[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MEQNAC1YSF8CVFAFA27F9R":3,"skill-same:01M6MEQNAC1YSF8CVFAFA27F9R":102},{"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":40,"linkOnly":41,"markdownContent":42,"markdownBody":43,"frontMatter":44,"refName":79,"commitSha":80,"skillDirectory":81,"forksCount":82,"repositoryHtmlUrl":83,"repositoryHomepageUrl":84,"ownerHtmlUrl":85,"ownerBlogUrl":86,"ownerDescription":87,"updatedAt":88,"install":89,"resources":101},"01M6MEQNAC1YSF8CVFAFA27F9R","navigate",null,"Pick the next work in an epic or bead graph; closed is not proven. Use when: asked what is next or whether an epic is done.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1571,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fnavigate\u002FSKILL.md",[],[5,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39],"observe","when","result","ratchet","native","churn","bounded-context","next","done","craft","customer","goal","lean","work","pick","select","open","ddd","orchestrate","acceptance","update","2026-11-10 10:12:30",false,"---\nname: navigate\ndescription: 'Pick the next work in an epic or bead graph; closed is not proven. Use when: asked what is next or whether an epic is done.'\npractices: [lean-startup, bdd-gherkin, ddd-bounded-context]\nhexagonal_role: supporting\nconsumes: [outer-goal-prompt, goal-acceptance, native-work-state, validation-result]\nproduces: [native-handoffs]\ncontext_rel: [{kind: customer-of, with: craft-goal}, {kind: supplier-to, with: orchestrate}]\nskill_api_version: 1\nuser-invocable: true\nmetadata:\n  tier: execution\n  dependencies: []\n  capabilities: [observe_work_graph, select_next_wave, ratchet_work_graph, report_graph_hygiene]\n  effects: [update_native_graph]\n  canonical_status: canonical\n  disposition: keep_strategy\n  stability: stable\noutput_contract: 'wave checkpoint in the existing handoff or root epic: acceptance matrix, frontier, wave and reasons, ratchets and churn, budget, helper use and native state, next thesis, open decisions; a single pass returns it with hygiene findings and writes nothing'\n---\n\n# Navigate\n\nPick the next wave (the ready beads run together next) on a bead graph and\nkeep the graph honest toward its frozen acceptance. The root epic holds\nacceptance; each child build bead is one experiment; a decision bead goes to\nthe resolver it names ([Foggy epics](#foggy-epics)). Navigate picks and\nrecords, and never edits acceptance, dispatches, judges or closes:\n[Plan](..\u002Fplan\u002FSKILL.md) shapes, [Orchestrate](..\u002Forchestrate\u002FSKILL.md)\ndispatches, native execution (the caller's coding agent and shell) or an\noptional [RPI](..\u002Frpi\u002FSKILL.md) run builds, [Validate](..\u002Fvalidate\u002FSKILL.md)\njudges, and Craft Goal owns the prompt and HOLD (the goal's stop on a\ndeclared trigger, so the cause can be examined before more work runs). What\nto build when no epic exists yet is [Idea Genie](..\u002Fidea-genie\u002FSKILL.md)'s.\n\n**One pass**, when a person asks what is next on an epic: steps 1 and 2 plus\n[hygiene](#hygiene), returning the wave in the step 4 shape instead of handing\nit off. Write nothing; change edges only on the caller's go-ahead; stop after\none pass. **Each wave of a running goal:** steps 1 to 4.\n\n## Rules that decide the pick\n\n- **Closed is not proven.** Only cited evidence for a criterion proves its row:\n  the passing check that exercises it, or the Validate PASS where a fresh read\n  was required. Closed status, a merge or an approving note leaves it open.\n- **Serve an open row.** Pick only ready beads that serve an open criterion or\n  a named blocking uncertainty; a bead tied to none is a hygiene finding.\n- **Stay disjoint.** Picked write and generated scopes overlap neither each\n  other nor any in-flight bead; an overlapping ready bead waits.\n- **Ready is a tracker state.** An empty ready list does not prove completion;\n  a closed prerequisite with missing or stale bytes (the output it claims is\n  absent or out of date) is not usable readiness.\n\n## Speak the domain\n\n- **BDD:** each criterion is a Given\u002FWhen\u002FThen example with an observable\n  result. Each bead names the example it moves; a bead that lacks one gets\n  Plan before it is built.\n- **DDD:** the root epic defines each domain term once, in one line. Titles,\n  examples, code and tests reuse that exact word. A synonym is a hygiene\n  finding; [Domain](..\u002Fdomain\u002FSKILL.md) settles disputes.\n- Write a bead as its title, then its id: `Locale fallback test (ag-12)`.\n\n## Bead graph contract\n\nRoot epic: outcome, acceptance examples, non-goals, authority, domain terms.\nChild bead: the question and the criterion or uncertainty it serves; method,\nexpected observation, falsifier, scope, non-goals; notes enough to resume\nafter compaction; verdict, evidence refs, learning.\n\nEdges: `parent-child` for membership, `blocks` only for real ordering, `related`\nfor alternatives, `discovered-from` for provenance. The tracker owns status and\nclosing. BD (Beads) is the example; any tracker with status, dependencies and\nnotes fits. With BD, run `bd context --json` before any write. Beads Viewer\n(`bv`) rank is advice; live BD beats it and any saved plan.\n\n## 1. Observe\n\n```bash\nbd context --json                   # verify the destination first\nbd show \u003Cepic>                      # outcome, acceptance, domain terms\nbd children \u003Cepic>                  # direct children only; recurse into child epics\nbd ready --parent \u003Cepic> --json     # ready frontier across descendants\nbd blocked --parent \u003Cepic>          # blocked work\nbd show \u003Cbead>; bd comments \u003Cbead>  # prior verdicts and evidence refs\n```\n\nBuild the acceptance matrix (criterion, evidence, status) under the rules\nabove; note in-flight beads with their scopes and any result limit you hit.\nDone when every criterion has a row and every open row names its bead, blocker\nor gap.\n\n## 2. Pick the wave\n\nWhen every row is proven, or no ready bead serves an open row, pick nothing,\nsay which, and go to step 4. Otherwise pick the smallest set of ready beads\nwith the most decision-relevant information that meets the rules above and\nfits the declared wave budget; no budget means one bead. Prefer an early\nfalsifier.\n\nHand each build bead to native execution, or to one RPI when the goal or\ncaller selects it: through Orchestrate when delegation is\nauthorized, one bead per worker, otherwise the caller's runtime. Its checks\nand CI are its result; it gets one fresh, author-distinct Validate only on\n[Validate's triggers](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it),\nand a repair does not start another. A [decision bead](#foggy-epics) goes to\nthe resolver it names, never to an implementer; one that needs the caller's\nanswer goes under decisions in the checkpoint. Done when each picked bead has a\none-line reason and a named handoff.\n\n## 3. Ratchet the graph\n\nRecord each result unchanged on its bead: the check facts, and the verdict when\none was obtained. For example\n`bd update \u003Cid> --append-notes \"verdict: FAIL; evidence: \u003Crefs>; learned: \u003Cdecision it changes>\"`.\nUpdate its matrix row, then classify each discovery:\n\n| Discovery | Action |\n|---|---|\n| **necessary-now**: needed for frozen acceptance, within authority and budget | `bd create \"\u003Ctitle>\" --parent \u003Cepic> --deps discovered-from:\u003Cid> --acceptance \"\u003Cexample it serves>\"` |\n| **linked-follow-up**: useful later | note or link it outside the epic; never run it in this goal |\n| **HOLD\u002Frescope**: changes acceptance, exceeds authority or budget | HOLD; the goal's breaker (the HOLD triggers its prompt declares) takes over |\n\nA result ratchets when it proves part of acceptance, falsifies a live\nhypothesis with discriminating evidence, or resolves an uncertainty so the next\nexperiment differs; FAIL and NOT_PROVEN can ratchet. Commits, counts, digests,\nrewritten plans and red with no new information are churn. Split old defects\nfrom regressions by before\u002Fafter reproduction or equivalent causal evidence\nunder the same acceptance; counts, timestamps and new ids prove no cause.\nUnknown cause, a reopened finding or recurrence of a closed finding class is\nHOLD, not proof the design is wrong. Never downgrade a necessary-now discovery to\nlinked-follow-up; no wave, helper, retry or compaction resets the goal's budget\ntotals. Done when every result sits on its bead and every discovery has a class.\n\n## 4. Checkpoint\n\nAppend this block to the existing handoff or root epic notes; no new artifact.\nStop after appending it: the goal continues, holds or ends. A one-pass reply\ndrops the Ratchets, Budget and Helper lines and writes nothing.\n\n```text\nAcceptance: \u003Cid> \u003Ccriterion as written>: proven (\u003Ccheck or PASS ref>)\n            \u003Cid> \u003Ccriterion as written>: open (\u003Cbead title> \u003Cid>, or the gap)\nFrontier:   \u003Cready beads, by title>\nWave:       \u003Cbead title>: \u003Crow or uncertainty it serves>; or none: \u003Cwhy>\nRatchets:   \u003Cresults that changed a decision>; churn: \u003Cresults that did not>\nFog:        \u003Cproposed decision beads>; questions: \u003Cnot yet beads>; ruled out: \u003Cwork>; or none\nHygiene:    \u003Cone finding per line>, or none\nBudget:     \u003Cremaining if measured, else unmeasured>\nHelper:     \u003CHOLD incident and helper use, or none>; native state: \u003Cobserved continue\u002Fstop>\nNext:       \u003Cthesis>; decisions: \u003Copen questions for the caller>\n```\n\n## Foggy epics\n\nWhen the outcome is clear but the way there is not, the next beads are\ndecisions, not build slices. Each open question becomes a decision bead whose\nanswer is a choice, sized to one session, naming how it resolves: a cited\nfact (Research), a rough artifact the caller reacts to (Plan's probes and\nprototypes), a conversation with the caller (Interview), or a manual step that\nonly unblocks a decision. Give it the tracker's decision type, never a build or\nagent-ready label (with BD, `bd create --type decision`, or\n`bd update \u003Cid> --type decision --remove-label agent-ready` for a decision\nalready filed as build work). Plain `bd ready` lists decisions too; pull build\nwork with `bd ready --parent \u003Cepic> --exclude-type decision`. A question that\nneeds the caller's own answer resolves only with the caller; never answer it\non their behalf, whether by a default, a recommendation or filing it as\nruled-out work.\n\nTrack two lists with the root epic: in-scope questions not yet specific\nenough to become beads, which graduate as the frontier moves, and work ruled\nout by the caller or the epic's non-goals, which does not come back without\nthe caller. Record each resolved decision as one line plus its bead, not a\nrestatement. The fog has lifted when no decision stands between the graph and\nbuild beads with acceptance examples; hand those to Plan.\n\nIn a one-pass reply, return the proposed decision beads and both lists in the\ncheckpoint's Fog line and write nothing. In a running goal, create beads and\nappend notes through step 3, within authority and the declared wave budget;\ndecision beads count against that budget like any other.\n\n## Hygiene\n\nReport cycles among the epic's beads (`bd dep cycles`, filtered to them),\nbeads tied to no criterion, `blocks` edges that are not real ordering,\ncriteria not in Given\u002FWhen\u002FThen form or with no observable result (an open\ndecision the caller can settle with Interview; never rewrite one), closed\nbeads with missing bytes, decision beads typed as build work, and drifted\nterms. `bd graph \u003Cepic>` shows the shape. Change edges only on the caller's\ngo-ahead.\n","# Navigate\n\nPick the next wave (the ready beads run together next) on a bead graph and\nkeep the graph honest toward its frozen acceptance. The root epic holds\nacceptance; each child build bead is one experiment; a decision bead goes to\nthe resolver it names ([Foggy epics](#foggy-epics)). Navigate picks and\nrecords, and never edits acceptance, dispatches, judges or closes:\n[Plan](..\u002Fplan\u002FSKILL.md) shapes, [Orchestrate](..\u002Forchestrate\u002FSKILL.md)\ndispatches, native execution (the caller's coding agent and shell) or an\noptional [RPI](..\u002Frpi\u002FSKILL.md) run builds, [Validate](..\u002Fvalidate\u002FSKILL.md)\njudges, and Craft Goal owns the prompt and HOLD (the goal's stop on a\ndeclared trigger, so the cause can be examined before more work runs). What\nto build when no epic exists yet is [Idea Genie](..\u002Fidea-genie\u002FSKILL.md)'s.\n\n**One pass**, when a person asks what is next on an epic: steps 1 and 2 plus\n[hygiene](#hygiene), returning the wave in the step 4 shape instead of handing\nit off. Write nothing; change edges only on the caller's go-ahead; stop after\none pass. **Each wave of a running goal:** steps 1 to 4.\n\n## Rules that decide the pick\n\n- **Closed is not proven.** Only cited evidence for a criterion proves its row:\n  the passing check that exercises it, or the Validate PASS where a fresh read\n  was required. Closed status, a merge or an approving note leaves it open.\n- **Serve an open row.** Pick only ready beads that serve an open criterion or\n  a named blocking uncertainty; a bead tied to none is a hygiene finding.\n- **Stay disjoint.** Picked write and generated scopes overlap neither each\n  other nor any in-flight bead; an overlapping ready bead waits.\n- **Ready is a tracker state.** An empty ready list does not prove completion;\n  a closed prerequisite with missing or stale bytes (the output it claims is\n  absent or out of date) is not usable readiness.\n\n## Speak the domain\n\n- **BDD:** each criterion is a Given\u002FWhen\u002FThen example with an observable\n  result. Each bead names the example it moves; a bead that lacks one gets\n  Plan before it is built.\n- **DDD:** the root epic defines each domain term once, in one line. Titles,\n  examples, code and tests reuse that exact word. A synonym is a hygiene\n  finding; [Domain](..\u002Fdomain\u002FSKILL.md) settles disputes.\n- Write a bead as its title, then its id: `Locale fallback test (ag-12)`.\n\n## Bead graph contract\n\nRoot epic: outcome, acceptance examples, non-goals, authority, domain terms.\nChild bead: the question and the criterion or uncertainty it serves; method,\nexpected observation, falsifier, scope, non-goals; notes enough to resume\nafter compaction; verdict, evidence refs, learning.\n\nEdges: `parent-child` for membership, `blocks` only for real ordering, `related`\nfor alternatives, `discovered-from` for provenance. The tracker owns status and\nclosing. BD (Beads) is the example; any tracker with status, dependencies and\nnotes fits. With BD, run `bd context --json` before any write. Beads Viewer\n(`bv`) rank is advice; live BD beats it and any saved plan.\n\n## 1. Observe\n\n```bash\nbd context --json                   # verify the destination first\nbd show \u003Cepic>                      # outcome, acceptance, domain terms\nbd children \u003Cepic>                  # direct children only; recurse into child epics\nbd ready --parent \u003Cepic> --json     # ready frontier across descendants\nbd blocked --parent \u003Cepic>          # blocked work\nbd show \u003Cbead>; bd comments \u003Cbead>  # prior verdicts and evidence refs\n```\n\nBuild the acceptance matrix (criterion, evidence, status) under the rules\nabove; note in-flight beads with their scopes and any result limit you hit.\nDone when every criterion has a row and every open row names its bead, blocker\nor gap.\n\n## 2. Pick the wave\n\nWhen every row is proven, or no ready bead serves an open row, pick nothing,\nsay which, and go to step 4. Otherwise pick the smallest set of ready beads\nwith the most decision-relevant information that meets the rules above and\nfits the declared wave budget; no budget means one bead. Prefer an early\nfalsifier.\n\nHand each build bead to native execution, or to one RPI when the goal or\ncaller selects it: through Orchestrate when delegation is\nauthorized, one bead per worker, otherwise the caller's runtime. Its checks\nand CI are its result; it gets one fresh, author-distinct Validate only on\n[Validate's triggers](..\u002Fvalidate\u002FSKILL.md#when-a-fresh-judgment-is-worth-it),\nand a repair does not start another. A [decision bead](#foggy-epics) goes to\nthe resolver it names, never to an implementer; one that needs the caller's\nanswer goes under decisions in the checkpoint. Done when each picked bead has a\none-line reason and a named handoff.\n\n## 3. Ratchet the graph\n\nRecord each result unchanged on its bead: the check facts, and the verdict when\none was obtained. For example\n`bd update \u003Cid> --append-notes \"verdict: FAIL; evidence: \u003Crefs>; learned: \u003Cdecision it changes>\"`.\nUpdate its matrix row, then classify each discovery:\n\n| Discovery | Action |\n|---|---|\n| **necessary-now**: needed for frozen acceptance, within authority and budget | `bd create \"\u003Ctitle>\" --parent \u003Cepic> --deps discovered-from:\u003Cid> --acceptance \"\u003Cexample it serves>\"` |\n| **linked-follow-up**: useful later | note or link it outside the epic; never run it in this goal |\n| **HOLD\u002Frescope**: changes acceptance, exceeds authority or budget | HOLD; the goal's breaker (the HOLD triggers its prompt declares) takes over |\n\nA result ratchets when it proves part of acceptance, falsifies a live\nhypothesis with discriminating evidence, or resolves an uncertainty so the next\nexperiment differs; FAIL and NOT_PROVEN can ratchet. Commits, counts, digests,\nrewritten plans and red with no new information are churn. Split old defects\nfrom regressions by before\u002Fafter reproduction or equivalent causal evidence\nunder the same acceptance; counts, timestamps and new ids prove no cause.\nUnknown cause, a reopened finding or recurrence of a closed finding class is\nHOLD, not proof the design is wrong. Never downgrade a necessary-now discovery to\nlinked-follow-up; no wave, helper, retry or compaction resets the goal's budget\ntotals. Done when every result sits on its bead and every discovery has a class.\n\n## 4. Checkpoint\n\nAppend this block to the existing handoff or root epic notes; no new artifact.\nStop after appending it: the goal continues, holds or ends. A one-pass reply\ndrops the Ratchets, Budget and Helper lines and writes nothing.\n\n```text\nAcceptance: \u003Cid> \u003Ccriterion as written>: proven (\u003Ccheck or PASS ref>)\n            \u003Cid> \u003Ccriterion as written>: open (\u003Cbead title> \u003Cid>, or the gap)\nFrontier:   \u003Cready beads, by title>\nWave:       \u003Cbead title>: \u003Crow or uncertainty it serves>; or none: \u003Cwhy>\nRatchets:   \u003Cresults that changed a decision>; churn: \u003Cresults that did not>\nFog:        \u003Cproposed decision beads>; questions: \u003Cnot yet beads>; ruled out: \u003Cwork>; or none\nHygiene:    \u003Cone finding per line>, or none\nBudget:     \u003Cremaining if measured, else unmeasured>\nHelper:     \u003CHOLD incident and helper use, or none>; native state: \u003Cobserved continue\u002Fstop>\nNext:       \u003Cthesis>; decisions: \u003Copen questions for the caller>\n```\n\n## Foggy epics\n\nWhen the outcome is clear but the way there is not, the next beads are\ndecisions, not build slices. Each open question becomes a decision bead whose\nanswer is a choice, sized to one session, naming how it resolves: a cited\nfact (Research), a rough artifact the caller reacts to (Plan's probes and\nprototypes), a conversation with the caller (Interview), or a manual step that\nonly unblocks a decision. Give it the tracker's decision type, never a build or\nagent-ready label (with BD, `bd create --type decision`, or\n`bd update \u003Cid> --type decision --remove-label agent-ready` for a decision\nalready filed as build work). Plain `bd ready` lists decisions too; pull build\nwork with `bd ready --parent \u003Cepic> --exclude-type decision`. A question that\nneeds the caller's own answer resolves only with the caller; never answer it\non their behalf, whether by a default, a recommendation or filing it as\nruled-out work.\n\nTrack two lists with the root epic: in-scope questions not yet specific\nenough to become beads, which graduate as the frontier moves, and work ruled\nout by the caller or the epic's non-goals, which does not come back without\nthe caller. Record each resolved decision as one line plus its bead, not a\nrestatement. The fog has lifted when no decision stands between the graph and\nbuild beads with acceptance examples; hand those to Plan.\n\nIn a one-pass reply, return the proposed decision beads and both lists in the\ncheckpoint's Fog line and write nothing. In a running goal, create beads and\nappend notes through step 3, within authority and the declared wave budget;\ndecision beads count against that budget like any other.\n\n## Hygiene\n\nReport cycles among the epic's beads (`bd dep cycles`, filtered to them),\nbeads tied to no criterion, `blocks` edges that are not real ordering,\ncriteria not in Given\u002FWhen\u002FThen form or with no observable result (an open\ndecision the caller can settle with Interview; never rewrite one), closed\nbeads with missing bytes, decision beads typed as build work, and drifted\nterms. `bd graph \u003Cepic>` shows the shape. Change edges only on the caller's\ngo-ahead.\n",{"name":5,"consumes":45,"metadata":50,"produces":63,"practices":65,"context_rel":69,"description":7,"hexagonal_role":75,"user-invocable":76,"output_contract":77,"skill_api_version":78},[46,47,48,49],"outer-goal-prompt","goal-acceptance","native-work-state","validation-result",{"tier":51,"effects":52,"stability":54,"disposition":55,"capabilities":56,"dependencies":61,"canonical_status":62},"execution",[53],"update_native_graph","stable","keep_strategy",[57,58,59,60],"observe_work_graph","select_next_wave","ratchet_work_graph","report_graph_hygiene",[],"canonical",[64],"native-handoffs",[66,67,68],"lean-startup","bdd-gherkin","ddd-bounded-context",[70,73],{"kind":71,"with":72},"customer-of","craft-goal",{"kind":74,"with":37},"supplier-to","supporting",true,"wave checkpoint in the existing handoff or root epic: acceptance matrix, frontier, wave and reasons, ratchets and churn, budget, helper use and native state, next thesis, open decisions; a single pass returns it with hygiene findings and writes nothing",1,"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fnavigate",490,"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 02:12:02",{"source":8,"skillName":5,"commands":90,"prompt":100,"zipAvailable":76},[91,94,97],{"tool":92,"command":93},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill navigate",{"tool":95,"command":96},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill navigate",{"tool":98,"command":99},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill navigate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fboshu2\u002Fagentops\u002Fskills\u002Fnavigate\u002FSKILL.md",[],[103,111,118,125,150,174],{"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":110},"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"publishedAt":110},"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":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":110},"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":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":40},"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",[],[132,133,134,135,136,137,138,139,140,141,142,20,143,27,144,145,146,147,148,149],"search","deja search","never","error","ready","memory","re","decide","fix","design","debugging","you","reviewer","io","change","cli","merge","past",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":40},"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",[],[157,158,159,145,160,161,162,26,163,164,165,166,167,168,137,169,170,171,172,173],"deja reflect","reflect","review","with","record","github","https","node","Rules","decisions","brew","remember","project rules","project","session","end","reflection",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":191,"publishedAt":40},"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",[180,185,188],{"categoryNo":181,"categoryName":182,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":186,"categoryName":187,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":189,"categoryName":190,"taxonomyType":183,"taxonomyTypeDesc":184},"01JBSEEDCAT000000000000010","后端与接口",[176,192,193,194,195,196,197,170,198,138,199,200,201,202,20,203,204,205,206,207],"URL","Video","short-form","standalone","PDF","viral","tiktok","short","social","MCP","song","image","mcp server","schedule","api","publish"]