[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A3HT1DMDAXHF50R8YVSNPP":3,"skill-same:01M7A3HT1DMDAXHF50R8YVSNPP":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":30,"ownerDescription":6,"updatedAt":31,"install":32,"resources":45},"01M7A3HT1DMDAXHF50R8YVSNPP","bug-report",null,"Research codebase to reproduce, diagnose, and document bugs as actionable reports under docs\u002Fplans. If invoked without arguments, automatically researches the repo for potential bugs and generates reports. Use when asked to investigate, report, or document a bug, defect, regression, or unexpected behavior.","eovipmak\u002Fcrowdsec-ui","eovipmak","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F62509465?v=4","01M7A3HPVDTMMHRZZ85QBQ4KDD","Tran Nguyen Tin","01M7A3HPW3309JAMP1HRW73J1C",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.commandcode\u002Fskills\u002Fbug-report\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bug-report\ndescription: Research codebase to reproduce, diagnose, and document bugs as actionable reports under docs\u002Fplans. If invoked without arguments, automatically researches the repo for potential bugs and generates reports. Use when asked to investigate, report, or document a bug, defect, regression, or unexpected behavior.\nargument-hint: \"[bug description, error message, or reproduction steps — leave empty to auto-research repo for bugs]\"\n---\n\n# Bug Report\n\nCreate an investigation-backed bug report without changing source code. **Default invocation (no arguments) automatically researches the repo for bugs.**\n\n## Workflow\n\n1. Read `AGENTS.md`, the relevant `README`, package\u002Fmodule manifests, existing plans under `docs\u002Fplans\u002F`, and repository structure.\n2. Determine mode — **if no argument is given, default to exploratory bug research automatically (do not ask for clarification, do not wait for extra input):**\n    - **Default \u002F Exploratory (no args or empty prompt):** Scan the repository systematically for potential bugs: error handling gaps, edge cases, recent regressions (git log\u002Fdiff), open TODOs\u002FFIXMEs, type\u002Flint warnings, unhandled API failures, race conditions, security issues, and UX inconsistencies. Enumerate 3-5 candidate bugs ranked by severity × impact × likelihood, with evidence (file paths, snippets, commit refs). Fully diagnose only the top 1-2 candidates; summarize the rest with evidence and a recommended follow-up.\n   - **Explicit bug:** Investigate the reported bug: locate relevant source files, routes, components, logs, and recent commits. Search for related issues, error messages, and reproduction paths. Identify scope and user impact.\n3. Attempt to confirm reproduction conditions from code evidence alone (no source edits). For the top 1-2 default candidates and every explicit bug, record exact reproduction steps, expected vs actual behavior, environment, and affected surfaces. For other default candidates, record only the evidence and what remains to validate. If reproduction cannot be confirmed statically, state the gap as an assumption to validate.\n4. Analyze root cause, contributing factors, and blast radius for the top 1-2 default candidates and every explicit bug. Keep analysis grounded in repository evidence; label speculation explicitly.\n5. Propose the smallest fix approach that fits existing patterns. Preserve project constraints such as native deployment and single-admin security when they apply. Do not add unrelated refactoring.\n6. Write English Markdown report(s) under `docs\u002Fplans\u002F` using a descriptive lowercase-hyphenated filename prefixed with `bug-` or `bugfix-` (e.g., `bug-alert-filter-empty-state.md`). Include the current date when the repository convention uses dates. **For default invocation:** write a consolidated research report (e.g., `bug-research-YYYY-MM-DD.md`) containing the full ranked candidate list with evidence, plus a detailed section for the top 1-2 bugs (reproduction → root cause → fix → verification). If additional candidates warrant separate reports, create individual `bug-*.md` files and link them from the consolidated report. Use `ask_user_question` to let the user pick which bug to fix first when interactive; if no pick is made, leave the research report with all candidates and a recommended priority order.\n\n## Required report content\n\n- Summary and severity\u002Fimpact (for default mode, per candidate with ranking).\n- Reproduction steps, expected vs actual behavior, environment.\n- Current-state findings and relevant files (with paths).\n- Root cause analysis and contributing factors.\n- Proposed fix: exact files or directories to create\u002Fmodify, approach, and data\u002Fcontrol flow if applicable.\n- Interfaces, schemas, routes, or configuration affected.\n- Verification and acceptance criteria (manual checks and commands to run).\n- Security, compatibility, migration, and operational considerations if relevant.\n- Risks, unresolved assumptions, and reviewer ownership.\n- Non-goals and explicitly out-of-scope items.\n\n## Rules\n\n- Do not implement code, modify existing source, or create kanban tasks while writing the report.\n- Do not invent APIs, commands, dependencies, or reproduction logs without labeling them as decisions\u002Fassumptions to validate.\n- Prefer existing project patterns over new abstractions.\n- Keep scope lean and explicitly exclude unrelated infrastructure.\n- Explicitly exclude CI\u002FCD, unit tests, testing infrastructure, and monitoring\u002Fobservability (Grafana\u002FPrometheus\u002Flogging platforms, alerting) unless the bug is directly about them or the user explicitly requests them. Do not add pipeline files, test scaffolding, or dashboards to the report.\n- Do not add real credentials, tokens, or sensitive host data to the report.\n- **Default behavior:** When invoked without arguments, do NOT ask the user what to do — immediately start repository research and generate bug reports. Never remain idle waiting for clarification in this mode.\n- If requirements are materially ambiguous in explicit mode, ask focused questions; otherwise proceed with documented assumptions.\n- After writing, reread the report and check that every claim traces to repository evidence and that reproduction → root cause → fix → verification forms a consistent chain.\n\n## Completion report\n\nState the report path(s), reproduction status (confirmed vs assumed), root cause summary, proposed fix scope, assumptions, and any questions that must be answered before implementation. For default invocation, also list all candidate bugs found with severity ranking and how the user can select one to proceed.\n","# Bug Report\n\nCreate an investigation-backed bug report without changing source code. **Default invocation (no arguments) automatically researches the repo for bugs.**\n\n## Workflow\n\n1. Read `AGENTS.md`, the relevant `README`, package\u002Fmodule manifests, existing plans under `docs\u002Fplans\u002F`, and repository structure.\n2. Determine mode — **if no argument is given, default to exploratory bug research automatically (do not ask for clarification, do not wait for extra input):**\n    - **Default \u002F Exploratory (no args or empty prompt):** Scan the repository systematically for potential bugs: error handling gaps, edge cases, recent regressions (git log\u002Fdiff), open TODOs\u002FFIXMEs, type\u002Flint warnings, unhandled API failures, race conditions, security issues, and UX inconsistencies. Enumerate 3-5 candidate bugs ranked by severity × impact × likelihood, with evidence (file paths, snippets, commit refs). Fully diagnose only the top 1-2 candidates; summarize the rest with evidence and a recommended follow-up.\n   - **Explicit bug:** Investigate the reported bug: locate relevant source files, routes, components, logs, and recent commits. Search for related issues, error messages, and reproduction paths. Identify scope and user impact.\n3. Attempt to confirm reproduction conditions from code evidence alone (no source edits). For the top 1-2 default candidates and every explicit bug, record exact reproduction steps, expected vs actual behavior, environment, and affected surfaces. For other default candidates, record only the evidence and what remains to validate. If reproduction cannot be confirmed statically, state the gap as an assumption to validate.\n4. Analyze root cause, contributing factors, and blast radius for the top 1-2 default candidates and every explicit bug. Keep analysis grounded in repository evidence; label speculation explicitly.\n5. Propose the smallest fix approach that fits existing patterns. Preserve project constraints such as native deployment and single-admin security when they apply. Do not add unrelated refactoring.\n6. Write English Markdown report(s) under `docs\u002Fplans\u002F` using a descriptive lowercase-hyphenated filename prefixed with `bug-` or `bugfix-` (e.g., `bug-alert-filter-empty-state.md`). Include the current date when the repository convention uses dates. **For default invocation:** write a consolidated research report (e.g., `bug-research-YYYY-MM-DD.md`) containing the full ranked candidate list with evidence, plus a detailed section for the top 1-2 bugs (reproduction → root cause → fix → verification). If additional candidates warrant separate reports, create individual `bug-*.md` files and link them from the consolidated report. Use `ask_user_question` to let the user pick which bug to fix first when interactive; if no pick is made, leave the research report with all candidates and a recommended priority order.\n\n## Required report content\n\n- Summary and severity\u002Fimpact (for default mode, per candidate with ranking).\n- Reproduction steps, expected vs actual behavior, environment.\n- Current-state findings and relevant files (with paths).\n- Root cause analysis and contributing factors.\n- Proposed fix: exact files or directories to create\u002Fmodify, approach, and data\u002Fcontrol flow if applicable.\n- Interfaces, schemas, routes, or configuration affected.\n- Verification and acceptance criteria (manual checks and commands to run).\n- Security, compatibility, migration, and operational considerations if relevant.\n- Risks, unresolved assumptions, and reviewer ownership.\n- Non-goals and explicitly out-of-scope items.\n\n## Rules\n\n- Do not implement code, modify existing source, or create kanban tasks while writing the report.\n- Do not invent APIs, commands, dependencies, or reproduction logs without labeling them as decisions\u002Fassumptions to validate.\n- Prefer existing project patterns over new abstractions.\n- Keep scope lean and explicitly exclude unrelated infrastructure.\n- Explicitly exclude CI\u002FCD, unit tests, testing infrastructure, and monitoring\u002Fobservability (Grafana\u002FPrometheus\u002Flogging platforms, alerting) unless the bug is directly about them or the user explicitly requests them. Do not add pipeline files, test scaffolding, or dashboards to the report.\n- Do not add real credentials, tokens, or sensitive host data to the report.\n- **Default behavior:** When invoked without arguments, do NOT ask the user what to do — immediately start repository research and generate bug reports. Never remain idle waiting for clarification in this mode.\n- If requirements are materially ambiguous in explicit mode, ask focused questions; otherwise proceed with documented assumptions.\n- After writing, reread the report and check that every claim traces to repository evidence and that reproduction → root cause → fix → verification forms a consistent chain.\n\n## Completion report\n\nState the report path(s), reproduction status (confirmed vs assumed), root cause summary, proposed fix scope, assumptions, and any questions that must be answered before implementation. For default invocation, also list all candidate bugs found with severity ranking and how the user can select one to proceed.\n",{"name":5,"description":7,"argument-hint":24},"[bug description, error message, or reproduction steps — leave empty to auto-research repo for bugs]","main","6de4714436264d026cecebf59af8e2a8ae8f1450",".commandcode\u002Fskills\u002Fbug-report","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui","https:\u002F\u002Fgithub.com\u002Feovipmak","tntin.id.vn","2026-08-21 14:35:58",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add eovipmak\u002Fcrowdsec-ui --skill bug-report",{"tool":38,"command":39},"bunx","bunx skills add eovipmak\u002Fcrowdsec-ui --skill bug-report",{"tool":41,"command":42},"pnpm","pnpm dlx skills add eovipmak\u002Fcrowdsec-ui --skill bug-report","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.commandcode\u002Fskills\u002Fbug-report\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7A3M56ND4QK41F336TRD72T","plan-task-breakdown","Convert a development plan in docs\u002Fplans into self-contained, dependency-aware Markdown tasks for agents under docs\u002Fkanban\u002F\u003Cdate>_\u003Cplan-name>. Use when asked to break down, decompose, or prepare a plan for parallel agent execution.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fplan-task-breakdown\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7A3M1QVMVCKY014J5Z7G76B","kanban-task-coordinator","Coordinate agents to execute a dependency-aware task set from a docs\u002Fkanban directory, including reviewing tasks, assigning work, collecting changes, verifying results, and handling blockers. Use when asked to execute or coordinate a kanban plan such as docs\u002Fkanban\u002F2026-08-04_deep-research-report.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkanban-task-coordinator\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7A3KYDK38Z8P032RX1HJ1ZB","feature-development-planner","Research repository structure and requirements, then create a complete feature development plan in docs\u002Fplans. If invoked without arguments, automatically researches the repo and proposes new features for the user to choose from. Supports explicit feature requests and exploratory research.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Ffeature-development-planner\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7A3KR8390H0E86SEGN2HD1W","crowdsec","Use when the user is installing, configuring, operating, or debugging CrowdSec — including cscli, LAPI\u002FCAPI, hub collections, parsers\u002Fscenarios\u002Fwhitelists deployment, bouncers (firewall, nginx, traefik, caddy), WAF (AppSec component) deployment, profiles, notifications, upgrades, and fail2ban migration. Covers bare-metal\u002Fsystemd, Docker, Kubernetes\u002FHelm, and CrowdSec Console enrollment. This is an operational skill — it does not author WAF rules, scenarios, or parsers.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fcrowdsec\u002FSKILL.md",[],[],{"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":19},"01M7A3KN3P65FF6R6R2N31X53F","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.commandcode\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7A3KJYA8MZHTNJ4RM0C653H","triage","Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.","https:\u002F\u002Fgithub.com\u002Feovipmak\u002Fcrowdsec-ui\u002Fblob\u002Fmain\u002F.commandcode\u002Fskills\u002Ftriage\u002FSKILL.md",[],[]]