[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AD42W1T0R05C204K9ATND0":3,"skill-same:01M6AD42W1T0R05C204K9ATND0":74},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":43,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M6AD42W1T0R05C204K9ATND0","agentic-workflows",null,"Route gh-aw design, creation, diagnosis, patching, active debugging, upgrades, and local SDLC issue requests to the right strategies.","github\u002Fgh-aw","github","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9919?v=4","01M6AC83DS133TPXFSP1DHNCC6","GitHub","01M6AD3VCZ4WKQSFSRTPN7N9DN",5636,"MIT","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagentic-workflows\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"agentic workflows","workflows","agentic","design","debugging","gh","patching","creation","upgrade","route","strategies","requests","active","diagnosis","2026-11-10 10:12:30",false,"---\nname: agentic-workflows\ndescription: Route gh-aw design, creation, diagnosis, patching, active debugging, upgrades, and local SDLC issue requests to the right strategies.\n---\n\n# Agentic Workflows Router\n\nUse this skill when a user asks to design, create, update, debug, or upgrade GitHub Agentic Workflows in this repository, or prepare a substantial issue for a local, self-contained SDLC.\n\nThis skill is a dispatcher: identify the task type, load the matching workflow prompt\u002Fskill file, and follow it directly. Keep responses concise and ask a clarifying question if the correct prompt is unclear.\n\nFor debugging sessions needing CLI setup or run-URL scoping, first load\n`https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F.github\u002Faw\u002Fdebug-bootstrap.md`; it bootstraps\nthe same shared strategy used by the debugging routes below.\n\nDebugging, incident, health, and failure-related optimization requests use the\nbootstrap's intent routing before generic update, upgrade, or optimization routes,\neven when the CLI is installed. Preserve the supplied guidance repository\u002Fref\nfor all debugging links and public raw fallbacks; URLs showing `main` below are\ndefaults only when no guidance revision is supplied. Reuse already-loaded guides.\nThe intent index is `.github\u002Faw\u002Fdebug-scenarios.md`; load only the selected\nspecialized route, not every debugging reference.\n\nRepository overlay (optional):\n- Load the target repository's `.github\u002Faw\u002Finstructions.md`, if present, after the matched prompt\u002Fskill. Use `@.github\u002Faw\u002Finstructions.md` only in a matching checkout; do not substitute a guidance-repository overlay.\n- Precedence: repository overlay instructions override upstream defaults when they conflict.\n\n## Load and route\n\nRead only the files needed for the selected task.\nUse a local guidance checkout only when its repository\u002Fref matches the requested guidance; otherwise use the resolved guidance repository\u002Fref (default `github\u002Fgh-aw`).\nIf GitHub API, `gh api`, or GitHub MCP downloads return HTTP 403 (including a token SAML-authorized for a different organization), do not retry with the same token. Fetch the public file without authentication from `https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F\u003Cpath>` instead, preserving its repository-relative path (including `.github\u002F`). For example: `curl --fail --silent --show-error --location 'https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F.github\u002Faw\u002Fcreate-agentic-workflow.md'`. Use the same fallback for referenced instructions and `SKILL.md` files; never send an Authorization header or token to the raw URL. If the public download fails, report that error rather than proceeding without the required instructions. This fallback is for public `github\u002Fgh-aw` content only, not private or enterprise repositories.\nAfter loading the matching workflow prompt or skill, follow it directly:\n- Design workflows from scratch via interview: `.github\u002Faw\u002Fdesigner.md`\n- Create new workflows: `.github\u002Faw\u002Fcreate-agentic-workflow.md`\n- Configure scheduled dreaming or consolidate persistent memory: `.github\u002Faw\u002Fcreate-agentic-workflow.md`, then `.github\u002Faw\u002Fmemory.md#scheduled-dreaming`; load `.github\u002Faw\u002Fdreaming.md` only when the decision and input scope justify implementation\n- Configure or add declarative engines: `.github\u002Faw\u002Fconfigure-agentic-engine.md`\n- Consume, author, or document third-party connectors: `.github\u002Faw\u002Fconnectors.md`\n- Create a new connector: `.github\u002Faw\u002Fconnectors.md#author-or-extend-a-declaration`, then the repository's `.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md` when available\n- Update existing workflows: `.github\u002Faw\u002Fupdate-agentic-workflow.md`\n- Diagnose, patch, audit, or actively debug workflows: `.github\u002Faw\u002Fdebug-agentic-workflow.md` (local-first strategy, evidence triage and live gates)\n- Analyze existing runs, logs, or recurring failures: `.github\u002Faw\u002Fanalyzing-runs.md`. General repository-wide debugging or optimization requests start here with failure clustering before selecting a workflow.\n- AWF model\u002Fendpoint 400s, silent cross-family sub-agent failures, `model: auto` failures, install-step 404s after a version pin, or questions about version fields: go directly to `.github\u002Faw\u002Fdebug-agentic-workflow.md#model-and-engine-misconfiguration` before suggesting model changes.\n- Upgrade workflows and fix deprecations: `.github\u002Faw\u002Fupgrade-agentic-workflows.md`\n- Create shared components or MCP wrappers: `.github\u002Faw\u002Fcreate-shared-agentic-workflow.md`\n- Create report-generating workflows: `.github\u002Faw\u002Freport.md`\n- Fix Dependabot manifest PRs: `.github\u002Faw\u002Fdependabot.md`\n- Analyze coverage workflows: `.github\u002Faw\u002Ftest-coverage.md`\n- Render compact markdown charts: `.github\u002Faw\u002Fasciicharts.md`\n- Map CLI commands to MCP usage: `.github\u002Faw\u002Fcli-commands.md`\n- Choose workflow architecture and patterns: `.github\u002Faw\u002Fpatterns.md`\n- Design, deploy, inspect or recover a Git-backed work queue: `.github\u002Faw\u002Fwork-queue.md`\n- Optimize token usage and cost: `.github\u002Faw\u002Ftoken-optimization.md`\n- Advanced cost controls without native settings (custom AIC allowances by server size or shared organization budget policies): read `docs\u002Fsrc\u002Fcontent\u002Fdocs\u002Freference\u002Fcost-management.md#configure-advanced-cost-controls-with-admission` ([published guidance](https:\u002F\u002Fgithub.github.com\u002Fgh-aw\u002Freference\u002Fcost-management\u002F#configure-advanced-cost-controls-with-admission)). Explain the external authority requirement and cooperative limits; do not invent frontmatter fields or promise hard caps, reservations, or mid-run cancellation.\n- Design long-running multi-agent research workflows: `.github\u002Faw\u002Fmulti-agent-research.md`\n- Add skills or agent plugins requested by the user (`skills:` \u002F `plugins:` frontmatter, never on-the-fly installs): `.github\u002Faw\u002Fskills.md`\n- Local SDLC issue bootstrap: `.github\u002Faw\u002Fsquad.md`\n\nWhen the task involves OTEL, OTLP, traces, observability backends, or telemetry-driven analysis, also read and follow `skills\u002Fotel-queries\u002FSKILL.md` after loading the matching workflow prompt or skill.\n\nWhen creating, updating, diagnosing or upgrading a workflow that uses `tools.work-queue`, also load `.github\u002Faw\u002Fwork-queue.md` after the primary prompt. Load deployment docs, operator reference or specification only when that task needs them.\n\nFor repository initialization or configuration involving third-party integrations,\nuse `.github\u002Faw\u002Fconnectors.md` and the selected editable declaration's\n`import-schema` and `connector-documentation` metadata. Discover local declarations,\nnormal local\u002Fpinned imports and matching `*-golden.md` consumers; do not invent a\nbuilt-in provider catalog. Use `gh aw connector \u003Cid> setup --file PATH` for\nphase-specific credential names\u002Fscopes and acquisition\u002Frenewal guidance.\nBind exact approved resources through `with`; secret NAMES only, never values.\nSelect reads\u002Fnative methods and staged safe outputs independently. Importing must\nnot enable capabilities, write credentials, broad grants or live webhook ingress.\nDerive network hosts from the selected contract, not provider-name guesses.\nToken acquisition\u002Frefresh, consent and real provider permissions remain external.\n\nWhen editing instructions, skills or their generators, keep the complete task\ncontract within the first 7,500 UTF-8 bytes (8,000-byte query limit). Front-load\nconstraints, routes, verification and stop conditions; defer examples and\ninventories. Preserve safety and exact schema\u002Fcommand names.\n\n\u003C!-- instruction-prefix-end -->\n\n## Optional reference inventory\n\n\u003Cdetails>\n\u003Csummary>Guidance file catalog\u003C\u002Fsummary>\n\nUse the task routes above first. This inventory is not required startup context.\n\n- `.github\u002Faw\u002Faction-container-substitutions.md`\n- `.github\u002Faw\u002Fagent-runtime-instructions.md`\n- `.github\u002Faw\u002Fagentic-chat.md`\n- `.github\u002Faw\u002Fagentic-workflows-mcp.md`\n- `.github\u002Faw\u002Fanalyzing-runs.md`\n- `.github\u002Faw\u002Fasciicharts.md`\n- `.github\u002Faw\u002Fcampaign.md`\n- `.github\u002Faw\u002Fcharts-trending.md`\n- `.github\u002Faw\u002Fcharts.md`\n- `.github\u002Faw\u002Fcli-commands.md`\n- `.github\u002Faw\u002Fcompat.md`\n- `.github\u002Faw\u002Fconfigure-agentic-engine.md`\n- `.github\u002Faw\u002Fconnectors.md`\n- `.github\u002Faw\u002Fcontext.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-design.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-evaluation.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-trigger-details.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-validation.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow.md`\n- `.github\u002Faw\u002Fcreate-shared-agentic-workflow.md`\n- `.github\u002Faw\u002Fdebug-agentic-workflow.md`\n- `.github\u002Faw\u002Fdebug-bootstrap.md`\n- `.github\u002Faw\u002Fdebug-compilation.md`\n- `.github\u002Faw\u002Fdebug-live-testing.md`\n- `.github\u002Faw\u002Fdebug-model-engine-misconfiguration.md`\n- `.github\u002Faw\u002Fdebug-playbook.md`\n- `.github\u002Faw\u002Fdebug-scenarios.md`\n- `.github\u002Faw\u002Fdebug-security-review.md`\n- `.github\u002Faw\u002Fdebug-workflow-evidence.md`\n- `.github\u002Faw\u002Fdebug-workflow-health.md`\n- `.github\u002Faw\u002Fdependabot.md`\n- `.github\u002Faw\u002Fdeployment-status.md`\n- `.github\u002Faw\u002Fdesigner-mappings.md`\n- `.github\u002Faw\u002Fdesigner.md`\n- `.github\u002Faw\u002Fdoctor.md`\n- `.github\u002Faw\u002Fdocumentation-workflows.md`\n- `.github\u002Faw\u002Fdreaming.md`\n- `.github\u002Faw\u002Fdrive-memory.md`\n- `.github\u002Faw\u002Fenclaves.md`\n- `.github\u002Faw\u002Fevals.md`\n- `.github\u002Faw\u002Fexperiments.md`\n- `.github\u002Faw\u002Fformal-methods.md`\n- `.github\u002Faw\u002Fgithub-agentic-workflows.md`\n- `.github\u002Faw\u002Fgithub-mcp-server-pagination.md`\n- `.github\u002Faw\u002Fgithub-mcp-server-tools.md`\n- `.github\u002Faw\u002Fgithub-mcp-server.md`\n- `.github\u002Faw\u002Fharbor.md`\n- `.github\u002Faw\u002Findex-search.md`\n- `.github\u002Faw\u002Finstructions.md`\n- `.github\u002Faw\u002Fintent.md`\n- `.github\u002Faw\u002Fjobs.md`\n- `.github\u002Faw\u002Fledger.md`\n- `.github\u002Faw\u002Flinter-workflows.md`\n- `.github\u002Faw\u002Fllms.md`\n- `.github\u002Faw\u002Floop.md`\n- `.github\u002Faw\u002Flsp.md`\n- `.github\u002Faw\u002Fmaintainer.md`\n- `.github\u002Faw\u002Fmcp-clis.md`\n- `.github\u002Faw\u002Fmemory-stateful-patterns.md`\n- `.github\u002Faw\u002Fmemory.md`\n- `.github\u002Faw\u002Fmessages.md`\n- `.github\u002Faw\u002Fmulti-agent-research.md`\n- `.github\u002Faw\u002Fnetwork.md`\n- `.github\u002Faw\u002Foptimize-agentic-workflow.md`\n- `.github\u002Faw\u002Fotel.md`\n- `.github\u002Faw\u002Fpatterns.md`\n- `.github\u002Faw\u002Fplaywright.md`\n- `.github\u002Faw\u002Fpr-reviewer.md`\n- `.github\u002Faw\u002Frelease-workflow.md`\n- `.github\u002Faw\u002Freport.md`\n- `.github\u002Faw\u002Fresponsible-ai.md`\n- `.github\u002Faw\u002Freuse.md`\n- `.github\u002Faw\u002Fsafe-outputs-automation.md`\n- `.github\u002Faw\u002Fsafe-outputs-content.md`\n- `.github\u002Faw\u002Fsafe-outputs-management.md`\n- `.github\u002Faw\u002Fsafe-outputs-runtime.md`\n- `.github\u002Faw\u002Fsafe-outputs.md`\n- `.github\u002Faw\u002Fserena-tool.md`\n- `.github\u002Faw\u002Fshared-safe-jobs.md`\n- `.github\u002Faw\u002Fskills.md`\n- `.github\u002Faw\u002Fsquad.md`\n- `.github\u002Faw\u002Fsubagents.md`\n- `.github\u002Faw\u002Fsyntax-agentic.md`\n- `.github\u002Faw\u002Fsyntax-checkout.md`\n- `.github\u002Faw\u002Fsyntax-core.md`\n- `.github\u002Faw\u002Fsyntax-engine.md`\n- `.github\u002Faw\u002Fsyntax-tools-imports.md`\n- `.github\u002Faw\u002Fsyntax.md`\n- `.github\u002Faw\u002Ftest-coverage.md`\n- `.github\u002Faw\u002Ftest-expression.md`\n- `.github\u002Faw\u002Ftoken-optimization-caching-budgets.md`\n- `.github\u002Faw\u002Ftoken-optimization-observability.md`\n- `.github\u002Faw\u002Ftoken-optimization.md`\n- `.github\u002Faw\u002Ftriggers.md`\n- `.github\u002Faw\u002Fupdate-agentic-workflow.md`\n- `.github\u002Faw\u002Fupgrade-agentic-workflows.md`\n- `.github\u002Faw\u002Fvisual-regression.md`\n- `.github\u002Faw\u002Fwork-queue.md`\n- `.github\u002Faw\u002Fworkflow-constraints.md`\n- `.github\u002Faw\u002Fworkflow-editing.md`\n- `.github\u002Faw\u002Fworkflow-patterns.md`\n\n\u003C\u002Fdetails>\n","# Agentic Workflows Router\n\nUse this skill when a user asks to design, create, update, debug, or upgrade GitHub Agentic Workflows in this repository, or prepare a substantial issue for a local, self-contained SDLC.\n\nThis skill is a dispatcher: identify the task type, load the matching workflow prompt\u002Fskill file, and follow it directly. Keep responses concise and ask a clarifying question if the correct prompt is unclear.\n\nFor debugging sessions needing CLI setup or run-URL scoping, first load\n`https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F.github\u002Faw\u002Fdebug-bootstrap.md`; it bootstraps\nthe same shared strategy used by the debugging routes below.\n\nDebugging, incident, health, and failure-related optimization requests use the\nbootstrap's intent routing before generic update, upgrade, or optimization routes,\neven when the CLI is installed. Preserve the supplied guidance repository\u002Fref\nfor all debugging links and public raw fallbacks; URLs showing `main` below are\ndefaults only when no guidance revision is supplied. Reuse already-loaded guides.\nThe intent index is `.github\u002Faw\u002Fdebug-scenarios.md`; load only the selected\nspecialized route, not every debugging reference.\n\nRepository overlay (optional):\n- Load the target repository's `.github\u002Faw\u002Finstructions.md`, if present, after the matched prompt\u002Fskill. Use `@.github\u002Faw\u002Finstructions.md` only in a matching checkout; do not substitute a guidance-repository overlay.\n- Precedence: repository overlay instructions override upstream defaults when they conflict.\n\n## Load and route\n\nRead only the files needed for the selected task.\nUse a local guidance checkout only when its repository\u002Fref matches the requested guidance; otherwise use the resolved guidance repository\u002Fref (default `github\u002Fgh-aw`).\nIf GitHub API, `gh api`, or GitHub MCP downloads return HTTP 403 (including a token SAML-authorized for a different organization), do not retry with the same token. Fetch the public file without authentication from `https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F\u003Cpath>` instead, preserving its repository-relative path (including `.github\u002F`). For example: `curl --fail --silent --show-error --location 'https:\u002F\u002Fraw.githubusercontent.com\u002Fgithub\u002Fgh-aw\u002Fmain\u002F.github\u002Faw\u002Fcreate-agentic-workflow.md'`. Use the same fallback for referenced instructions and `SKILL.md` files; never send an Authorization header or token to the raw URL. If the public download fails, report that error rather than proceeding without the required instructions. This fallback is for public `github\u002Fgh-aw` content only, not private or enterprise repositories.\nAfter loading the matching workflow prompt or skill, follow it directly:\n- Design workflows from scratch via interview: `.github\u002Faw\u002Fdesigner.md`\n- Create new workflows: `.github\u002Faw\u002Fcreate-agentic-workflow.md`\n- Configure scheduled dreaming or consolidate persistent memory: `.github\u002Faw\u002Fcreate-agentic-workflow.md`, then `.github\u002Faw\u002Fmemory.md#scheduled-dreaming`; load `.github\u002Faw\u002Fdreaming.md` only when the decision and input scope justify implementation\n- Configure or add declarative engines: `.github\u002Faw\u002Fconfigure-agentic-engine.md`\n- Consume, author, or document third-party connectors: `.github\u002Faw\u002Fconnectors.md`\n- Create a new connector: `.github\u002Faw\u002Fconnectors.md#author-or-extend-a-declaration`, then the repository's `.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md` when available\n- Update existing workflows: `.github\u002Faw\u002Fupdate-agentic-workflow.md`\n- Diagnose, patch, audit, or actively debug workflows: `.github\u002Faw\u002Fdebug-agentic-workflow.md` (local-first strategy, evidence triage and live gates)\n- Analyze existing runs, logs, or recurring failures: `.github\u002Faw\u002Fanalyzing-runs.md`. General repository-wide debugging or optimization requests start here with failure clustering before selecting a workflow.\n- AWF model\u002Fendpoint 400s, silent cross-family sub-agent failures, `model: auto` failures, install-step 404s after a version pin, or questions about version fields: go directly to `.github\u002Faw\u002Fdebug-agentic-workflow.md#model-and-engine-misconfiguration` before suggesting model changes.\n- Upgrade workflows and fix deprecations: `.github\u002Faw\u002Fupgrade-agentic-workflows.md`\n- Create shared components or MCP wrappers: `.github\u002Faw\u002Fcreate-shared-agentic-workflow.md`\n- Create report-generating workflows: `.github\u002Faw\u002Freport.md`\n- Fix Dependabot manifest PRs: `.github\u002Faw\u002Fdependabot.md`\n- Analyze coverage workflows: `.github\u002Faw\u002Ftest-coverage.md`\n- Render compact markdown charts: `.github\u002Faw\u002Fasciicharts.md`\n- Map CLI commands to MCP usage: `.github\u002Faw\u002Fcli-commands.md`\n- Choose workflow architecture and patterns: `.github\u002Faw\u002Fpatterns.md`\n- Design, deploy, inspect or recover a Git-backed work queue: `.github\u002Faw\u002Fwork-queue.md`\n- Optimize token usage and cost: `.github\u002Faw\u002Ftoken-optimization.md`\n- Advanced cost controls without native settings (custom AIC allowances by server size or shared organization budget policies): read `docs\u002Fsrc\u002Fcontent\u002Fdocs\u002Freference\u002Fcost-management.md#configure-advanced-cost-controls-with-admission` ([published guidance](https:\u002F\u002Fgithub.github.com\u002Fgh-aw\u002Freference\u002Fcost-management\u002F#configure-advanced-cost-controls-with-admission)). Explain the external authority requirement and cooperative limits; do not invent frontmatter fields or promise hard caps, reservations, or mid-run cancellation.\n- Design long-running multi-agent research workflows: `.github\u002Faw\u002Fmulti-agent-research.md`\n- Add skills or agent plugins requested by the user (`skills:` \u002F `plugins:` frontmatter, never on-the-fly installs): `.github\u002Faw\u002Fskills.md`\n- Local SDLC issue bootstrap: `.github\u002Faw\u002Fsquad.md`\n\nWhen the task involves OTEL, OTLP, traces, observability backends, or telemetry-driven analysis, also read and follow `skills\u002Fotel-queries\u002FSKILL.md` after loading the matching workflow prompt or skill.\n\nWhen creating, updating, diagnosing or upgrading a workflow that uses `tools.work-queue`, also load `.github\u002Faw\u002Fwork-queue.md` after the primary prompt. Load deployment docs, operator reference or specification only when that task needs them.\n\nFor repository initialization or configuration involving third-party integrations,\nuse `.github\u002Faw\u002Fconnectors.md` and the selected editable declaration's\n`import-schema` and `connector-documentation` metadata. Discover local declarations,\nnormal local\u002Fpinned imports and matching `*-golden.md` consumers; do not invent a\nbuilt-in provider catalog. Use `gh aw connector \u003Cid> setup --file PATH` for\nphase-specific credential names\u002Fscopes and acquisition\u002Frenewal guidance.\nBind exact approved resources through `with`; secret NAMES only, never values.\nSelect reads\u002Fnative methods and staged safe outputs independently. Importing must\nnot enable capabilities, write credentials, broad grants or live webhook ingress.\nDerive network hosts from the selected contract, not provider-name guesses.\nToken acquisition\u002Frefresh, consent and real provider permissions remain external.\n\nWhen editing instructions, skills or their generators, keep the complete task\ncontract within the first 7,500 UTF-8 bytes (8,000-byte query limit). Front-load\nconstraints, routes, verification and stop conditions; defer examples and\ninventories. Preserve safety and exact schema\u002Fcommand names.\n\n\u003C!-- instruction-prefix-end -->\n\n## Optional reference inventory\n\n\u003Cdetails>\n\u003Csummary>Guidance file catalog\u003C\u002Fsummary>\n\nUse the task routes above first. This inventory is not required startup context.\n\n- `.github\u002Faw\u002Faction-container-substitutions.md`\n- `.github\u002Faw\u002Fagent-runtime-instructions.md`\n- `.github\u002Faw\u002Fagentic-chat.md`\n- `.github\u002Faw\u002Fagentic-workflows-mcp.md`\n- `.github\u002Faw\u002Fanalyzing-runs.md`\n- `.github\u002Faw\u002Fasciicharts.md`\n- `.github\u002Faw\u002Fcampaign.md`\n- `.github\u002Faw\u002Fcharts-trending.md`\n- `.github\u002Faw\u002Fcharts.md`\n- `.github\u002Faw\u002Fcli-commands.md`\n- `.github\u002Faw\u002Fcompat.md`\n- `.github\u002Faw\u002Fconfigure-agentic-engine.md`\n- `.github\u002Faw\u002Fconnectors.md`\n- `.github\u002Faw\u002Fcontext.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-design.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-evaluation.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-trigger-details.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow-validation.md`\n- `.github\u002Faw\u002Fcreate-agentic-workflow.md`\n- `.github\u002Faw\u002Fcreate-shared-agentic-workflow.md`\n- `.github\u002Faw\u002Fdebug-agentic-workflow.md`\n- `.github\u002Faw\u002Fdebug-bootstrap.md`\n- `.github\u002Faw\u002Fdebug-compilation.md`\n- `.github\u002Faw\u002Fdebug-live-testing.md`\n- `.github\u002Faw\u002Fdebug-model-engine-misconfiguration.md`\n- `.github\u002Faw\u002Fdebug-playbook.md`\n- `.github\u002Faw\u002Fdebug-scenarios.md`\n- `.github\u002Faw\u002Fdebug-security-review.md`\n- `.github\u002Faw\u002Fdebug-workflow-evidence.md`\n- `.github\u002Faw\u002Fdebug-workflow-health.md`\n- `.github\u002Faw\u002Fdependabot.md`\n- `.github\u002Faw\u002Fdeployment-status.md`\n- `.github\u002Faw\u002Fdesigner-mappings.md`\n- `.github\u002Faw\u002Fdesigner.md`\n- `.github\u002Faw\u002Fdoctor.md`\n- `.github\u002Faw\u002Fdocumentation-workflows.md`\n- `.github\u002Faw\u002Fdreaming.md`\n- `.github\u002Faw\u002Fdrive-memory.md`\n- `.github\u002Faw\u002Fenclaves.md`\n- `.github\u002Faw\u002Fevals.md`\n- `.github\u002Faw\u002Fexperiments.md`\n- `.github\u002Faw\u002Fformal-methods.md`\n- `.github\u002Faw\u002Fgithub-agentic-workflows.md`\n- `.github\u002Faw\u002Fgithub-mcp-server-pagination.md`\n- `.github\u002Faw\u002Fgithub-mcp-server-tools.md`\n- `.github\u002Faw\u002Fgithub-mcp-server.md`\n- `.github\u002Faw\u002Fharbor.md`\n- `.github\u002Faw\u002Findex-search.md`\n- `.github\u002Faw\u002Finstructions.md`\n- `.github\u002Faw\u002Fintent.md`\n- `.github\u002Faw\u002Fjobs.md`\n- `.github\u002Faw\u002Fledger.md`\n- `.github\u002Faw\u002Flinter-workflows.md`\n- `.github\u002Faw\u002Fllms.md`\n- `.github\u002Faw\u002Floop.md`\n- `.github\u002Faw\u002Flsp.md`\n- `.github\u002Faw\u002Fmaintainer.md`\n- `.github\u002Faw\u002Fmcp-clis.md`\n- `.github\u002Faw\u002Fmemory-stateful-patterns.md`\n- `.github\u002Faw\u002Fmemory.md`\n- `.github\u002Faw\u002Fmessages.md`\n- `.github\u002Faw\u002Fmulti-agent-research.md`\n- `.github\u002Faw\u002Fnetwork.md`\n- `.github\u002Faw\u002Foptimize-agentic-workflow.md`\n- `.github\u002Faw\u002Fotel.md`\n- `.github\u002Faw\u002Fpatterns.md`\n- `.github\u002Faw\u002Fplaywright.md`\n- `.github\u002Faw\u002Fpr-reviewer.md`\n- `.github\u002Faw\u002Frelease-workflow.md`\n- `.github\u002Faw\u002Freport.md`\n- `.github\u002Faw\u002Fresponsible-ai.md`\n- `.github\u002Faw\u002Freuse.md`\n- `.github\u002Faw\u002Fsafe-outputs-automation.md`\n- `.github\u002Faw\u002Fsafe-outputs-content.md`\n- `.github\u002Faw\u002Fsafe-outputs-management.md`\n- `.github\u002Faw\u002Fsafe-outputs-runtime.md`\n- `.github\u002Faw\u002Fsafe-outputs.md`\n- `.github\u002Faw\u002Fserena-tool.md`\n- `.github\u002Faw\u002Fshared-safe-jobs.md`\n- `.github\u002Faw\u002Fskills.md`\n- `.github\u002Faw\u002Fsquad.md`\n- `.github\u002Faw\u002Fsubagents.md`\n- `.github\u002Faw\u002Fsyntax-agentic.md`\n- `.github\u002Faw\u002Fsyntax-checkout.md`\n- `.github\u002Faw\u002Fsyntax-core.md`\n- `.github\u002Faw\u002Fsyntax-engine.md`\n- `.github\u002Faw\u002Fsyntax-tools-imports.md`\n- `.github\u002Faw\u002Fsyntax.md`\n- `.github\u002Faw\u002Ftest-coverage.md`\n- `.github\u002Faw\u002Ftest-expression.md`\n- `.github\u002Faw\u002Ftoken-optimization-caching-budgets.md`\n- `.github\u002Faw\u002Ftoken-optimization-observability.md`\n- `.github\u002Faw\u002Ftoken-optimization.md`\n- `.github\u002Faw\u002Ftriggers.md`\n- `.github\u002Faw\u002Fupdate-agentic-workflow.md`\n- `.github\u002Faw\u002Fupgrade-agentic-workflows.md`\n- `.github\u002Faw\u002Fvisual-regression.md`\n- `.github\u002Faw\u002Fwork-queue.md`\n- `.github\u002Faw\u002Fworkflow-constraints.md`\n- `.github\u002Faw\u002Fworkflow-editing.md`\n- `.github\u002Faw\u002Fworkflow-patterns.md`\n\n\u003C\u002Fdetails>\n",{"name":5,"description":7},"main","c37e0fd7d7a73277c293c54059b13b0d7155ac17",".github\u002Fskills\u002Fagentic-workflows",626,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw","https:\u002F\u002Fgh.io\u002Fgh-aw","https:\u002F\u002Fgithub.com\u002Fgithub","https:\u002F\u002Fgithub.com\u002Fabout","How people build software.","2026-11-15 06:45:15",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add github\u002Fgh-aw --skill agentic-workflows",{"tool":54,"command":55},"bunx","bunx skills add github\u002Fgh-aw --skill agentic-workflows",{"tool":57,"command":58},"pnpm","pnpm dlx skills add github\u002Fgh-aw --skill agentic-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagentic-workflows\u002FSKILL.md",true,[62,68],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"tests\u002Ffixtures.json","REFERENCE","参考文档",13989,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagentic-workflows\u002Ftests\u002Ffixtures.json",{"path":69,"resourceType":70,"resourceTypeDesc":71,"sizeBytes":72,"sourceHtmlUrl":73},"tests\u002Ftest_guidance.py","SCRIPT","脚本",86537,"https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fagentic-workflows\u002Ftests\u002Ftest_guidance.py",[75,83,91,116,134,159],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":82},"01M7DQYVZ9W9DDXKQ9452SNP8J","cracktro","Edit, preview, and verify the standalone interactive talk deck in docs\u002Fpublic\u002Fcracktro (slides, SVG diagrams, transitions, WebAudio sound).","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcracktro\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":90},"01M7612HQ4378TK8QZ5HPAF4KR","create-connector","Create or extend a declaration-only third-party connector, with narrow reads, separate safe outputs, optional protected triggers, and offline conformance evidence.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcreate-connector\u002FSKILL.md",[],[],"2026-11-12 13:55:43",{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":105,"publishedAt":33},"01M6ADC942STTXHFV410J4DH0X","GitHub Agentic Workflows","GitHub Agentic Workflows (`gh-aw`) is a GitHub CLI extension for writing Agentic Workflows in markdown and compiling them to GitHub Actions.","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002FSKILL.md",[97,102],{"categoryNo":98,"categoryName":99,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",{"categoryNo":103,"categoryName":104,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000023","Skill与智能体开发",[9,106,19,20,21,107,108,109,110,24,111,112,113,114,115],"github agentic workflows","extension","markdown","github cli","cli","for","compiling","writing","github actions","actions",{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":33},"01M6ADC6ZXSA46N9XD6VNAP1MS","windows-compatibility","Cross-platform path handling and command patterns","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fwindows-compatibility\u002FSKILL.md",[],[123,124,125,126,127,128,129,130,131,132,133],"windows","windows compatibility","compatibility","command","git","bugs","platform","high","patterns","cross-platform","path",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":33},"01M6ADC44957SVQF96R5YY247P","versioning-policy","Semver versioning rules for Squad SDK and CLI — prevents prerelease version incidents","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Fversioning-policy\u002FSKILL.md",[],[141,142,143,144,145,110,146,147,148,149,150,151,152,153,111,154,155,156,157,158],"versioning","policy","versioning policy","gate","implementation","workspace","pr","sdk","release","ci","npm","semver","squad","incident","incidents","Rules","version","resolution",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":169,"publishedAt":33},"01M6ADC1PHMEAEVR87F8PDR89X","tiered-memory","Three-tier agent memory model (hot\u002Fcold\u002Fwiki) for context reduction per spawn","https:\u002F\u002Fgithub.com\u002Fgithub\u002Fgh-aw\u002Fblob\u002Fmain\u002F.squad\u002Ftemplates\u002Fskills\u002Ftiered-memory\u002FSKILL.md",[165,168],{"categoryNo":166,"categoryName":167,"taxonomyType":100,"taxonomyTypeDesc":101},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":103,"categoryName":104,"taxonomyType":100,"taxonomyTypeDesc":101},[170,171,172,22,173,174,175,176,177,178,179,180,181,111,182,183],"tiered memory","memory","performance","agent memory","proposal","cold","model","wiki","spawn","memory-management","context","three","runtime","management"]