[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X47VB486QVY8JQB4FZQHW6":3,"skill-same:01M6X47VB486QVY8JQB4FZQHW6":78},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":58,"commitSha":59,"skillDirectory":60,"forksCount":14,"repositoryHtmlUrl":61,"repositoryHomepageUrl":62,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":77},"01M6X47VB486QVY8JQB4FZQHW6","skill-finder",null,"Navigation aid for the processkit skill catalog — maps natural-language\ncues and task types to the right skill. Read this when you are unsure\nwhich skill applies to the current task, when the user names a task\nwithout naming a skill, or at session start when orienting to an\nunfamiliar project. Always the first skill to consult; never the last.","projectious-work\u002Fprocesskit","projectious-work","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F263889726?v=4","01M6N97TJJ118WQ35CHRV8RD0E","projectious.work","01M6N97TPWJPF0BMKYQ4PBY5W8",0,"MIT","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.7.0\u002Fskills\u002Fskill-finder\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"skill finder","types","when","for","v1","which","natural-language","true","last","you","Meta","session start","project","task","maps","never","catalog","session","work","consult","2026-11-10 10:12:30",false,"---\nname: skill-finder\ndescription: |\n  Navigation aid for the processkit skill catalog — maps natural-language\n  cues and task types to the right skill. Read this when you are unsure\n  which skill applies to the current task, when the user names a task\n  without naming a skill, or at session start when orienting to an\n  unfamiliar project. Always the first skill to consult; never the last.\nmetadata:\n  processkit:\n    apiVersion: processkit.projectious.work\u002Fv1\n    id: SKILL-skill-finder\n    version: \"1.0.0\"\n    created: 2026-04-08T00:00:00Z\n    category: meta\n    core: true   # proposed: always install regardless of [skills].include\u002Fexclude\n                 # pending aibox companion issue for content_install.rs change\n---\n\n# Skill Finder\n\n## Intro\n\nWhen you are unsure which skill to use, start here. This skill maps\nwhat the user is asking for to the skill that handles it. It is not a\nskill you invoke to do work — it is a skill you read to decide what to\ninvoke next.\n\n## Overview\n\n### By trigger phrase\n\nFind the phrase that most closely matches what the user said, then load\nthat skill before proceeding.\n\n| If the user says… | Skill to load |\n|---|---|\n| \"refactor this\", \"clean up the code\" | `refactoring` |\n| \"review this PR\", \"code review\" | `code-review` |\n| \"write a test\", \"test this\", \"TDD\" | `tdd-workflow` |\n| \"testing strategy\", \"what tests do we need\" | `testing-strategy` |\n| \"debug this\", \"find the bug\", \"why is this failing\" | `debugging` |\n| \"design the API\", \"API contract\" | `api-design` |\n| \"system design\", \"design this system\" | `system-design` |\n| \"architecture\", \"how should we structure this\" | `software-architecture` |\n| \"domain model\", \"DDD\" | `domain-driven-design` |\n| \"module structure\", \"package boundaries\", \"split this up\" | `software-modularization` |\n| \"new service\", \"microservice\", \"extract this into a service\" | `microservice-creation` |\n| \"events\", \"event-driven\", \"pub-sub\" | `event-driven-architecture` |\n| \"deploy\", \"CI\u002FCD pipeline\", \"set up CI\" | `ci-cd-setup` |\n| \"Docker\", \"Dockerfile\", \"containerise this\" | `dockerfile-review` |\n| \"Kubernetes\", \"k8s\", \"set up the cluster\" | `kubernetes-basics` |\n| \"Terraform\", \"infrastructure as code\" | `terraform-basics` |\n| \"write SQL\", \"SQL query\", \"query the database\" | `sql-patterns` |\n| \"SQL style\", \"format the SQL\" | `sql-style-guide` |\n| \"database design\", \"schema design\" | `database-modeling` |\n| \"database migration\", \"migrate the schema\" | `database-migration` |\n| \"NoSQL\", \"MongoDB\", \"document store\" | `nosql-patterns` |\n| \"secure this\", \"security review\" | `secure-coding` |\n| \"threat model\" | `threat-modeling` |\n| \"secrets\", \"API keys\", \"credential management\" | `secret-management` |\n| \"auth\", \"authentication\", \"OAuth\" | `auth-patterns` |\n| \"logging\", \"log this\" | `logging-strategy` |\n| \"metrics\", \"monitoring\", \"dashboards\" | `metrics-monitoring` |\n| \"trace\", \"distributed tracing\" | `distributed-tracing` |\n| \"alert\", \"on-call\", \"PagerDuty\" | `alerting-oncall` |\n| \"postmortem\", \"incident review\" | `postmortem-writing` |\n| \"incident\", \"on fire\", \"outage\" | `incident-response` |\n| \"profile this\", \"find the bottleneck\", \"performance\" | `performance-profiling` |\n| \"load test\", \"stress test\" | `load-testing` |\n| \"Python\" | `python-best-practices` |\n| \"TypeScript\", \"JavaScript\" | `typescript-patterns` |\n| \"Go\", \"Golang\" | `go-conventions` |\n| \"Rust\" | `rust-conventions` |\n| \"Java\" | `java-patterns` |\n| \"FastAPI\", \"Python API\" | `fastapi-patterns` |\n| \"gRPC\", \"protobuf\" | `grpc-protobuf` |\n| \"GraphQL\" | `graphql-patterns` |\n| \"Flutter\", \"mobile app\" | `flutter-development` |\n| \"Tailwind\", \"CSS utility classes\" | `tailwind` |\n| \"frontend design\", \"UI components\" | `frontend-design` |\n| \"analyse data\", \"pandas\", \"polars\", \"dataframe\" | `pandas-polars` |\n| \"data pipeline\", \"ETL\", \"data engineering\" | `data-pipeline` |\n| \"data quality\", \"data validation\" | `data-quality` |\n| \"data science\", \"notebook\", \"EDA\" | `data-science` |\n| \"visualise data\", \"chart this\" | `data-visualization` |\n| \"RAG\", \"retrieval\", \"vector search\" | `rag-engineering` |\n| \"embeddings\", \"vector database\" | `embedding-vectordb` |\n| \"prompt engineering\", \"write a prompt\" | `prompt-engineering` |\n| \"evaluate the LLM\", \"benchmark the model\" | `llm-evaluation` |\n| \"which model should I use\", \"recommend a model\", \"which LLM is best\", \"help me pick an AI model\", \"route tasks to the right model\", \"which Claude should I use\" | `model-recommender` |\n| \"ML pipeline\", \"train a model\" | `ml-pipeline` |\n| \"feature engineering\" | `feature-engineering` |\n| \"diagram\", \"draw\", \"whiteboard\", \"Excalidraw\" | `excalidraw` |\n| \"infographic\", \"SVG chart\" | `infographics` |\n| \"logo\", \"brand mark\", \"SVG icon\" | `logo-design` |\n| \"mobile design\", \"iOS\", \"Android UI\" | `mobile-app-design` |\n| \"SEO\", \"search optimisation\", \"meta tags\" | `seo-optimization` |\n| \"Word document\", \"docx\" | `docx-authoring` |\n| \"PowerPoint\", \"slides\", \"pptx\" | `pptx-authoring` |\n| \"Excel\", \"spreadsheet\", \"xlsx\" | `xlsx-modeling` |\n| \"PDF\", \"generate a PDF\" | `pdf-workflow` |\n| \"LaTeX\", \"academic paper\" | `latex-authoring` |\n| \"write a PRD\", \"product requirements\" | `prd-writing` |\n| \"user research\", \"user interview\" | `user-research` |\n| \"data story\", \"present the analysis\" | `data-storytelling` |\n| \"legal review\", \"contract review\" | `legal-review` |\n| \"write an email\", \"draft a message\" | `email-drafter` |\n| \"status update\", \"progress report\" | `status-update-writer` |\n| \"onboard\", \"new joiner guide\" | `onboarding-guide` |\n| \"changelog\", \"what changed in this release\" | `changelog` |\n| \"plan the release\", \"version bump\", \"semver\" | `release-semver` |\n| \"write a decision\", \"document this decision\", \"ADR\" | `decision-record` |\n| \"backlog\", \"work items\", \"create a ticket\" | `workitem-management` |\n| \"log this event\", \"audit trail\" | `event-log` |\n| \"remember this\", \"note this idea\", \"capture this\" | `note-management` |\n| \"write a standup\", \"daily update\" | `standup-context` |\n| \"write a handover\", \"shutting down\", \"container restart\" | `session-handover` |\n| \"morning briefing\", \"catch me up\", \"state of things\" | `morning-briefing` |\n| \"groom the context\", \"clean up context\" | `context-grooming` |\n| \"second opinion\", \"devil's advocate\", \"poke holes in this\" | `devils-advocate` |\n| \"multiple perspectives\", \"board of advisors\" | `board-of-advisors` |\n| \"research this\", \"I'm not sure about this fact\" | `research-with-confidence` |\n| \"build a new skill\", \"author a skill\" | `skill-builder` |\n| \"review this skill\", \"is this skill good\" | `skill-reviewer` |\n| \"dependency audit\", \"check dependencies\" | `dependency-audit` |\n| \"dependency management\", \"update packages\" | `dependency-management` |\n| \"git workflow\", \"branching strategy\", \"commit message\" | `git-workflow` |\n| \"shell script\", \"bash script\" | `shell-scripting` |\n| \"caching\", \"cache strategy\" | `caching-strategies` |\n| \"concurrency\", \"async\", \"parallelism\" | `concurrency-patterns` |\n| \"webhook\", \"callback URL\" | `webhook-integration` |\n| \"error handling\", \"exception handling\" | `error-handling` |\n| \"documentation\", \"write the docs\" | `documentation` |\n| \"retrospective\", \"retro\", \"lessons learned\" | `retrospective` |\n| \"estimation\", \"story points\", \"planning poker\" | `estimation-planning` |\n\n### By category\n\nA curated selection of the most commonly used skills per category.\nFor the full 120+ skill catalog, read `src\u002Fskills\u002FINDEX.md`.\n\n**Process**\n- `workitem-management` — create, transition, and query WorkItems\n- `decision-record` — capture architectural and product decisions as DecisionRecords\n- `event-log` — write auditable log entries for any project event\n- `note-management` — capture, review, and promote fleeting ideas and insights\n- `session-handover` — write an end-of-session handover before shutdown\n- `standup-context` — write a standup update (done \u002F doing \u002F next \u002F blockers)\n- `morning-briefing` — generate a session-start orientation from project state\n- `context-grooming` — periodically prune and compact the project context\n- `release-semver` — plan and execute a semver release\n\n**Architecture**\n- `software-architecture` — high-level system design patterns and trade-offs\n- `system-design` — designing systems from requirements to components\n- `api-design` — REST, RPC, and event-based API contracts\n- `domain-driven-design` — bounded contexts, aggregates, ubiquitous language\n- `software-modularization` — module and package boundary design\n- `microservice-creation` — service extraction, communication patterns, orchestration\n- `event-driven-architecture` — pub-sub, event sourcing, CQRS\n\n**Code quality**\n- `code-review` — reviewing diffs and PRs for correctness, style, and risk\n- `refactoring` — safe, incremental refactoring strategies\n- `tdd-workflow` — test-first development cycle\n- `testing-strategy` — choosing the right test types and coverage targets\n- `debugging` — systematic bug investigation and root-cause analysis\n- `error-handling` — error propagation, recovery, and user-facing messages\n\n**Security**\n- `secure-coding` — OWASP top 10, input validation, output encoding\n- `threat-modeling` — STRIDE analysis and risk prioritisation\n- `secret-management` — credential storage, rotation, and injection\n- `auth-patterns` — authentication and authorization patterns\n\n**Infrastructure**\n- `ci-cd-setup` — pipeline design and configuration\n- `dockerfile-review` — image hardening, layer optimisation, multi-stage builds\n- `kubernetes-basics` — Deployments, Services, ConfigMaps, autoscaling\n- `terraform-basics` — resource definitions, state management, modules\n\n**Observability**\n- `logging-strategy` — structured logging, levels, and retention\n- `metrics-monitoring` — metric types, dashboards, SLOs\n- `distributed-tracing` — trace propagation, span design, sampling\n- `incident-response` — triage, mitigation, and communication during incidents\n\n**Data and AI**\n- `rag-engineering` — retrieval-augmented generation pipelines\n- `prompt-engineering` — prompt design, few-shot examples, chain-of-thought\n- `llm-evaluation` — benchmarking and red-teaming language models\n- `model-recommender` — pick the right AI model via spider-chart profiles and task-plan routing\n- `data-pipeline` — ETL\u002FELT design and orchestration\n- `pandas-polars` — dataframe operations and transformations\n\n**Document creation**\n- `docx-authoring` — python-docx for Word documents\n- `pptx-authoring` — python-pptx for presentations\n- `xlsx-modeling` — openpyxl for spreadsheets and financial models\n- `pdf-workflow` — WeasyPrint \u002F ReportLab \u002F pypdf for PDF generation\n\n**Role-specific**\n- `prd-writing` — product requirements documents\n- `user-research` — interview guides, synthesis, personas\n- `data-storytelling` — turning analysis into decisions for non-technical audiences\n- `legal-review` — pre-consultation contract and compliance review\n- `email-drafter` — professional email drafting with copy-paste output\n\n**Meta**\n- `skill-builder` — design and author new processkit skills\n- `skill-reviewer` — review a skill against the processkit standard\n- `research-with-confidence` — structured research with explicit confidence labels\n- `devils-advocate` — adversarial analysis of a plan or proposal\n- `board-of-advisors` — multi-perspective simulation with named advisor archetypes\n- `morning-briefing` — session-start orientation (also listed under Process)\n\n### How to use a skill\n\nOnce you have identified the right skill:\n\n1. Read the skill's `SKILL.md` — start with the **Intro** (3 sentences) to\n   confirm it is the right match. If yes, read **Overview** for the workflow.\n2. Follow the skill's instructions, adapting to the project's specific context.\n3. Use **Full reference** only for edge cases or field-by-field specs.\n4. If the skill has an MCP server (`mcp\u002FSERVER.md`), its tools are available\n   as function calls — the skill's Overview section describes when to use them.\n\nIf no skill in this index matches, check `src\u002Fskills\u002FINDEX.md` for the full\ncatalog, or use `skill-builder` to author a new skill for the gap.\n\n## Gotchas\n\n- **Loading this skill every time instead of once.** skill-finder is an\n  orientation aid, not a workflow skill. Read it once to identify the right\n  skill, then load that skill and work from it. Do not keep skill-finder\n  loaded alongside the working skill — it consumes context without adding\n  value once you have identified the skill to use.\n- **Treating the trigger-phrase table as exhaustive.** The table maps common\n  phrases; it is not a complete index of all 120+ skills. If no phrase\n  matches, scan the by-category section or read `src\u002Fskills\u002FINDEX.md`. If\n  the task is genuinely novel, use `skill-builder` to create a skill for it.\n- **Skipping skill-finder when the task is \"obvious.\"** The most common\n  mistake is loading a skill by name from memory and discovering mid-task\n  that the skill does not quite fit. Thirty seconds with the trigger-phrase\n  table prevents an incorrect skill invocation. Default to checking even for\n  familiar task types.\n- **Using the category labels to filter instead of the trigger phrases.**\n  The categories help humans browse; agents should match on trigger phrases,\n  not category names. \"Code quality\" does not tell you whether to load\n  `code-review`, `refactoring`, or `tdd-workflow` — the trigger phrase does.\n- **Not updating skill-finder when new skills are added.** When a new skill\n  is added to the catalog, add its trigger phrases to the table and its\n  one-liner to the appropriate category. skill-finder is only reliable if\n  it is kept current. The `skill-builder` skill includes a reminder to\n  update this index.\n- **Confusing skill-finder with skill-builder.** skill-finder helps you\n  find an existing skill. skill-builder helps you create a new one. If\n  skill-finder returns no match, the correct next step is `skill-builder`,\n  not a general-purpose attempt to solve the task without a skill.\n- **Ignoring the `core: true` intent when customising skill packages.**\n  Until aibox enforces `core: true` in the install pipeline, project owners\n  who configure `[skills].include` must add `skill-finder` explicitly.\n  Omitting it means agents lose the navigation aid exactly when the catalog\n  is most customised and therefore hardest to navigate.\n\n## Full reference\n\n### The `core: true` flag\n\nThe `core: true` field in this skill's frontmatter is a **proposed**\nconvention. It signals intent: this skill should be installed unconditionally,\nregardless of `[skills].include` or `[skills].exclude` configuration in\n`aibox.toml`.\n\n**Current status:** the flag is present in the frontmatter as documentation.\naibox does not yet enforce it — a companion aibox issue will land the\n`content_install.rs` change. Until then, project owners must include\n`skill-finder` in any explicit `[skills].include` list.\n\n**Why it matters:** a project owner who limits the installed skills to a\ncurated subset has, by definition, the most non-obvious skill catalog. That\nis precisely when skill-finder is most needed. A skill that can be excluded\nprovides weaker guarantees than one that cannot.\n\n### Keeping this index current\n\nWhen adding a new skill to processkit:\n1. Add 1–3 trigger phrases to the trigger-phrase table\n2. Add a one-liner under the appropriate category in the by-category section\n3. If no existing category fits, add a new category\n\nThe `skill-builder` skill includes a step reminding the author to update\nskill-finder. The `skill-reviewer` skill checks that skill-finder has been\nupdated.\n","# Skill Finder\n\n## Intro\n\nWhen you are unsure which skill to use, start here. This skill maps\nwhat the user is asking for to the skill that handles it. It is not a\nskill you invoke to do work — it is a skill you read to decide what to\ninvoke next.\n\n## Overview\n\n### By trigger phrase\n\nFind the phrase that most closely matches what the user said, then load\nthat skill before proceeding.\n\n| If the user says… | Skill to load |\n|---|---|\n| \"refactor this\", \"clean up the code\" | `refactoring` |\n| \"review this PR\", \"code review\" | `code-review` |\n| \"write a test\", \"test this\", \"TDD\" | `tdd-workflow` |\n| \"testing strategy\", \"what tests do we need\" | `testing-strategy` |\n| \"debug this\", \"find the bug\", \"why is this failing\" | `debugging` |\n| \"design the API\", \"API contract\" | `api-design` |\n| \"system design\", \"design this system\" | `system-design` |\n| \"architecture\", \"how should we structure this\" | `software-architecture` |\n| \"domain model\", \"DDD\" | `domain-driven-design` |\n| \"module structure\", \"package boundaries\", \"split this up\" | `software-modularization` |\n| \"new service\", \"microservice\", \"extract this into a service\" | `microservice-creation` |\n| \"events\", \"event-driven\", \"pub-sub\" | `event-driven-architecture` |\n| \"deploy\", \"CI\u002FCD pipeline\", \"set up CI\" | `ci-cd-setup` |\n| \"Docker\", \"Dockerfile\", \"containerise this\" | `dockerfile-review` |\n| \"Kubernetes\", \"k8s\", \"set up the cluster\" | `kubernetes-basics` |\n| \"Terraform\", \"infrastructure as code\" | `terraform-basics` |\n| \"write SQL\", \"SQL query\", \"query the database\" | `sql-patterns` |\n| \"SQL style\", \"format the SQL\" | `sql-style-guide` |\n| \"database design\", \"schema design\" | `database-modeling` |\n| \"database migration\", \"migrate the schema\" | `database-migration` |\n| \"NoSQL\", \"MongoDB\", \"document store\" | `nosql-patterns` |\n| \"secure this\", \"security review\" | `secure-coding` |\n| \"threat model\" | `threat-modeling` |\n| \"secrets\", \"API keys\", \"credential management\" | `secret-management` |\n| \"auth\", \"authentication\", \"OAuth\" | `auth-patterns` |\n| \"logging\", \"log this\" | `logging-strategy` |\n| \"metrics\", \"monitoring\", \"dashboards\" | `metrics-monitoring` |\n| \"trace\", \"distributed tracing\" | `distributed-tracing` |\n| \"alert\", \"on-call\", \"PagerDuty\" | `alerting-oncall` |\n| \"postmortem\", \"incident review\" | `postmortem-writing` |\n| \"incident\", \"on fire\", \"outage\" | `incident-response` |\n| \"profile this\", \"find the bottleneck\", \"performance\" | `performance-profiling` |\n| \"load test\", \"stress test\" | `load-testing` |\n| \"Python\" | `python-best-practices` |\n| \"TypeScript\", \"JavaScript\" | `typescript-patterns` |\n| \"Go\", \"Golang\" | `go-conventions` |\n| \"Rust\" | `rust-conventions` |\n| \"Java\" | `java-patterns` |\n| \"FastAPI\", \"Python API\" | `fastapi-patterns` |\n| \"gRPC\", \"protobuf\" | `grpc-protobuf` |\n| \"GraphQL\" | `graphql-patterns` |\n| \"Flutter\", \"mobile app\" | `flutter-development` |\n| \"Tailwind\", \"CSS utility classes\" | `tailwind` |\n| \"frontend design\", \"UI components\" | `frontend-design` |\n| \"analyse data\", \"pandas\", \"polars\", \"dataframe\" | `pandas-polars` |\n| \"data pipeline\", \"ETL\", \"data engineering\" | `data-pipeline` |\n| \"data quality\", \"data validation\" | `data-quality` |\n| \"data science\", \"notebook\", \"EDA\" | `data-science` |\n| \"visualise data\", \"chart this\" | `data-visualization` |\n| \"RAG\", \"retrieval\", \"vector search\" | `rag-engineering` |\n| \"embeddings\", \"vector database\" | `embedding-vectordb` |\n| \"prompt engineering\", \"write a prompt\" | `prompt-engineering` |\n| \"evaluate the LLM\", \"benchmark the model\" | `llm-evaluation` |\n| \"which model should I use\", \"recommend a model\", \"which LLM is best\", \"help me pick an AI model\", \"route tasks to the right model\", \"which Claude should I use\" | `model-recommender` |\n| \"ML pipeline\", \"train a model\" | `ml-pipeline` |\n| \"feature engineering\" | `feature-engineering` |\n| \"diagram\", \"draw\", \"whiteboard\", \"Excalidraw\" | `excalidraw` |\n| \"infographic\", \"SVG chart\" | `infographics` |\n| \"logo\", \"brand mark\", \"SVG icon\" | `logo-design` |\n| \"mobile design\", \"iOS\", \"Android UI\" | `mobile-app-design` |\n| \"SEO\", \"search optimisation\", \"meta tags\" | `seo-optimization` |\n| \"Word document\", \"docx\" | `docx-authoring` |\n| \"PowerPoint\", \"slides\", \"pptx\" | `pptx-authoring` |\n| \"Excel\", \"spreadsheet\", \"xlsx\" | `xlsx-modeling` |\n| \"PDF\", \"generate a PDF\" | `pdf-workflow` |\n| \"LaTeX\", \"academic paper\" | `latex-authoring` |\n| \"write a PRD\", \"product requirements\" | `prd-writing` |\n| \"user research\", \"user interview\" | `user-research` |\n| \"data story\", \"present the analysis\" | `data-storytelling` |\n| \"legal review\", \"contract review\" | `legal-review` |\n| \"write an email\", \"draft a message\" | `email-drafter` |\n| \"status update\", \"progress report\" | `status-update-writer` |\n| \"onboard\", \"new joiner guide\" | `onboarding-guide` |\n| \"changelog\", \"what changed in this release\" | `changelog` |\n| \"plan the release\", \"version bump\", \"semver\" | `release-semver` |\n| \"write a decision\", \"document this decision\", \"ADR\" | `decision-record` |\n| \"backlog\", \"work items\", \"create a ticket\" | `workitem-management` |\n| \"log this event\", \"audit trail\" | `event-log` |\n| \"remember this\", \"note this idea\", \"capture this\" | `note-management` |\n| \"write a standup\", \"daily update\" | `standup-context` |\n| \"write a handover\", \"shutting down\", \"container restart\" | `session-handover` |\n| \"morning briefing\", \"catch me up\", \"state of things\" | `morning-briefing` |\n| \"groom the context\", \"clean up context\" | `context-grooming` |\n| \"second opinion\", \"devil's advocate\", \"poke holes in this\" | `devils-advocate` |\n| \"multiple perspectives\", \"board of advisors\" | `board-of-advisors` |\n| \"research this\", \"I'm not sure about this fact\" | `research-with-confidence` |\n| \"build a new skill\", \"author a skill\" | `skill-builder` |\n| \"review this skill\", \"is this skill good\" | `skill-reviewer` |\n| \"dependency audit\", \"check dependencies\" | `dependency-audit` |\n| \"dependency management\", \"update packages\" | `dependency-management` |\n| \"git workflow\", \"branching strategy\", \"commit message\" | `git-workflow` |\n| \"shell script\", \"bash script\" | `shell-scripting` |\n| \"caching\", \"cache strategy\" | `caching-strategies` |\n| \"concurrency\", \"async\", \"parallelism\" | `concurrency-patterns` |\n| \"webhook\", \"callback URL\" | `webhook-integration` |\n| \"error handling\", \"exception handling\" | `error-handling` |\n| \"documentation\", \"write the docs\" | `documentation` |\n| \"retrospective\", \"retro\", \"lessons learned\" | `retrospective` |\n| \"estimation\", \"story points\", \"planning poker\" | `estimation-planning` |\n\n### By category\n\nA curated selection of the most commonly used skills per category.\nFor the full 120+ skill catalog, read `src\u002Fskills\u002FINDEX.md`.\n\n**Process**\n- `workitem-management` — create, transition, and query WorkItems\n- `decision-record` — capture architectural and product decisions as DecisionRecords\n- `event-log` — write auditable log entries for any project event\n- `note-management` — capture, review, and promote fleeting ideas and insights\n- `session-handover` — write an end-of-session handover before shutdown\n- `standup-context` — write a standup update (done \u002F doing \u002F next \u002F blockers)\n- `morning-briefing` — generate a session-start orientation from project state\n- `context-grooming` — periodically prune and compact the project context\n- `release-semver` — plan and execute a semver release\n\n**Architecture**\n- `software-architecture` — high-level system design patterns and trade-offs\n- `system-design` — designing systems from requirements to components\n- `api-design` — REST, RPC, and event-based API contracts\n- `domain-driven-design` — bounded contexts, aggregates, ubiquitous language\n- `software-modularization` — module and package boundary design\n- `microservice-creation` — service extraction, communication patterns, orchestration\n- `event-driven-architecture` — pub-sub, event sourcing, CQRS\n\n**Code quality**\n- `code-review` — reviewing diffs and PRs for correctness, style, and risk\n- `refactoring` — safe, incremental refactoring strategies\n- `tdd-workflow` — test-first development cycle\n- `testing-strategy` — choosing the right test types and coverage targets\n- `debugging` — systematic bug investigation and root-cause analysis\n- `error-handling` — error propagation, recovery, and user-facing messages\n\n**Security**\n- `secure-coding` — OWASP top 10, input validation, output encoding\n- `threat-modeling` — STRIDE analysis and risk prioritisation\n- `secret-management` — credential storage, rotation, and injection\n- `auth-patterns` — authentication and authorization patterns\n\n**Infrastructure**\n- `ci-cd-setup` — pipeline design and configuration\n- `dockerfile-review` — image hardening, layer optimisation, multi-stage builds\n- `kubernetes-basics` — Deployments, Services, ConfigMaps, autoscaling\n- `terraform-basics` — resource definitions, state management, modules\n\n**Observability**\n- `logging-strategy` — structured logging, levels, and retention\n- `metrics-monitoring` — metric types, dashboards, SLOs\n- `distributed-tracing` — trace propagation, span design, sampling\n- `incident-response` — triage, mitigation, and communication during incidents\n\n**Data and AI**\n- `rag-engineering` — retrieval-augmented generation pipelines\n- `prompt-engineering` — prompt design, few-shot examples, chain-of-thought\n- `llm-evaluation` — benchmarking and red-teaming language models\n- `model-recommender` — pick the right AI model via spider-chart profiles and task-plan routing\n- `data-pipeline` — ETL\u002FELT design and orchestration\n- `pandas-polars` — dataframe operations and transformations\n\n**Document creation**\n- `docx-authoring` — python-docx for Word documents\n- `pptx-authoring` — python-pptx for presentations\n- `xlsx-modeling` — openpyxl for spreadsheets and financial models\n- `pdf-workflow` — WeasyPrint \u002F ReportLab \u002F pypdf for PDF generation\n\n**Role-specific**\n- `prd-writing` — product requirements documents\n- `user-research` — interview guides, synthesis, personas\n- `data-storytelling` — turning analysis into decisions for non-technical audiences\n- `legal-review` — pre-consultation contract and compliance review\n- `email-drafter` — professional email drafting with copy-paste output\n\n**Meta**\n- `skill-builder` — design and author new processkit skills\n- `skill-reviewer` — review a skill against the processkit standard\n- `research-with-confidence` — structured research with explicit confidence labels\n- `devils-advocate` — adversarial analysis of a plan or proposal\n- `board-of-advisors` — multi-perspective simulation with named advisor archetypes\n- `morning-briefing` — session-start orientation (also listed under Process)\n\n### How to use a skill\n\nOnce you have identified the right skill:\n\n1. Read the skill's `SKILL.md` — start with the **Intro** (3 sentences) to\n   confirm it is the right match. If yes, read **Overview** for the workflow.\n2. Follow the skill's instructions, adapting to the project's specific context.\n3. Use **Full reference** only for edge cases or field-by-field specs.\n4. If the skill has an MCP server (`mcp\u002FSERVER.md`), its tools are available\n   as function calls — the skill's Overview section describes when to use them.\n\nIf no skill in this index matches, check `src\u002Fskills\u002FINDEX.md` for the full\ncatalog, or use `skill-builder` to author a new skill for the gap.\n\n## Gotchas\n\n- **Loading this skill every time instead of once.** skill-finder is an\n  orientation aid, not a workflow skill. Read it once to identify the right\n  skill, then load that skill and work from it. Do not keep skill-finder\n  loaded alongside the working skill — it consumes context without adding\n  value once you have identified the skill to use.\n- **Treating the trigger-phrase table as exhaustive.** The table maps common\n  phrases; it is not a complete index of all 120+ skills. If no phrase\n  matches, scan the by-category section or read `src\u002Fskills\u002FINDEX.md`. If\n  the task is genuinely novel, use `skill-builder` to create a skill for it.\n- **Skipping skill-finder when the task is \"obvious.\"** The most common\n  mistake is loading a skill by name from memory and discovering mid-task\n  that the skill does not quite fit. Thirty seconds with the trigger-phrase\n  table prevents an incorrect skill invocation. Default to checking even for\n  familiar task types.\n- **Using the category labels to filter instead of the trigger phrases.**\n  The categories help humans browse; agents should match on trigger phrases,\n  not category names. \"Code quality\" does not tell you whether to load\n  `code-review`, `refactoring`, or `tdd-workflow` — the trigger phrase does.\n- **Not updating skill-finder when new skills are added.** When a new skill\n  is added to the catalog, add its trigger phrases to the table and its\n  one-liner to the appropriate category. skill-finder is only reliable if\n  it is kept current. The `skill-builder` skill includes a reminder to\n  update this index.\n- **Confusing skill-finder with skill-builder.** skill-finder helps you\n  find an existing skill. skill-builder helps you create a new one. If\n  skill-finder returns no match, the correct next step is `skill-builder`,\n  not a general-purpose attempt to solve the task without a skill.\n- **Ignoring the `core: true` intent when customising skill packages.**\n  Until aibox enforces `core: true` in the install pipeline, project owners\n  who configure `[skills].include` must add `skill-finder` explicitly.\n  Omitting it means agents lose the navigation aid exactly when the catalog\n  is most customised and therefore hardest to navigate.\n\n## Full reference\n\n### The `core: true` flag\n\nThe `core: true` field in this skill's frontmatter is a **proposed**\nconvention. It signals intent: this skill should be installed unconditionally,\nregardless of `[skills].include` or `[skills].exclude` configuration in\n`aibox.toml`.\n\n**Current status:** the flag is present in the frontmatter as documentation.\naibox does not yet enforce it — a companion aibox issue will land the\n`content_install.rs` change. Until then, project owners must include\n`skill-finder` in any explicit `[skills].include` list.\n\n**Why it matters:** a project owner who limits the installed skills to a\ncurated subset has, by definition, the most non-obvious skill catalog. That\nis precisely when skill-finder is most needed. A skill that can be excluded\nprovides weaker guarantees than one that cannot.\n\n### Keeping this index current\n\nWhen adding a new skill to processkit:\n1. Add 1–3 trigger phrases to the trigger-phrase table\n2. Add a one-liner under the appropriate category in the by-category section\n3. If no existing category fits, add a new category\n\nThe `skill-builder` skill includes a step reminding the author to update\nskill-finder. The `skill-reviewer` skill checks that skill-finder has been\nupdated.\n",{"name":5,"metadata":49,"description":57},{"processkit":50},{"id":51,"core":52,"created":53,"version":54,"category":55,"apiVersion":56},"SKILL-skill-finder",true,1775606400000,"1.0.0","meta","processkit.projectious.work\u002Fv1","Navigation aid for the processkit skill catalog — maps natural-language\ncues and task types to the right skill. Read this when you are unsure\nwhich skill applies to the current task, when the user names a task\nwithout naming a skill, or at session start when orienting to an\nunfamiliar project. Always the first skill to consult; never the last.\n","main","4876a92620ee792aac2ac9a1a806322d8a572367","archive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.7.0\u002Fskills\u002Fskill-finder","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit","https:\u002F\u002Fprojectious-work.github.io\u002Fprocesskit\u002F","https:\u002F\u002Fgithub.com\u002Fprojectious-work","2026-11-11 23:24:18",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":52},[67,70,73],{"tool":68,"command":69},"npx","npx skills add projectious-work\u002Fprocesskit --skill skill-finder",{"tool":71,"command":72},"bunx","bunx skills add projectious-work\u002Fprocesskit --skill skill-finder",{"tool":74,"command":75},"pnpm","pnpm dlx skills add projectious-work\u002Fprocesskit --skill skill-finder","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Farchive\u002Fprocesskit-install-20261101\u002Fcontext\u002Ftemplates\u002Fprocesskit\u002Fv0.7.0\u002Fskills\u002Fskill-finder\u002FSKILL.md",[],[79,101,121,142,159,177],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":86,"publishedAt":44},"01M6X5MTC89B4ZGXW3JVSQCPF8","skill-management","Manage Skill package manifests as v1 ontology entities.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fskill-management\u002FSKILL.md",[85],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,88,89,90,91,92,42,93,94,95,81,96,97,98,28,99,100],"management","skill management","create","update","package","alpha","list","manage","ontology","get","as","manifests","skill package","transition",{"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":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":108,"publishedAt":44},"01M6X5MCV74NHW5MEDNHZRF2C8","schema-management","Manage generated processkit schema contracts through deterministic MCP rebuild and inspection workflows.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fschema-management\u002FSKILL.md",[107],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[87,109,110,111,112,113,92,42,114,115,94,116,117,118,96,119,120],"schema","schema management","MCP","workflows","validation","generated","rebuild","contracts","wed","deterministic","contract","mode",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":44},"01M6X5M5G6YJ96AMZGSCZJ1D13","proposition-management","Record claims, risks, beliefs, world facts, WSJF estimates, and assumptions through the Proposition interface.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fproposition-management\u002FSKILL.md",[],[87,128,129,89,90,130,92,42,131,132,133,134,96,135,136,137,138,139,140,141],"proposition","proposition management","index","log","world","record","query","creation","event","interface","updates","facts","claims","WSJF",{"skillNo":143,"name":144,"nameZh":6,"description":145,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":146,"categories":147,"keywords":148,"publishedAt":44},"01M6X5KMQ83QN9M6MPWZM7344F","ontology-management","Manage generated v1 ontology entities that do not require a dedicated domain server.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fontology-management\u002FSKILL.md",[],[87,95,149,89,92,150,151,114,152,131,94,153,154,96,155,156,136,157,28,158],"ontology management","lifecycle","archive","roadmap","do","domain","iteration","keep","measurement","generic",{"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":165,"publishedAt":44},"01M6X5KCY2DN3SM21RERSFNEBT","okf-compatibility","Import, export, and validate conformant Open Knowledge Format bundles.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fokf-compatibility\u002FSKILL.md",[],[166,167,168,169,92,170,171,172,42,173,174,175,176],"okf","compatibility","okf compatibility","validate","open","knowledge","format","export","bundles","bundle","import",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":183,"publishedAt":44},"01M6X5JA8S5PNGJVFW4EQY8T83","capability-management","Manage versioned Capability entities and their governed lifecycle.","https:\u002F\u002Fgithub.com\u002Fprojectious-work\u002Fprocesskit\u002Fblob\u002Fmain\u002Fsrc\u002Fcontext\u002Fskills\u002Fprocesskit\u002Fcapability-management\u002FSKILL.md",[],[87,184,185,89,90,130,92,150,42,93,131,186,94,133,96,156,136,137,187,100],"capability","capability management","queries","changes"]