission denial inside the run (`EPERM`,\n  \"Operation not permitted\") shows only what the mode blocks, not whether the\n  host or the code would fail. Quote it and list the check under\n  `not_as_briefed` as sandbox-limited: neither a pass nor a failed check. A\n  host-side observation still stands; a host run is the caller's decision.\n- **Persist the transcript a receipt needs.** `--ephemeral` writes no session\n  file under `$CODEX_HOME\u002Fsessions`. A validator whose\n  [judgment receipt](..\u002Fvalidate\u002Freferences\u002Fjudgment-receipts.md) the\n  caller requires runs without `--ephemeral`, and the caller copies that\n  run's `rollout-*.jsonl` into protected evidence storage. Add `--ephemeral`\n  only when no receipt is required.\n- **Close stdin.** `codex exec` reads the prompt from stdin when no prompt\n  argument is given, and appends piped stdin to a prompt argument. A non-TTY run\n  (CI, a script) with an open stdin can wait forever: the **stdin hang**. Feed\n  the prompt on stdin and let it end, or redirect `\u003C\u002Fdev\u002Fnull`.\n- **One deadline, never renewed.** Fix one absolute deadline before the first\n  attempt. Each invocation, including any retry the caller decides to make,\n  gets only the time left before that deadline. A retry never gets a fresh\n  budget: a loop that gives each attempt its own new timeout has silently\n  multiplied the caller's bound. A missing, zero, negative or malformed bound\n  prevents launch; an expired deadline stops before dispatch.\n- **No retry here.** Report a timeout, error or empty output as it is. Another\n  invocation is the caller's decision, under the same deadline.\n- **Capped capture, typed exit.** Capture output to a file under a byte cap and\n  report the exit status. A timeout is not a result.\n\n## Run it\n\nIn an AgentOps source checkout, use the guarded library. It enforces the\ndeadline, the combined output cap (10 MiB default), process-group cleanup and\necho detection:\n\n```bash\n# AGENTOPS_ROOT: the agentops source checkout. DEADLINE_EPOCH: absolute Unix\n# time fixed once by the caller and reused by every invocation in its scope.\n. \"$AGENTOPS_ROOT\u002Fscripts\u002Flib\u002Fcodex-exec.sh\"\nCODEX_EXEC_EXTRA_ARGS=(--ignore-user-config)  # add --ephemeral only when no receipt is required\nCODEX_EXEC_DIR=\"$WORKSPACE\" CODEX_EXEC_SANDBOX=read-only \\\nCODEX_EXEC_PROMPT_FILE=\"$PROMPT_FILE\" CODEX_EXEC_DEADLINE_EPOCH=\"$DEADLINE_EPOCH\" \\\nCODEX_EXEC_MAX_OUTPUT_BYTES=10485760 CODEX_EXEC_OUT_FILE=\"$OUTPUT\" \\\n  codex_exec_guarded \u003C\u002Fdev\u002Fnull\n```\n\nOutside a Git repository add `CODEX_EXEC_SKIP_GIT_CHECK=1`; to keep the final\nmessage outside the cap, add `-o \"$LAST\"` to that array (assigned on its own line).\n\nAn installed skill ships no scripts, so `scripts\u002Flib\u002Fcodex-exec.sh` is absent\noutside a source checkout. Run `codex exec` directly instead, with bash or zsh\n(flags as of codex-cli 0.163.0; confirm with `codex exec --help`; add\n`--skip-git-repo-check` and `-o \u003Cfile>` as above):\n\n```bash\ncase \"${DEADLINE_EPOCH:-}\" in ''|0*|*[!0-9]*) echo \"no valid deadline; not launched\" >&2; exit 2;; esac\nTO=$(command -v timeout || command -v gtimeout) || { echo \"no timeout; not launched\" >&2; exit 2; }\nremaining=$(( DEADLINE_EPOCH - $(date +%s) - 10 ))  # keep the 10 s KILL grace inside\n[ \"$remaining\" -gt 0 ] || { echo \"deadline passed or within 10 s; not launched\" >&2; exit 124; }\nset -o pipefail  # bash and zsh: $? is the failing stage, not head's\n\"$TO\" -k 10 \"$remaining\" \\\n  codex exec --ignore-user-config -C \"$WORKSPACE\" -s read-only - \u003C\"$PROMPT_FILE\" 2>&1 \\\n  | head -c 10485760 >\"$OUTPUT\"\nrc=$?  # 124 timed out, 137 killed after grace, 127 no codex, else codex's status\n```\n\nAn output file exactly at the cap was truncated, and its status reflects the\nclosed pipe, not a review. The fallback has no survivor check or echo\ndetection; report both as not enforced.\n\n## Exit codes (guarded library)\n\n| Exit | Meaning |\n|---|---|\n| 0 | Codex completed and produced output |\n| 2 | precondition: binary missing, bounds invalid or missing, capability unavailable, or cleanup unverified; not a result |\n| 122 | descendants survived Codex's exit; degraded run |\n| 123 | capture or prompt-preparation cap reached; partial evidence kept |\n| 124 | deadline expired, or a clean exit with empty output; a stall, not a result |\n| 125 | output repeats the prompt; not a result |\n| 128+N | cancelled by signal N (129 HUP, 130 INT, 143 TERM) |\n| other | Codex's own nonzero status, preserved |\n\nReserved codes are runtime evidence, never a semantic verdict. A Codex 124 or\n137 returns 124 with the STALL line; a Codex 2, 122, 123, 129, 130 or 143\nreturns with no `codex-exec:` stderr line, so check stderr, the capture and\nelapsed time before reading one as the runner's.\n[Guarded runner internals](references\u002Fguarded-runner.md) covers inputs, host\nrequirements, process supervision and the external sandbox wrapper.\n\n## Report, then stop\n\n```text\ncommand:  exact argv or library call (prompt by reference)\nsandbox:  -s value and the declared effect that needs it\nbound:    absolute deadline and seconds remaining at launch\ncapture:  output path, byte cap, truncated yes\u002Fno\nexit:     status and its meaning from the table\ncleanup:  library result, or \"not enforced\" for the direct fallback\nnot_as_briefed: steps the output reports refused or sandbox-limited, quoted | none reported\n```\n\nA Codex validator follows the\n[judgment receipt convention](..\u002Fvalidate\u002Freferences\u002Fjudgment-receipts.md)\nand the [model-dispatch recipe](..\u002Fvalidate\u002Freferences\u002Fmodel-dispatch.md#association-before-execution):\na requested model flag or the model's own description does not prove which\nmodel ran.\n\n- Use [claude-exec](..\u002Fclaude-exec\u002FSKILL.md) for one headless Claude prompt.\n- Use [agy-native](..\u002Fagy-native\u002FSKILL.md) when AGY is named.\n- Use [orchestrate](..\u002Forchestrate\u002FSKILL.md) for a batch of workers.\n",{"name":5,"consumes":46,"metadata":48,"produces":57,"practices":59,"context_rel":61,"description":7,"hexagonal_role":65,"user-invocable":66,"output_contract":67,"skill_api_version":68},[47],"codex-command-packet",{"tier":36,"effects":49,"stability":52,"disposition":53,"capabilities":54,"dependencies":56,"canonical_status":29},[50,51],"run_codex_process","sandbox_tiered_workspace_and_network_effects","stable","keep_optional_adapter",[55],"codex_exec",[],[58],"codex-run-output",[60],"pragmatic-programmer",[62],{"kind":63,"with":64},"supplier-to","validate","driving-adapter",true,"process exit status and captured Codex output artifact",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcodex-exec",491,"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.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":80,"prompt":90,"zipAvailable":66},[81,84,87],{"tool":82,"command":83},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill codex-exec",{"tool":85,"command":86},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill codex-exec",{"tool":88,"command":89},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill codex-exec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcodex-exec\u002FSKILL.md",[92],{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fguarded-runner.md","REFERENCE","参考文档",3897,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fcodex-exec\u002Freferences\u002Fguarded-runner.md",[99,107,114,121,147,172],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":106},"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":106},"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":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":120,"publishedAt":106},"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":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":41},"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",[],[128,129,130,131,132,133,134,135,136,137,138,23,139,140,141,142,143,144,145,146],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","you","done","reviewer","io","change","cli","merge","past",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":153,"publishedAt":41},"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",[],[154,155,156,142,157,158,159,160,161,162,163,164,165,166,133,167,168,169,170,171],"deja reflect","reflect","review","with","record","github","next","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":173,"name":174,"nameZh":6,"description":175,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":189,"publishedAt":41},"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",[178,183,186],{"categoryNo":179,"categoryName":180,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":184,"categoryName":185,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":187,"categoryName":188,"taxonomyType":181,"taxonomyTypeDesc":182},"01JBSEEDCAT000000000000010","后端与接口",[174,190,191,192,193,194,195,168,196,134,197,198,199,200,23,201,202,203,204,205],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]