Menu
Use when: SSMA console operations — create project, generate assessment report, convert schema, migrate data, Oracle to SQL Server migration, schema conversion, data migration
Basé sur la classification professionnelle SOC
Expert on the history, origin, and correct use of the em dash. Use when writing or reviewing code, comments, or data files to avoid em and en dashes, defaulting to never using them and replacing any found with a hyphen (-). Includes strong knowledge of punctuation marks and the proper usage of punctuation characters when writing comments.
Use when an outage, production incident, or significant service degradation has occurred and the team needs to write a structured blameless post-mortem. Triggers on phrases like "write a post-mortem", "incident review", "what went wrong", "outage report", "root cause analysis", or "RCA". Covers timeline reconstruction, contributing factor analysis, impact quantification, and action item generation with owners.
Create, set up, or update the personal context portfolio: structured markdown files describing who you are, how you work, your teams, and your tool/ADO configuration. Runs the interview workflow for first-time setup and targeted edits for updates. Trigger this skill when the user asks to: set up their context, create or update their context portfolio, "create my IQ", "set up my IQ", edit their profile, add/remove a stakeholder, update ADO config, change team info, update pillars, or set up any plugin configuration. Trigger when another skill fails to find context (missing files or TODO markers) and needs context populated. Also trigger when the user mentions a context change in passing (e.g., "my manager changed", "we added someone to the team") to offer a context file update. Do NOT trigger for read-only questions like "who's on my team?" or "what's my ADO config?". Those are answered directly from the context files referenced in the loaded custom instructions; no skill is needed.
Adopt repository-level harness engineering for coding agents. Use when a user wants to prevent repeated AI coding-agent mistakes by turning failures into durable instructions, drift checks, regression tests, failure memory, and adoption reports tailored to the target repository.
Security hardening reviewer for GitHub Actions workflow files (.github/workflows/*.yml). Reasons about the Actions threat model that pattern matchers and general code linters miss — untrusted-input script injection, privileged triggers running fork code, mutable action references, and over-scoped tokens. Use this skill when asked to review, audit, harden, or secure a GitHub Actions workflow, when writing a new workflow, or for any request like "is this workflow safe?", "review my CI for security issues", "why is pull_request_target dangerous here?", "pin my actions", or "lock down GITHUB_TOKEN permissions". Covers script injection via ${{ }} interpolation, pull_request_target / workflow_run privilege escalation, SHA-pinning of third-party actions, least-privilege permissions, GITHUB_ENV/GITHUB_OUTPUT injection, secret exposure, OIDC over long-lived credentials, and self-hosted runner exposure on public repositories.
Build GitHub Copilot workflows with Xquik X API SDKs, REST endpoints, MCP tools, signed webhooks, tweet search, user lookup, follower exports, media actions, and agent automation.
| name | ssma-console |
| description | Use when: SSMA console operations — create project, generate assessment report, convert schema, migrate data, Oracle to SQL Server migration, schema conversion, data migration |
Generate XML configs and invoke SSMAforOracleConsole.exe directly — no external scripts or wrappers.
Operations (run in order for "full migration"):
Ask for missing parameters. Defaults in parentheses.
Oracle: Host (localhost), Port (1521), Instance (required, service name), User, Password, Schema
SQL Server: Server, Database, User, Password, Encrypt (true), Trust Server Certificate (true), Target Schema (dbo)
Project: Name (ssma-migration), Folder (.), Type (sql-server-2022 — also 2016/2017/2019/2025/sql-azure), SSMA Path (C:\Program Files\Microsoft SQL Server Migration Assistant for Oracle\bin\SSMAforOracleConsole.exe)
Resolve ALL {PLACEHOLDER} tokens before writing. Generate 3 files:
ssma-variables.xml<?xml version="1.0" encoding="utf-8"?>
<variables>
<variable name="$WorkingFolder$" value="{PROJECT_FOLDER}" />
<variable name="$ProjectType$" value="{PROJECT_TYPE}" />
<variable name="$ProjectName$" value="{PROJECT_NAME}" />
<variable-group name="OracleConnection">
<variable name="$OracleHostName$" value="{ORACLE_HOST}" />
<variable name="$OracleInstance$" value="{ORACLE_INSTANCE}" />
<variable name="$OraclePort$" value="{ORACLE_PORT}" />
<variable name="$OracleUserName$" value="{ORACLE_USER}" />
<variable name="$OraclePassword$" value="{ORACLE_PASSWORD}" />
<variable name="$OracleSchemaName$" value="{ORACLE_SCHEMA}" />
</variable-group>
<variable-group name="SQLServerConnection">
<variable name="$SQLServerName$" value="{SQL_SERVER}" />
<variable name="$SQLServerDb$" value="{SQL_DATABASE}" />
<variable name="$SQLServerUsrID$" value="{SQL_USER}" />
<variable name="$SQLServerPwd$" value="{SQL_PASSWORD}" />
</variable-group>
<variable-group name="ReportSettings">
<variable name="$SummaryReportFile$" value="Reports\Assessment\AssessmentReport.xml" />
<variable name="$ConversionReportFile$" value="Reports\Conversion\ConversionReport.xml" />
<variable name="$ConversionReportFolder$" value="Reports\Conversion" />
<variable name="$DataMigrationReportFile$" value="Reports\Migration\DataMigrationReport.xml" />
<variable name="$SynchronizationReportFolder$" value="Reports\Synchronization" />
</variable-group>
</variables>
ssma-servers.xmlCRITICAL: Use tns-name-mode — standard-mode treats instance as SID and fails with ORA-12505.
<?xml version="1.0" encoding="utf-8"?>
<servers>
<oracle name="source_oracle">
<tns-name-mode>
<connection-provider value="OracleClient" />
<service-name value="(DESCRIPTION =(ADDRESS_LIST =(ADDRESS = (PROTOCOL = TCP)(HOST = $OracleHostName$)(PORT = $OraclePort$)))(CONNECT_DATA =(SERVICE_NAME = $OracleInstance$)))" />
<user-id value="$OracleUserName$" />
<password value="$OraclePassword$" />
</tns-name-mode>
</oracle>
<sql-server name="target_sqlserver">
<sql-server-authentication>
<server value="$SQLServerName$" />
<database value="$SQLServerDb$" />
<user-id value="$SQLServerUsrID$" />
<password value="$SQLServerPwd$" />
<encrypt value="{ENCRYPT}" />
<trust-server-certificate value="{TRUST_CERT}" />
</sql-server-authentication>
</sql-server>
</servers>
Generate one script per operation. All scripts share this common <config> block (add <object-overwrite action="overwrite" /> for migrate-schema/migrate-data, add <data-migration-connection source-use-last-used="true" target-server="target_sqlserver" /> for migrate-data, use every-5% progress for schema/data ops):
<config>
<output-providers>
<output-window suppress-messages="false" destination="stdout" />
<upgrade-project action="yes" />
<user-input-popup mode="continue" />
<progress-reporting enable="true" report-messages="true" report-progress="every-10%" />
<log-verbosity level="info" />
</output-providers>
</config>
All scripts start with this preamble in <script-commands>:
<create-new-project project-folder="$WorkingFolder$" project-name="$ProjectName$"
overwrite-if-exists="true" project-type="$ProjectType$" />
<connect-source-database server="source_oracle">
<object-to-collect object-name="$OracleSchemaName$" />
</connect-source-database>
CRITICAL: Always include <object-to-collect> — without it, map-schema fails with "Source namespace was not found".
Per-operation commands (after preamble, before <save-project />):
| Operation | File | Commands after preamble |
|---|---|---|
| create-project | ssma-create-project.xml | connect-target-database → map-schema source-schema="$OracleSchemaName$" sql-server-schema="$SQLServerDb$.{TARGET_SCHEMA}" |
| generate-report | ssma-assessment.xml | generate-assessment-report object-name="$OracleSchemaName$" object-type="Schemas" write-summary-report-to="$SummaryReportFile$" verbose="true" report-errors="true" |
| migrate-schema | ssma-schema.xml | connect-target-database → map-schema → convert-schema (to $ConversionReportFile$) → synchronize-target object-name="$SQLServerDb$.{TARGET_SCHEMA}" |
| migrate-data | ssma-data.xml | Same as migrate-schema + refresh-from-database → migrate-data object-name="$OracleSchemaName$.Tables" object-type="category" (to $DataMigrationReportFile$) → close-project |
Show resolved XML and command to user. Confirm before running.
New-Item -ItemType Directory -Force -Path "Reports\Assessment","Reports\Conversion","Reports\Migration","Reports\Synchronization","Logs" | Out-Null
& "{SSMA_CONSOLE_PATH}" -s "{SCRIPT_XML}" -c "ssma-servers.xml" -v "ssma-variables.xml" -l "Logs\{OPERATION}.log"
Check exit code (0 = success), read logs and reports (Reports\Assessment\, Reports\Conversion\, Reports\Migration\), summarize findings.
.ps1, .bat, .sh{...} in final XML| Symptom | Fix |
|---|---|
ORA-12505: SID not registered | Use tns-name-mode, not standard-mode |
Source namespace was not found | Add <object-to-collect> to connect-source-database |
not found in metabase on force-load | Use object-to-collect instead — force-load is unreliable |
SQL Server Agent is not running | Warning only — BCP client-side migration still works |