[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AGG7CYKFSFYEM5MWPPAWSS":3,"skill-same:01M7AGG7CYKFSFYEM5MWPPAWSS":52},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7AGG7CYKFSFYEM5MWPPAWSS","generate-playbook",null,"Write an Ansible playbook, inventory, and group_vars for a repeatable change across many network devices, then validate it locally before handing it back. Use when the user asks for Ansible by name, or asks how to push the same change to a fleet — VLANs, banners, NTP\u002FAAA, SNMPv3, config backup, compliance checks — using cisco.ios, cisco.nxos, arista.eos, juniper.device (Junos), paloaltonetworks.panos, or fortinet.fortios. For Python (Nornir\u002FNetmiko\u002FScrapli) use generate-automation, for Terraform use generate-terraform, for pyATS\u002Fpytest checks use generate-tests, for a CI pipeline use generate-pipeline, and for a single device's config use generate-config.","ciscoittech\u002Fdamira-plugins","ciscoittech","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12874990?v=4","01M7AGA34QQBQX1NVX7SJEF93Z","Notorious CSV","01M7AGA35B7M33H4QSKVCB013C",0,"MIT","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fgenerate-playbook\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: generate-playbook\ndescription: Write an Ansible playbook, inventory, and group_vars for a repeatable change across many network devices, then validate it locally before handing it back. Use when the user asks for Ansible by name, or asks how to push the same change to a fleet — VLANs, banners, NTP\u002FAAA, SNMPv3, config backup, compliance checks — using cisco.ios, cisco.nxos, arista.eos, juniper.device (Junos), paloaltonetworks.panos, or fortinet.fortios. For Python (Nornir\u002FNetmiko\u002FScrapli) use generate-automation, for Terraform use generate-terraform, for pyATS\u002Fpytest checks use generate-tests, for a CI pipeline use generate-pipeline, and for a single device's config use generate-config.\n---\n\n# Ansible playbook generation\n\nYou write the playbook. Damira supplies the vendor facts and the gate: every playbook goes\nthrough `damira validate` before you hand it back.\n\n## Step 1: Gather requirements\n\n- **Task** — deploy VLANs, back up configs, push NTP\u002FAAA\u002FSNMPv3, compliance check\n- **Targets** — how many devices, what platform and OS version\n- **Variables** — VLAN IDs, interface names, server IPs\n- **Connection** — `network_cli` (SSH), `httpapi` (eAPI\u002FNX-API), or `netconf`\n\nIf the user named a different framework, use the sibling skill instead (see the description).\n\n## Step 2: Look up the modules\n\nRun `~\u002F.damira\u002Fbin\u002Fdamira search-vendor-docs \"\u003Cquery>\" --vendor \u003Cvendor>` for the collection and module you plan to use, e.g.\n`\"ansible cisco.ios ios_ntp_global parameters\"` with the vendor set. Module names and\nparameters change between collection versions; this lookup is what keeps the playbook\nfrom using a parameter that no longer exists. **If the lookup fails, say so** rather than\nemitting parameters you could not verify.\n\nRead `references\u002Fansible-collections.md` (beside this file) for the collection per platform,\nresource modules vs `*_config`, connection plugins, and check-mode caveats.\n\nIf the change is a standard baseline (NTP, AAA\u002FTACACS+, SNMPv3, syslog) on IOS,\nNX-OS, EOS or Junos, the plugin ships golden templates. Render the device lines with\n`--secrets ansible`, so secret values (TACACS key, SNMP passphrases) come out as\n`{{ lookup('env', 'NAME') }}` and are resolved when the playbook runs — never render real\nsecrets into your context or into a playbook:\n`~\u002F.damira\u002Fbin\u002Fdamira render \u003Ctask> --platform \u003Cp> --vars vars.yml --secrets ansible`\nand push them with the platform's `*_config` module (Junos: `juniper.device.junos_config`\nwith the `set` lines under `lines:` — it takes set\u002Fdelete lines directly and has no `format`\noption; drop the `#` comment lines, which it rejects), instead of hand-writing the lines. Banners are the exception: use the\nbanner modules (`cisco.ios.ios_banner`, `cisco.nxos.nxos_banner`, `arista.eos.eos_banner`,\n`juniper.device.junos_banner`) with the text as a variable — a\ndelimited `banner login ^ ... ^` block does not fit `*_config` `lines:`.\n\n## Step 3: Write the playbook\n\n- **Inventory** — YAML, device groups, `ansible_network_os` + `ansible_connection` per group\n- **Credentials** — Ansible Vault or env lookups (`lookup('env', 'NET_PASSWORD')`), never inline\n- **Tasks** — resource modules (`state: merged`) where one exists; `*_config` only for lines\n  with no resource module. `gather_facts: false`. Fully-qualified module names.\n- **Error handling** — `block`\u002F`rescue` around anything that changes device state\n- **Idempotency** — safe to run repeatedly. Resource modules are; `*_config` `lines:` only\n  when they match the running config exactly. Golden AAA\u002FSNMPv3 lines carrying secrets\n  never do (IOS shows `key 7`, hides `snmp-server user`), so they report `changed` every run.\n  Say so in the hand-back, or split them into a task with `when:` on a first-run\u002Frotation flag\n\nSave under `playbooks\u002F`: `playbooks\u002F{task}.yml`, `playbooks\u002Finventory\u002F{group}.yml`,\n`playbooks\u002Fgroup_vars\u002F{group}.yml`.\n\n## Validate loop\n\n**Delegate this loop to the `damira-fixer` subagent** (pinned to a cheap model). Give it the path and `--skill generate-playbook`. It runs the command below, fixes only what the findings name, and stops after 3 rounds. Read its report: a change to a device command, module or resource is your call, not its. If the subagent isn't available, run the loop yourself as below.\n\nThe validator is `~\u002F.damira\u002Fbin\u002Fdamira validate`. It runs locally (yamllint, `ansible-playbook\n--syntax-check`, `ansible-lint --profile production`) and makes no API call. `--skill` tags\nthe local workflow event with this skill.\n\n```bash\n~\u002F.damira\u002Fbin\u002Fdamira validate playbooks\u002F --skill generate-playbook --host cursor\n```\n\n1. Run it on everything you wrote.\n2. Fix every FAIL and re-run — at most 3 rounds.\n3. Still failing after 3 rounds: stop, tell the user which checks fail and why. Do not hand\n   it back as finished.\n4. A `skipped` check means the tool is not installed — pass the install hint on; it is not\n   a pass. An `UNVERIFIED` result is not a pass either.\n5. `couldn't resolve module\u002Faction '\u003Cns>.\u003Ccoll>.\u003Cmodule>'` or\n   `syntax-check[unknown-module]` means the collection is not installed, not that the module\n   is wrong. Do not rename or swap modules to make it go away: treat it like a skipped check,\n   tell the user to run `ansible-galaxy collection install \u003Cns>.\u003Ccoll>` (or `-r\n   collections\u002Frequirements.yml`) and re-validate, and don't count it against the 3 rounds.\n\n## Step 4: Hand back\n\nLead with the dry run, then a single-device first run:\n\n```bash\nansible-playbook -i playbooks\u002Finventory\u002F{group}.yml playbooks\u002F{task}.yml --check --diff\n# review the diff, then one device first:\nansible-playbook -i playbooks\u002Finventory\u002F{group}.yml playbooks\u002F{task}.yml --limit \u003Cone-host>\n```\n\nState what validate reported (pass \u002F warnings \u002F skipped tools) and any assumption you made.\n","# Ansible playbook generation\n\nYou write the playbook. Damira supplies the vendor facts and the gate: every playbook goes\nthrough `damira validate` before you hand it back.\n\n## Step 1: Gather requirements\n\n- **Task** — deploy VLANs, back up configs, push NTP\u002FAAA\u002FSNMPv3, compliance check\n- **Targets** — how many devices, what platform and OS version\n- **Variables** — VLAN IDs, interface names, server IPs\n- **Connection** — `network_cli` (SSH), `httpapi` (eAPI\u002FNX-API), or `netconf`\n\nIf the user named a different framework, use the sibling skill instead (see the description).\n\n## Step 2: Look up the modules\n\nRun `~\u002F.damira\u002Fbin\u002Fdamira search-vendor-docs \"\u003Cquery>\" --vendor \u003Cvendor>` for the collection and module you plan to use, e.g.\n`\"ansible cisco.ios ios_ntp_global parameters\"` with the vendor set. Module names and\nparameters change between collection versions; this lookup is what keeps the playbook\nfrom using a parameter that no longer exists. **If the lookup fails, say so** rather than\nemitting parameters you could not verify.\n\nRead `references\u002Fansible-collections.md` (beside this file) for the collection per platform,\nresource modules vs `*_config`, connection plugins, and check-mode caveats.\n\nIf the change is a standard baseline (NTP, AAA\u002FTACACS+, SNMPv3, syslog) on IOS,\nNX-OS, EOS or Junos, the plugin ships golden templates. Render the device lines with\n`--secrets ansible`, so secret values (TACACS key, SNMP passphrases) come out as\n`{{ lookup('env', 'NAME') }}` and are resolved when the playbook runs — never render real\nsecrets into your context or into a playbook:\n`~\u002F.damira\u002Fbin\u002Fdamira render \u003Ctask> --platform \u003Cp> --vars vars.yml --secrets ansible`\nand push them with the platform's `*_config` module (Junos: `juniper.device.junos_config`\nwith the `set` lines under `lines:` — it takes set\u002Fdelete lines directly and has no `format`\noption; drop the `#` comment lines, which it rejects), instead of hand-writing the lines. Banners are the exception: use the\nbanner modules (`cisco.ios.ios_banner`, `cisco.nxos.nxos_banner`, `arista.eos.eos_banner`,\n`juniper.device.junos_banner`) with the text as a variable — a\ndelimited `banner login ^ ... ^` block does not fit `*_config` `lines:`.\n\n## Step 3: Write the playbook\n\n- **Inventory** — YAML, device groups, `ansible_network_os` + `ansible_connection` per group\n- **Credentials** — Ansible Vault or env lookups (`lookup('env', 'NET_PASSWORD')`), never inline\n- **Tasks** — resource modules (`state: merged`) where one exists; `*_config` only for lines\n  with no resource module. `gather_facts: false`. Fully-qualified module names.\n- **Error handling** — `block`\u002F`rescue` around anything that changes device state\n- **Idempotency** — safe to run repeatedly. Resource modules are; `*_config` `lines:` only\n  when they match the running config exactly. Golden AAA\u002FSNMPv3 lines carrying secrets\n  never do (IOS shows `key 7`, hides `snmp-server user`), so they report `changed` every run.\n  Say so in the hand-back, or split them into a task with `when:` on a first-run\u002Frotation flag\n\nSave under `playbooks\u002F`: `playbooks\u002F{task}.yml`, `playbooks\u002Finventory\u002F{group}.yml`,\n`playbooks\u002Fgroup_vars\u002F{group}.yml`.\n\n## Validate loop\n\n**Delegate this loop to the `damira-fixer` subagent** (pinned to a cheap model). Give it the path and `--skill generate-playbook`. It runs the command below, fixes only what the findings name, and stops after 3 rounds. Read its report: a change to a device command, module or resource is your call, not its. If the subagent isn't available, run the loop yourself as below.\n\nThe validator is `~\u002F.damira\u002Fbin\u002Fdamira validate`. It runs locally (yamllint, `ansible-playbook\n--syntax-check`, `ansible-lint --profile production`) and makes no API call. `--skill` tags\nthe local workflow event with this skill.\n\n```bash\n~\u002F.damira\u002Fbin\u002Fdamira validate playbooks\u002F --skill generate-playbook --host cursor\n```\n\n1. Run it on everything you wrote.\n2. Fix every FAIL and re-run — at most 3 rounds.\n3. Still failing after 3 rounds: stop, tell the user which checks fail and why. Do not hand\n   it back as finished.\n4. A `skipped` check means the tool is not installed — pass the install hint on; it is not\n   a pass. An `UNVERIFIED` result is not a pass either.\n5. `couldn't resolve module\u002Faction '\u003Cns>.\u003Ccoll>.\u003Cmodule>'` or\n   `syntax-check[unknown-module]` means the collection is not installed, not that the module\n   is wrong. Do not rename or swap modules to make it go away: treat it like a skipped check,\n   tell the user to run `ansible-galaxy collection install \u003Cns>.\u003Ccoll>` (or `-r\n   collections\u002Frequirements.yml`) and re-validate, and don't count it against the 3 rounds.\n\n## Step 4: Hand back\n\nLead with the dry run, then a single-device first run:\n\n```bash\nansible-playbook -i playbooks\u002Finventory\u002F{group}.yml playbooks\u002F{task}.yml --check --diff\n# review the diff, then one device first:\nansible-playbook -i playbooks\u002Finventory\u002F{group}.yml playbooks\u002F{task}.yml --limit \u003Cone-host>\n```\n\nState what validate reported (pass \u002F warnings \u002F skipped tools) and any assumption you made.\n",{"name":5,"description":7},"main","016916dbccc55b32762ccec3eac9030f8bacb249","damira-cursor\u002Fskills\u002Fgenerate-playbook","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins","https:\u002F\u002Fdamiraai.com","https:\u002F\u002Fgithub.com\u002Fciscoittech","I do crazy things with A.I","2026-11-02 11:12:12",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add ciscoittech\u002Fdamira-plugins --skill generate-playbook",{"tool":38,"command":39},"bunx","bunx skills add ciscoittech\u002Fdamira-plugins --skill generate-playbook",{"tool":41,"command":42},"pnpm","pnpm dlx skills add ciscoittech\u002Fdamira-plugins --skill generate-playbook","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fgenerate-playbook\u002FSKILL.md",true,[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fansible-collections.md","REFERENCE","参考文档",4703,"https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fgenerate-playbook\u002Freferences\u002Fansible-collections.md",[53,60,67,74,81,88],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7AGHRRQXXRQVG1W3GCF9YW7","upgrade-plan","Ask Damira to assess a version-to-version upgrade of a network platform and produce the MOP and change control. Use when the user names a product and a target release — \"IOS-XE 17.6.5 to 17.9.5\", \"CUCM 12.5 SU7 to 15\", \"PAN-OS 10.2 to 11.1\" — or asks what breaks, what the risk is, or how long a maintenance window needs to be. Covers CUCM, IOS-XE, IOS-XR, NX-OS, PAN-OS, FortiOS, Junos, ISE, ASA, WLC\u002FCatalyst 9800. Not for platform-to-platform migration (CUCM to Webex Calling, on-prem to cloud) and not for diagnosing a fault after an upgrade — use troubleshoot for that.","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fupgrade-plan\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7AGHKWQX8XPBAFSZH7E4N1D","troubleshoot","Ask Damira to diagnose an active, in-progress network fault. Use when the user reports something broken right now — an outage, a flapping interface, a BGP or OSPF adjacency down, dropped or blackholed traffic, failed calls, users unable to connect — or pastes show\u002Flog output for analysis. Also fires on direct questions like \"why is BGP down\" or \"why is OSPF stuck in EXSTART\". Returns vendor-specific diagnosis with exact CLI commands. Do NOT use for \"how does X work\" protocol questions, for reviewing a config that is not currently broken (use config-audit), or for planning an upgrade (use upgrade-plan).","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Ftroubleshoot\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7AGHEG8SYWJ12TQRC04XXWZ","source-of-truth-change","Turn intended state in the engineer's source of truth (NetBox or Nautobot) into a validated change, then hand it to the automation they already run — an Ansible Automation Platform job in check mode, a pyATS\u002FGenie before-and-after diff, or a Terraform plan. Use when the user asks to make a change \"from NetBox\" or \"from Nautobot\", to push what the source of truth says, to bring devices in line with intended state, or to run a validated playbook through AAP or pyATS. Damira never applies the change; the engineer does. For a playbook with no source of truth use generate-playbook, for Terraform alone use generate-terraform, and for an active outage use troubleshoot.","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fsource-of-truth-change\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7AGH9A7RS5CC5H5NSNC04K3","lab-test-change","Test a network change in a throwaway ContainerLab lab before it goes near production — deploy the lab, apply the playbook or script, run show-command or pyATS\u002FGenie checks, report pass\u002Ffail, and always destroy the lab. Use when the user says \"test this in a lab first\", \"prove this change before the window\", \"dry-run this playbook against a lab\", or wants evidence a change works before a CAB. Needs docker and containerlab on the engineer's machine; without them it validates only and says so. To only build a lab, use generate-lab; to write the change, use generate-playbook, generate-automation or generate-terraform.","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Flab-test-change\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7AGH4SFXKQA552XNMB0M4QT","generate-workbook","Build an Excel workbook (.xlsx) for a network procedure — a migration, platform migration, security audit, change control, or incident-response workbook — grounded in Damira evidence, with an HTML preview. Use when the user asks for a spreadsheet, workbook, tracker, or Excel version of a migration plan, cutover, audit findings, change record, or incident timeline. For a version-to-version upgrade, use upgrade-plan (it offers the workbook itself). Not for diagnosing an active fault — use troubleshoot.","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fgenerate-workbook\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7AGH0RPM7QTN4094HYS023Z","generate-tests","Write network tests — pyATS\u002FGenie learn, change, learn, diff jobs that prove a change did what it should and nothing else, and pytest tests for automation scripts — then validate them locally. Use when the user asks for pyATS, Genie, AEtest, a testbed file, pre\u002Fpost change verification, state snapshots, or unit tests for a Nornir\u002FNetmiko script. For the change itself use generate-playbook, generate-automation or generate-terraform.","https:\u002F\u002Fgithub.com\u002Fciscoittech\u002Fdamira-plugins\u002Fblob\u002Fmain\u002Fdamira-cursor\u002Fskills\u002Fgenerate-tests\u002FSKILL.md",[],[]]