desplega

Plugin desplega from marketplace desplega-ai-toolbox in desplega-ai/ai-toolbox. Commands read from the repo's manifest — 12 days ago.

Skills (25)

• ask-user

  Conventions for asking the user questions during a workflow via the AskUserQuestion tool. Other skills reference this to keep prompts consistent and structured.

• babysit-pr

  Keep a GitHub PR moving until it is clean on its head commit. Each round fixes CI failures, handles review findings, rebases when needed, re-triggers the reviewers, and then waits in the background for the next event. Use when the user says "babysit the PR", "watch the PR until it's approved", "keep

• brainstorming

  Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.

• code-reviewing

  Two-axis code review of a diff — Standards (is the code well built?) and Spec (does it actually solve the stated problem?) — run as parallel sub-agents and reported separately, never merged. Use when reviewing implementation output (a phase, a wave, a branch, a PR), when the user says "review the co

• comms

  Re-express something so it lands — re-explain your last reply in plain casual language, show the current topic visually (diagram, code-shape sketch, HTML artifact), do both at once, or rewrite artifact text into unambiguous ASD-STE100 English. Use when the user runs /desplega:comms, types /bro, says

• delegate-work

  Executor routing policy for ALL delegated work — pick the right model for every sub-agent and the right Codex variant for every implementation slice. Use whenever you are about to spawn a sub-agent/Task (research, review, QA, UI, search), whenever a desplega skill (implement-plan, v-implement, run-p

• design-docs

  Create and maintain living per-system design docs at thoughts/*/design-docs/<system-slug>.md — Purpose, Glossary, numbered testable Invariants (normative for the code-reviewing Spec axis), Boundaries & Non-goals, Interfaces, Decision log, Amendment log. Use when the user says "create a design doc",

• engineering-standards

  Code-shape policy for ALL code that gets written or reviewed — the senior-engineer bar for minimal complexity. Use whenever you are about to write code, design a module or abstraction, draft a plan phase that shapes code, or review a diff; also when the user asks "is this over-engineered", "can this

• implementing

  Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.

• improve-agents-md

  Improve (or bootstrap) an AGENTS.md / CLAUDE.md file using `<important if>` conditional blocks so the agent actually attends to the right guidance at the right time. Use this skill whenever the user mentions AGENTS.md, CLAUDE.md, agent instructions, project rules for AI, "my claude config", onboardi

• learning

  Compounding knowledge across projects and teams. Captures, searches, and promotes institutional learnings via tiered backends (local/qmd/agent-fs).

• one-shot

  Small-scope plan+implement in one session. Assess the prompt, optionally one bundled round of questions, maintain a lightweight yolo plan while implementing, verify, quick code review, commit. Use when the user invokes /one-shot, or asks to "just build/fix/add" something small without the full creat

• phase-running

  Execute individual plan phases as background sub-agents for context-efficient implementation.

• planning

  Implementation planning skill. Creates detailed technical plans through interactive research and iteration.

• qa

  Functional validation skill. Captures test evidence (screenshots, recordings, links) and produces QA reports in thoughts/*/qa/.

• questioning

  One-shot question answering using the research process. Answers inline without generating documents, then offers handoff to brainstorm or research.

• researching

  Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.

• reviewing

  Structured critique of research, plan, and brainstorm documents for completeness, gaps, and quality.

• script-builder

  Generate durable, re-runnable scripts from session intent — validation scripts (PASS/FAIL contract) AND gather/bulk scripts (many API/tool calls in code, one derived summary out). Supports TypeScript, Python, Bash with auto-detection, enforces context-optimal output, and auto-documents scripts in CL

• step-running

  Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /r

• tackle-gh-comments

  Work through every review comment on a GitHub PR — fetch the threads, verify each claim against the code, fix what is real, then reply and mark each thread resolved before pushing. Use when the user says "tackle the PR comments", "address the review", "handle the bot comments", "check the comments o

• tdd-planning

  TDD-focused implementation planning. Creates plans with strict Red-Green-Commit/Rollback cycles for each step.

• v-implementing

  Parallel DAG-plan implementation skill. Reads a v-planning plan directory (root.md + step-<n>.md files), topologically schedules ready steps, and fans them out as parallel sub-agents. Use whenever the user invokes /v-implement, points at a plan directory produced by /v-plan, or asks to "run the para

• v-planning

  Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-pla

• verifying

  Post-implementation plan verification. Cross-references plans against actual changes for completeness and accuracy.

Slash commands (22)

• /desplega:babysit-pr

  Keep a GitHub PR moving until it is clean on its head commit

• /desplega:brainstorm

  Interactive exploration of ideas through Socratic Q&A

• /desplega:bu-auto-instrument
• /desplega:commit
• /desplega:comms

  Re-express the last reply or current topic so it lands (simpler, visual, joint, or precise STE rewrite)

• /desplega:continue-handoff

  Continue work from a saved handoff file

• /desplega:create-plan

  Create detailed implementation plans through interactive research and iteration

• /desplega:create-tdd-plan

  Create TDD implementation plans with strict Red-Green-Commit/Rollback cycles

• /desplega:implement-plan

  Implement technical plans from a predefined plan file

• /desplega:improve-agents-md

  Improve or bootstrap an AGENTS.md / CLAUDE.md file using conditional `<important if>` blocks

• /desplega:learning

  Capture, search, and promote institutional learnings across projects

• /desplega:one-shot

  Plan and implement a small task in one session with a lightweight yolo plan

• /desplega:qa

  Functional validation with test evidence and QA reports

• /desplega:question

  One-shot question answering using the research process

• /desplega:research

  Document codebase as-is with thoughts directory for historical context

• /desplega:review

  Structured critique of research, plan, and brainstorm documents

• /desplega:run-phase

  Execute a single plan phase as a background sub-agent

• /desplega:script-builder

  Generate durable validation scripts from testing intent

• /desplega:tackle-gh-comments

  Work through every review comment and finding on a GitHub PR

• /desplega:v-implement

  Implement a DAG plan in parallel — topologically schedules ready steps and fans them out as sub-agents

• /desplega:v-plan

  Create a DAG-structured implementation plan for parallel execution

• /desplega:verify-plan

  Post-implementation plan verification and audit

Subagents (6)

• codebase-analyzer

  Analyzes codebase implementation details. Call the codebase-analyzer agent when you need to find detailed information about specific components. As always, the more detailed your request prompt, the better! :)

• codebase-locator

  Locates files, directories, and components relevant to a feature or task. Call `codebase-locator` with human language prompt describing what you're looking for. Basically a "Super Grep/Glob/LS tool" — Use it if you find yourself desiring to use one of these tools more than once.

• codebase-pattern-finder

  codebase-pattern-finder is a useful subagent_type for finding similar implementations, usage examples, or existing patterns that can be modeled after. It will give you concrete code examples based on what you're looking for! It's sorta like codebase-locator, but it will not only tell you the locatio

• context-handoff

  Use this agent when you need to preserve context before running out of context window space, when you want to checkpoint progress on a complex task, when transitioning between sessions, or when explicitly asked to save/store current progress. Examples:\n\n<example>\nContext: The assistant has been w

• phase-running

  Executes a single plan phase as an autonomous background sub-agent. Invokes the desplega:phase-running skill which contains the full execution logic and registers plan checkbox tracking hooks.

• web-search-researcher

  Do you find yourself desiring information that you don't quite feel well-trained (confident) on? Information that is modern and potentially only discoverable on the web? Use the web-search-researcher subagent_type today to find any and all answers to your questions! It will research deeply to figure

Hooks (3)

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/hooks/validate-thoughts.py

• UserPromptSubmit

  ${CLAUDE_PLUGIN_ROOT}/hooks/context_warn.py

• Stop

  ${CLAUDE_PLUGIN_ROOT}/hooks/stop_confirm.py

Similar plugins