The daily-work arc in one plugin, entered via /daily (hybrid router: bare = 5-station menu — start/work/file/report/wrap — argument jumps straight there; see PLAYBOOK.md at the marketplace repo root). Design & planning: grill-then-plan. Debug chain: debug-mantra -> (grill-then-plan when the fix involves a design choice) -> post-mortem -> generating-test-cases (regression case) -> management-talk. Review & verification: scrutinize, review-pr (GitHub PR review — safe workspace, scrutinize as the judge, then send-back / fix-it / chat-only), dual-verifier. Testing & QA: generating-test-cases (evidence-grounded test-case suites for a feature/change/fixed bug, rendered to Excel/Markdown/CSV or delegated to a tracker). Documents: sa-doc (full SA&D document — use cases, diagrams, data dictionary, architecture — generated from one validated model; Markdown canonical, PDF optional). System study: study-design-verify, fit-gap-analysis, naming-audit, drive-to-legacy, crm-archaeology (Dynamics 365/Dataverse org study), ticket-trace. Communication: management-talk, invoice-generator (Tribletext daily summary from git commits), problem-description (interactive HTML walkthroughs). Reflection: reflect (session retrospective that routes each lesson into an owned skill, a CLAUDE.md, a cross-project GOTCHAS.md, or memory — closing the daily arc with a learn beat).
The one daily-work command — routes you to the right skill for your moment in the day. Bare = 5-station menu (start / work / file / report / wrap); with a station word it jumps straight there. The entry point into the whole daily arc mapped in PLAYBOOK.md.
Generate a complete SA&D document (use cases, diagrams, data dictionary, architecture) from one validated model — Markdown canonical, PDF optional. Academic or professional profile.
Study a live Dynamics 365 / Dataverse environment end-to-end and produce one ARCHITECTURE.md — pull every customization to disk (solutions, entities, forms, JS and React web resources, PCF controls, classic workflows, plugins, cloud flows, classic RibbonDiffXml AND modern commands, security roles, embedded Power BI), map every business entity (standard AND custom), then trace the business processes layer by layer. Use whenever the user wants to learn, study, understand, reverse-engineer, audit, or document an existing Dynamics 365 / CRM / Dataverse org or model-driven app — "how does this CRM work", "document my D365 org", "learn the business logic of this environment", "what does this solution actually do", onboarding to a customer's CRM, or scoping a migration/rebuild. Read-only by design — it never writes to the org. NOT for building or changing CRM components (use the dataverse plugin skills) or for studying a plain source-code repo (use drive-to-legacy).
The single entry point into the daily-work arc — a hybrid menu/argument router. Trigger whenever the user invokes /dev-workflows:daily, types /daily, asks "what should I do now", "where was I", "start my day", "what's next today", "wrap up my day", "end my day", or seems unsure which skill fits their current daily-work moment. Bare invocation shows a 5-station menu (starting / working / filing findings / reporting / wrapping up); with an argument (start | work | file | report | wrap, synonyms accepted) it jumps straight to the station and hands off to the right skill: ado-backlog:my-work, the situational toolbox (grill-then-plan, debug-mantra, study-design-verify, naming-audit, fit-gap-analysis, problem-description, ticket-trace, scrutinize, review-pr, dual-verifier, drive-to-legacy, crm-archaeology, generating-test-cases), findings-to-ado-backlog or ado-create-work-items (github-backlog twins on request), management-talk, or invoice-generator.
Four-mantra debugging discipline — reproduce, trace the fail path, falsify the hypothesis, cross-reference every breadcrumb. Recite the mantra block verbatim at the start of any debugging session, then apply the four steps in order before proposing any fix. Trigger on /debug-mantra and proactively whenever debugging starts — user reports a bug, says something is broken/throwing/failing, asks to debug/diagnose/investigate an issue, or pastes a stack trace or error log.
Use when exploring, studying, or porting an unfamiliar legacy codebase. Triggers when the user says "explore this project", "understand this code", "I need to port this", "how does this app work", "document this codebase", "study this code", or any request to deeply understand an existing project they did not write. Also triggers when onboarding to a new repo or preparing migration/rewrite plans.
Use when an implementation task has just been completed and the user wants independent verification that the work is actually correct. Dispatches two subagents that perform the SAME verification checks independently, then merges their findings into one deduplicated report with severity and confidence. Triggers when the user says "verify this", "double-check the implementation", "cross-check what was done", "did this actually work", "verify the task", or invokes a slash command for verification. Especially valuable right before commits, PRs, or hand-offs, where over-claiming is most costly.
Executes bash commands
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Hook triggers when Bash tool is used
Hook triggers when Bash tool is used
A Claude Code plugin marketplace for daily-work automation. It ships four plugins:
ado-backlog — turn findings from any input (an Excel/CSV audit, a doc, a code/QA
review, a pasted list of issues) into an Azure DevOps backlog: extract → triage →
classify by your project's process → dry-run → create on approval → write ticket links
back to the source. Each step is its own reusable skill, plus a one-shot orchestrator.github-backlog — the same findings pipeline against GitHub Issues: labels +
milestone classification, a visual dry-run gate, a tracking issue, and write-back.dev-workflows — the daily-work arc: the /daily router plus design
(grill-then-plan), debugging (debug-mantra → post-mortem), review (scrutinize,
dual-verifier), system study (study-design-verify, fit-gap-analysis, naming-audit,
drive-to-legacy, ticket-trace), and communication (management-talk, invoice-generator,
problem-description) skills. Also installable on Google Antigravity — see
dev-workflows on Antigravity.react-workflows — opt-in, frontend structure conventions for React/TSX work
(react-structure): per-component file separation (UI .tsx / hook .ts / type.ts /
optional Redux slice), a TypeScript + Redux Toolkit + MUI + DataGridPremium stack, and a
planning flowchart before code. Install it only on React projects — see
plugins/react-workflows/README.md for why it's kept
separate from the always-on plugins above.Start here: PLAYBOOK.md — the one-page map of when to reach for what.
The only command to memorize is /daily.
Prerequisites: Claude Code, Azure CLI (az login),
.NET 10 SDK, Python 3 + openpyxl (pip install openpyxl).
# in Claude Code:
/plugin marketplace add ThodsaphonSonthiphin/workflow-daily-work
/plugin install ado-backlog@workflow-daily-work
/plugin install github-backlog@workflow-daily-work
/plugin install dev-workflows@workflow-daily-work
# then sign in to Azure DevOps and check your setup:
az login
/ado-backlog:setup-check
react-workflows is opt-in — only install it on React/TSX projects (see above):
/plugin install react-workflows@workflow-daily-work
CLI equivalents:
claude plugin marketplace add ThodsaphonSonthiphin/workflow-daily-workandclaude plugin install ado-backlog@workflow-daily-work. For team-wide install, add--scope project(writes to.claude/settings.json). Installing mid-session? run/reload-pluginsto activate without restarting.
The dev-workflows skills also run on Google Antigravity (IDE or CLI). Antigravity
does not read the Claude Code marketplace and resolves bundled-file paths relative to each
skill directory (no ${CLAUDE_PLUGIN_ROOT} expansion), so install via the bundled script:
it stages the skills into Antigravity's skills directory and rewrites those paths to
absolute. The source tree stays Claude-native, so the marketplace install above is
unaffected.
Prerequisites: git, Python 3.9+, and Antigravity installed.
git clone https://github.com/ThodsaphonSonthiphin/workflow-daily-work.git
cd workflow-daily-work/plugins/dev-workflows/.antigravity
python install-antigravity.py # default: ~/.gemini/config/skills (IDE global)
# --scope cli -> ~/.gemini/antigravity-cli/skills
# --scope project --project <repo> -> <repo>/.agents/skills
Then reload Antigravity so it rediscovers the skills. A clean run ends with
rewrote N ${CLAUDE_PLUGIN_ROOT} reference(s) and no warning (the exact count isn't
load-bearing). Verify the staged script runs:
python "$HOME/.gemini/config/skills/.dev-workflows-shared/scripts/daily-state.py" --help
dev-workflows ships an Antigravity installer; ado-backlog / github-backlog
are Claude-Code-only for now.grill-then-plan hands off to superpowers:writing-plans, so it also needs a
superpowers skills port installed on Antigravity.plugins/dev-workflows/.antigravity/INSTALL.md./ado-backlog:run "C:\path\to\your-findings.xlsx"
Answer the prompts (column mapping, which severities, who to assign to), approve the dry-run, and it creates the work items and writes the ticket links back into your file. Nothing is created in Azure DevOps until you approve the dry-run.
See plugins/ado-backlog/README.md for the full toolkit and
plugins/ado-backlog/QUICKSTART.md for the one-page cheat sheet.
npx claudepluginhub thodsaphonsonthiphin/workflow-daily-work --plugin dev-workflowsTurn findings from any input into an Azure DevOps backlog: extract -> triage -> classify (by your project's process) -> create (dry-run gated) -> write ticket links back. Composable: each step is its own skill, plus a one-shot orchestrator.
Evidence-gated AI coding workflow: scan → analyze → plan → TDD → execute → fix → verify → review, powered by Codebase Memory MCP >= 0.9.0 with optional Serena LSP intelligence. Includes blast-radius planning, test/cycle gates, independent review, and Windows Git Bash hook auto-resolution.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.