Skill catalogue and prerequisites
Choose by task and distinguish standalone search packages, full-repository workflows, and Data Foundry requirements.
Choose by the input you have and the result you need, then check prerequisites and write risks. These 21 entries come from the reviewed Skills revision. This is not a promise that installing everything makes every workflow ready.
Independently installable: three search skills
Each includes its launcher, example, and references, with no Skills/CLI checkout or Data Foundry requirement. Follow installation and replace only the name after --skill. All need the specified Node.js/pnpm versions and human-completed CLI OAuth sign-in.
| Skill | Input → result | Prerequisite or boundary |
|---|---|---|
flow-hybrid-search | Flow description and optional filters → candidate flows | Remote read-only |
process-hybrid-search | Process description and optional filters → candidate processes | Remote read-only |
lifecyclemodel-hybrid-search | Model description and optional filters → candidate models | Remote read-only |
Full Skills repository: build, review, and operations
These wrappers still use the repository-level shared launcher, and some read other skills’ rules or assets. Copying a single directory is insufficient. Have the workflow maintainer prepare the complete layout, matching CLI, and task inputs. These are not the beginner standalone installation path.
| Skill | Input → result | Prerequisite or boundary |
|---|---|---|
process-automated-builder | Reference flow, evidence, and plan → local process build and publishing handoff | Building and publishing are separate; publishing needs approval |
lifecyclemodel-automated-builder | Existing process builds → life-cycle model and connections | Requires upstream build directories |
lifecyclemodel-resulting-process-builder | Existing model and process data → aggregated process and relations | May read remote data; publishing needs separate authorization |
lifecyclemodel-recursive-orchestrator | Prepared candidates and build request → multi-layer models, graph, and lineage | Depends on other builders and the complete runtime layout |
lifecycleinventory-review | Local builds or frozen remote snapshots → inventory quality report | Review output is not publishing approval |
flow-governance-review | Flow snapshots and repair plan → QA, repair, and publishing preparation | Some subcommands write; approve each step |
process-dedup-review | Grouped duplicate snapshots → keep/delete recommendations and evidence | A recommendation is not deletion permission |
process-scope-statistics | Authorized process scope → snapshot, coverage statistics, and reports | Remote reads; retain scope and count evidence |
current-account-dataset-review | Current-account snapshots → validation, reference repair, drafts, and audit | Review and repair permissions are distinct |
tiangong-lca-remote-ops | Specific process maintenance input → reference refresh and post-write checks | May write remotely; not an unrestricted admin interface |
lca-publish-executor | Completed publishing handoff → preflight, publish, and verification reports | Actual writes need explicit approval |
embedding-ft | Operational input → embedding-job investigation or processing | Operations only, not part of the introduction |
Instruction-led skills
These organize existing CLI capabilities. Installing instructions does not prepare inputs, dependencies, or permissions. Use them within an explicit task scope; advanced maintenance is not ordinary search.
| Skill | Input → result | Prerequisite or boundary |
|---|---|---|
tidas-contract-context | Dataset type and task → schema, methodology, and rules context | Needs a working CLI; prepares authoring context |
tidas-bilingual-transcreation | Extracted translation units and evidence → reviewed Chinese/English fields | Explicit post-import language completion only, not an import/publish gate |
dataset-rls-maintenance | Current-account maintenance scope → plan, approval, and verification | May delete or modify data; high risk |
Data production that depends on Data Foundry
These tasks require Foundry workspaces, manifests, or scripts. Do not assume one Skill installation is enough. For local conversion only, start with the independent tidas tool.
| Skill | Input → result | Prerequisite or boundary |
|---|---|---|
external-dataset-curated-import | Legitimately obtained package and Foundry manifest → curated candidates | Needs Foundry, import configuration, and downstream skills |
source-evidence-dataset-development | Source documents and Foundry seed → evidence dossier and candidates | May need additional research/document tools |
tidas-data-import | Package or source files → conversion/authoring and import preparation | Needs Foundry; local conversion can use tidas directly |
Complete one read-only task before introducing production workflows. Before real writes, read Organize tasks safely; for sign-in or script issues, use troubleshooting.