[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6JWSZNXPQ6JCBFHCSJJP3JJ":3,"skill-same:01M6JWSZNXPQ6JCBFHCSJJP3JJ":82},{"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":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6JWSZNXPQ6JCBFHCSJJP3JJ","dev-fix",null,"Investigate bugs, regressions, failing tests, or broken behavior by tracing evidence to the root cause, then implement and verify a scoped fix when requested. For explanation-only requests, diagnose without editing. Does not handle new feature design or commit-message-only requests.","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\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-fix\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"dev","fix","dev fix","new","design","failing","when","root cause","scoped","bugs","for","feature design","feature","tests","message","evidence","only","broken","editing","investigate","tracing","diagnose","commit","implement","2026-11-10 10:12:30",false,"---\nname: dev-fix\ndescription: Investigate bugs, regressions, failing tests, or broken behavior by tracing evidence to the root cause, then implement and verify a scoped fix when requested. For explanation-only requests, diagnose without editing. Does not handle new feature design or commit-message-only requests.\n---\n\n# Dev Fix\n\nTrace the failure to the state or value that first violates the intended contract. Fix the supported cause, and verify the original symptom rather than treating a plausible patch as proof.\n\n## Load baseline\n\nRead [references\u002Fdev-baseline.md](references\u002Fdev-baseline.md) before execution. Resolve paths relative to this skill directory.\n\n## Scope and triage\n\n- Distinguish diagnosis-only requests from requests to fix. \"Why does this fail?\" or \"先别动代码\" authorizes investigation, not file edits.\n- Establish the symptom, expected behavior, trigger, and relevant environment from the request, logs, code, and recent changes. Investigate available evidence before asking for missing facts; continue independent work while a necessary clarification is pending.\n- `--quick` requests a concise investigation; `--deep` requests deeper diagnosis and an RCA. Adapt depth to evidence and consequence without fixed hypothesis counts, fabricated probabilities, or mode-confirmation exchanges.\n- Before any write, identify the actual repository root, branch, working tree, and index. Preserve existing edits and partial staging. Use an isolated checkout when useful and authorized by task scope; do not force a worktree question or treat unrelated dirty files as a reason to stop.\n\n## Reproduce and trace\n\nCapture the smallest faithful reproduction available: preferably an automated failing regression test, otherwise a command, request, trace, or repeatable UI\u002Fdevice action. Failure to reproduce locally is a limitation to investigate, not a prohibition on reading code or collecting logs.\n\nFor intermittent failures, record observed frequency and control the relevant event ordering. Prefer deterministic barriers, fake clocks, or condition-based waits over arbitrary sleeps. Repeat only enough to characterize uncertainty; three failures alone do not prove reliability.\n\nTrace the actual data\u002Fcontrol path from trigger to failure, including callers, transformations, serialization, configuration, generated clients, and external boundaries when relevant. Follow bad state backward to where it first violates the contract. A guard at the crash site is insufficient when the bad value originates upstream.\n\nUse competing hypotheses only where there is real uncertainty. For each useful hypothesis, identify a predicted observation, collect discriminating evidence, and update its status. Existing logs and debugging tools may suffice; add temporary instrumentation only when it resolves a specific gap, without exposing secrets or changing timing unnecessarily.\n\nWhen repeated attempts fail, reassess assumptions and choose a different evidence source or independent diagnostic pass. Do not infer an architectural defect from an arbitrary attempt count. Pause dependent edits only when the remaining decision exceeds task scope, changes a user-facing contract, or requires unavailable access; state the concrete blocker.\n\n## Fix and regression evidence\n\nWhen a fix is requested and the causal explanation is supported:\n\n1. Prefer a regression test that fails for the original symptom before editing production code. Existing failing tests may already provide this evidence.\n2. Change the cause and directly required callers or restore\u002Fsave paths together. Avoid speculative fallbacks and unrelated cleanup. Add boundary validation only when necessary to establish the intended invariant.\n3. Rerun the original reproduction, then checks covering affected neighboring behavior. Scale wider testing to blast radius and project requirements.\n4. Remove temporary instrumentation introduced for this investigation and rerun affected checks if removal changes executable code. Preserve intentional project logging.\n\nIf an automated regression is infeasible, use the strongest feasible proof and say exactly what remains unverified. A code-level test is not evidence of a real device, production service, or authenticated browser succeeding.\n\nAn observed red result before the fix followed by green is normally sufficient. Use isolated mutation\u002Freversal testing only if test sensitivity remains uncertain: retain the test, reverse only this fix in a temporary copy, observe the expected failure, then verify the final implementation. Never use a blanket `git stash`, `git reset`, or checkout restoration on shared user changes to manufacture proof.\n\n## SDD Contract and report\n\nThe failure contract is: symptom and expectation, reproduction, causal trace, fix, regression evidence, and remaining limits. Use it to align with relevant existing SDD spec\u002Fplan artifacts; the latest user correction governs.\n\nFor a short fix, report that contract concisely in the answer. Maintain `.claude\u002Fartifacts\u002Ffixes\u002F\u003Cbug-slug>.md` when requested, required by the project, or useful for a substantial investigation's durable handoff. Record status accurately, such as `FIXED`, `DIAGNOSED`, `PARTIALLY_VERIFIED`, or `BLOCKED`; include only observed commands\u002Fresults, and never invent an introduction commit or RCA history.\n\nSearch for analogous defects when the root cause plausibly recurs; report out-of-scope findings separately. Finish authorized investigation\u002Ffix work without requiring the user to manually invoke another skill. Use `dev-plan` or equivalent reasoning when design work is needed within scope; use `dev-verify` or equivalent checks before a completion claim. Bug regression work stays here and does not require a second TDD workflow.\n\nFor examples of diagnosis-only work, deterministic reproduction, and evidence limits, read [examples.md](examples.md) when useful.\n\n## Multi-Agent Profile\n\nRecommended agent_type: worker\n\nWhen delegation is permitted, assign a bounded failure path or independent hypothesis with explicit read\u002Fwrite ownership. Workers report raw observations, the causal trace, changed files, and verification limits. A separate reviewer\u002Fverifier evaluates the resulting fix rather than rubber-stamping the author's diagnosis.\n\nWhen this repository is available, consult `docs\u002Fmulti-agent-policy.md` for additional coordination conventions. Standalone installations use the ownership and evidence rules above.\n","# Dev Fix\n\nTrace the failure to the state or value that first violates the intended contract. Fix the supported cause, and verify the original symptom rather than treating a plausible patch as proof.\n\n## Load baseline\n\nRead [references\u002Fdev-baseline.md](references\u002Fdev-baseline.md) before execution. Resolve paths relative to this skill directory.\n\n## Scope and triage\n\n- Distinguish diagnosis-only requests from requests to fix. \"Why does this fail?\" or \"先别动代码\" authorizes investigation, not file edits.\n- Establish the symptom, expected behavior, trigger, and relevant environment from the request, logs, code, and recent changes. Investigate available evidence before asking for missing facts; continue independent work while a necessary clarification is pending.\n- `--quick` requests a concise investigation; `--deep` requests deeper diagnosis and an RCA. Adapt depth to evidence and consequence without fixed hypothesis counts, fabricated probabilities, or mode-confirmation exchanges.\n- Before any write, identify the actual repository root, branch, working tree, and index. Preserve existing edits and partial staging. Use an isolated checkout when useful and authorized by task scope; do not force a worktree question or treat unrelated dirty files as a reason to stop.\n\n## Reproduce and trace\n\nCapture the smallest faithful reproduction available: preferably an automated failing regression test, otherwise a command, request, trace, or repeatable UI\u002Fdevice action. Failure to reproduce locally is a limitation to investigate, not a prohibition on reading code or collecting logs.\n\nFor intermittent failures, record observed frequency and control the relevant event ordering. Prefer deterministic barriers, fake clocks, or condition-based waits over arbitrary sleeps. Repeat only enough to characterize uncertainty; three failures alone do not prove reliability.\n\nTrace the actual data\u002Fcontrol path from trigger to failure, including callers, transformations, serialization, configuration, generated clients, and external boundaries when relevant. Follow bad state backward to where it first violates the contract. A guard at the crash site is insufficient when the bad value originates upstream.\n\nUse competing hypotheses only where there is real uncertainty. For each useful hypothesis, identify a predicted observation, collect discriminating evidence, and update its status. Existing logs and debugging tools may suffice; add temporary instrumentation only when it resolves a specific gap, without exposing secrets or changing timing unnecessarily.\n\nWhen repeated attempts fail, reassess assumptions and choose a different evidence source or independent diagnostic pass. Do not infer an architectural defect from an arbitrary attempt count. Pause dependent edits only when the remaining decision exceeds task scope, changes a user-facing contract, or requires unavailable access; state the concrete blocker.\n\n## Fix and regression evidence\n\nWhen a fix is requested and the causal explanation is supported:\n\n1. Prefer a regression test that fails for the original symptom before editing production code. Existing failing tests may already provide this evidence.\n2. Change the cause and directly required callers or restore\u002Fsave paths together. Avoid speculative fallbacks and unrelated cleanup. Add boundary validation only when necessary to establish the intended invariant.\n3. Rerun the original reproduction, then checks covering affected neighboring behavior. Scale wider testing to blast radius and project requirements.\n4. Remove temporary instrumentation introduced for this investigation and rerun affected checks if removal changes executable code. Preserve intentional project logging.\n\nIf an automated regression is infeasible, use the strongest feasible proof and say exactly what remains unverified. A code-level test is not evidence of a real device, production service, or authenticated browser succeeding.\n\nAn observed red result before the fix followed by green is normally sufficient. Use isolated mutation\u002Freversal testing only if test sensitivity remains uncertain: retain the test, reverse only this fix in a temporary copy, observe the expected failure, then verify the final implementation. Never use a blanket `git stash`, `git reset`, or checkout restoration on shared user changes to manufacture proof.\n\n## SDD Contract and report\n\nThe failure contract is: symptom and expectation, reproduction, causal trace, fix, regression evidence, and remaining limits. Use it to align with relevant existing SDD spec\u002Fplan artifacts; the latest user correction governs.\n\nFor a short fix, report that contract concisely in the answer. Maintain `.claude\u002Fartifacts\u002Ffixes\u002F\u003Cbug-slug>.md` when requested, required by the project, or useful for a substantial investigation's durable handoff. Record status accurately, such as `FIXED`, `DIAGNOSED`, `PARTIALLY_VERIFIED`, or `BLOCKED`; include only observed commands\u002Fresults, and never invent an introduction commit or RCA history.\n\nSearch for analogous defects when the root cause plausibly recurs; report out-of-scope findings separately. Finish authorized investigation\u002Ffix work without requiring the user to manually invoke another skill. Use `dev-plan` or equivalent reasoning when design work is needed within scope; use `dev-verify` or equivalent checks before a completion claim. Bug regression work stays here and does not require a second TDD workflow.\n\nFor examples of diagnosis-only work, deterministic reproduction, and evidence limits, read [examples.md](examples.md) when useful.\n\n## Multi-Agent Profile\n\nRecommended agent_type: worker\n\nWhen delegation is permitted, assign a bounded failure path or independent hypothesis with explicit read\u002Fwrite ownership. Workers report raw observations, the causal trace, changed files, and verification limits. A separate reviewer\u002Fverifier evaluates the resulting fix rather than rubber-stamping the author's diagnosis.\n\nWhen this repository is available, consult `docs\u002Fmulti-agent-policy.md` for additional coordination conventions. Standalone installations use the ownership and evidence rules above.\n",{"name":5,"description":7},"main","b0f0a87593c578a7898eccaf1b363f7f87c1f99b","plugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-fix",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill dev-fix",{"tool":64,"command":65},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill dev-fix",{"tool":67,"command":68},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill dev-fix","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-fix\u002FSKILL.md",true,[72,78],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"examples.md","REFERENCE","参考文档",2481,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-fix\u002Fexamples.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fdev-baseline.md",3571,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FJason-chen-coder\u002Fdev-skills\u002Fskills\u002Fdev-fix\u002Freferences\u002Fdev-baseline.md",[83,93,101,109,117,125],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":88,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":92},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":92},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":92},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":87,"licenseFileUrl":113,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":92},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\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":87,"licenseFileUrl":121,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":92},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\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":87,"licenseFileUrl":129,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":92},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]