sdlc-skills

Measure the token/cost/time efficiency of AI coding-agent work — per session, per role, per day, and per individual sub-agent — with every dollar metered by ccusage. Use when the user asks "what did this cost", cost per session/role/test case, which role/sub-agent burned the most, tool-call/skill/time breakdowns, "before vs after" cost comparisons, or wants to audit AI spend over time.

Per-role persistent memory — durable facts, preferences, decisions, and a daily log, as plain markdown. Use when the user says "remember this" or "log this", asks "what did you learn yesterday", or whenever you discover something worth keeping across sessions.

UI/E2E test automation with Playwright MCP. Use when the user asks to "test the UI", "automate browser tests", "check the page", "take a screenshot", "run Playwright", "write E2E tests", or anything about browser-based testing.

Turn a vague bug report into precise, repeatable steps with evidence and a CONFIRMED / CANNOT-REPRODUCE / PARTIAL verdict. Use when a bug is unclear or unconfirmed and needs reproduction before RCA or any fix. Reproduction and documentation only — does not fix code.

Generate AGENTS.md and .agents/ configuration files for a new project. Use when the user asks to "seed the project", "onboard this repo", "generate project config", "create AGENTS.md", or after the scout has explored the codebase.

Use when a TMS test case needs to become an automated test, or when automating a regression batch — "automate TC-NNN", "convert this case to a framework test", any flow from a manual case to green framework tests. Pluggable TMS (Zephyr/TestRail/Xray/Azure/markdown).

Use when a TMS test case needs manual execution, handle discovery (selectors / endpoints / element-ids / metric queries — whatever the surface uses), or defect investigation before automation — "analyse SCRUM-T101", "run this case and emit an AFS", any pre-automation case exploration. Produces an Automation-Friendly Spec (AFS); does not write test code.

Microsoft 365 (Graph) access to email, Teams, calendar, and SharePoint. Use when the user asks to "check my email/Teams/calendar", "what meetings do I have", "any messages about X", or whenever a task needs live M365 data rather than memory. Scriptable scans + interactive query.py.

Use when a manual-QA agent does live browser testing through the Playwright MCP server — exploring/profiling a web app or executing a web test case against a running app, with no test code generated. Web/PWA/hybrid targets; used by app-profiler and test-runner. Mobile native → use mobile-testing instead.

Generate AGENTS.md and .agents/ configuration files for a new project. Use when the user asks to "seed the project", "onboard this repo", "generate project config", "create AGENTS.md", or after the scout has explored the codebase.

Use when you need to run arbitrary JS in a page, inspect cookies/localStorage, check computed styles, emulate devices, or drive real mouse/keyboard events. Chrome DevTools Protocol browser automation with zero external dependencies.

Use when the user says "fix bug", "fix

Review code for correctness, security, performance, and maintainability. Use when the user asks to "review this code", "check my changes", "review PR", "audit" — and proactively after a non-trivial change or before opening, approving, or merging a PR, even unprompted.

Use after implementing a routed task, when working code needs to be committed, pushed, PR'd, commented on the issue, and handed to a reviewer. The canonical task-handoff protocol; runs standalone or as the final phase of implement-feature.

Use when the user asks to "commit", "create PR", "branch", "merge", "rebase", "cherry-pick", "tag", or otherwise manage git history. Guides disciplined git operations — branching, commits, PRs, and recovery.

Use when the user says "implement", "build feature", "work on task", or once a plan or story is approved and you're about to start building. The end-to-end feature-implementation workflow; delegates the final handoff to completing-a-task.

Create, manage, and track issues in GitHub, Linear, or GitLab. Use when the user asks to "create an issue", "file a bug", "check issues", "update a ticket", "create an epic", or anything about issue/ticket management.

Per-role persistent memory — durable facts, preferences, decisions, and a daily log, as plain markdown. Use when the user says "remember this" or "log this", asks "what did you learn yesterday", or whenever you discover something worth keeping across sessions.

Use when the user says "plan a feature", "design this", "how should we build", or before writing code for any non-trivial feature. Produces an approved task breakdown before implementation begins — plan first, build second.

Turn a vague bug report into precise, repeatable steps with evidence and a CONFIRMED / CANNOT-REPRODUCE / PARTIAL verdict. Use when a bug is unclear or unconfirmed and needs reproduction before RCA or any fix. Reproduction and documentation only — does not fix code.

Use after a bug is reproduced/confirmed and before proposing a fix, or when the user says "investigate issue", to trace a bug to its exact cause in the codebase. Investigation only — reports the cause on the ticket; does not edit code.

Use when asked to run a retrospective, mine past sessions, or improve the team from what already happened — turning prior Claude Code conversations and sub-agent sessions into proposed memory and workflow updates. Used by scout.

Use when a TMS test case needs to become an automated test, or when automating a regression batch — "automate TC-NNN", "convert this case to Playwright", any flow from a manual case to green framework tests. Pluggable TMS (Zephyr/TestRail/Xray/Azure/markdown).

Use when a TMS test case needs manual execution, selector discovery, or defect investigation before automation — "analyse SCRUM-T101", "run this case and emit an AFS", any pre-automation case exploration. Produces an Automation-Friendly Spec (AFS); does not write test code.

Mobile app testing for all manual-qa agents. Covers native iOS/Android via Appium MCP and Mobitru device farm, and PWA/hybrid via Playwright mobile viewport. Use when profiling a mobile app, authoring mobile TCs, sizing mobile TCs, orchestrating a mobile suite run, executing a mobile TC, generating a manual guide, or producing a mobile run report.

Read .xlsx/.xls spreadsheets (test cases, checklists, requirement matrices) into Markdown tables so an agent can ingest them. Use when the user provides an Excel file of test cases or requirements, or asks to import a spreadsheet.

Create well-formatted Jira issues/comments and Confluence pages on both Cloud and Server/Data Center, with mandatory post-creation re-fetch + repair. Load for "file a bug", "comment on JIRA-123", "write up a decision page", or any authored Atlassian content.

Disk-first, checkpointed research workflow with three modes — trend research, topic analysis, and fact-checking. Use when the user asks to "research trends", "analyze a topic", "fact-check this", "verify claims", "what's the state of X", or hands you a document to vet.

Gather cross-channel context (local KB, email, Teams, optional web) about a person or topic before responding. Use when the user says "what do we know about X", "find prior discussions with Y", or before drafting any reply where prior history matters.

Headless, file-system Obsidian vault operations (no Obsidian app needed). Use when the user says "save to vault", "log this note", "find my notes about X", "what's in my inbox", "open loops", or when filing an incoming signal (email/chat/memo) or updating people/project/meeting notes.

Tricentis TOSCA Cloud automation via the bundled tosca_cli.py — create/update/run TestCases, Modules, Reusable Blocks, Playlists, folders, and TSU import/export. Use when the user asks to create a TOSCA test case, run a playlist, organize cases, or any TOSCA Cloud REST/CLI operation.

Goal-backward verification — checks whether the desired outcome was achieved, not whether tasks were marked done. Use when the user asks to "verify", "did this actually work", "is X really done" — or before you claim a task is complete and before closing an issue / merging a PR.

Bootstrap, configure, and author tests for the Vividus BDD framework — JBehave-based, config-first .story files spanning web/REST/mobile/DB via 47+ plugins. Use when the user mentions Vividus, .story files, vividus-bom/-starter, backtick-parameter BDD, or ./gradlew runStories.

CRUD + results import on Xray entities (Test, Precondition, Test Set/Plan/Execution/Run) across Cloud (GraphQL) and Server/DC (REST). Load for "pull test PROJ-T42", "create Xray test from this AFS", "upload JUnit to test plan", or any Xray CRUD.