All authors
Claude Skills by desplega-ai
github.com/desplega-ai69 skills0 installs33 views
- VerifyingPost-implementation plan verification. Cross-references plans against actual changes for completeness and accuracy.Votes: 0GitHub stars: 36
- Brain ExpertPersonal knowledge management expert for the brain CLI. Use when users want to capture notes, search their knowledge base, or manage their second brain.Votes: 0GitHub stars: 36
- File ReviewFile review tool \u2014 launch GUI, process comments, or install. Use when user mentions file-review, reviewing files, leaving comments, or processing review comments.Votes: 0GitHub stars: 36
- InstallInstall the file-review tool. Use when user needs to install file-review on a new machine or asks how to set it up.Votes: 0GitHub stars: 36
- Process ReviewProcess review comments in a file after user finishes reviewing in file-review GUI. Extracts HTML comment markers, guides Claude through addressing each comment interactively, and removes resolved markers.Votes: 0GitHub stars: 36
- Oapi ExpertOpenAPI CLI expert for @desplega.ai/oapi. Use when users want to register OpenAPI specs, execute API requests, manage auth profiles, explore API endpoints, or work with REST APIs from the terminal.Votes: 0GitHub stars: 36
- FeedbackGive Radically Candid feedback to the user — kind, clear, specific, and sincere — based on Kim Scott's framework (Care Personally × Challenge Directly). Use this whenever the user asks for your opinion, review, critique, or pushback on a plan, idea, code, writing, design, or decision; when the user invites honest disagreement ("tell me what you really think", "be honest", "poke holes in this", "am I missing something"); when something the user just said or did looks wrong and silence would be...Votes: 0GitHub stars: 36
- Remarkable ExpertreMarkable tablet expert. Use when users want to list, download, or upload files to their reMarkable tablet.Votes: 0GitHub stars: 36
- Swarm ExpertMulti-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.Votes: 0GitHub stars: 36
- Wts ExpertGit worktree management expert for @desplega.ai/wts. Use when the user asks about git worktrees, wts commands, worktree workflows, or wants help managing multiple branches simultaneously.Votes: 0GitHub stars: 36
- BrainstormsTaras is considering adding a `/learning` skill to the cc-plugin/base plugin. The core idea is a **compounding learning mechanism** that works cross-project and across team members (agents).Votes: 0GitHub stars: 36
- BrainstormsTaras wants a new skill in `cc-plugin/base/` (working name: `script-builder`) whose sole purpose is to help users and coding agents generate **one-off / custom / special scripts** that are later used by coding agents (Claude or others) to autonomously **test/validate** things during:Votes: 0GitHub stars: 36
- PlansCreate a single unified `file-review` skill (`SKILL.md`) that acts as an intelligent router for all file-review functionality. The existing commands in `commands/` remain as backward-compatible shortcuts, but the skill is the canonical entry point that understands natural language intents.Votes: 0GitHub stars: 36
- PlansAdd a QA (functional validation) skill to `cc-plugin/base/` that captures test evidence (screenshots, recordings, links) and produces QA reports in `thoughts/*/qa/`. The skill works standalone and integrates into the existing skill chain via optional per-phase QA specs in plans and handoff additions to verify/review.Votes: 0GitHub stars: 36
- PlansAdd a new one-shot question-answering skill to `cc-plugin/base/` that uses the research process to answer questions inline (no document by default), then offers to continue with more questions, save the answer, start a brainstorm, or start research.Votes: 0GitHub stars: 36
- PlansImplement a `/learning` skill for cc-plugin/base that captures, stores, searches, and promotes institutional knowledge across projects and sessions. The skill uses a tiered backend model (local → qmd → agent-fs) where each tier adds reach without replacing the previous one.Votes: 0GitHub stars: 36
- PlansAdd a new `script-builder` skill to `cc-plugin/base/skills/` that converts testing/validation intent into durable, re-runnable scripts committed to the target project's `scripts/` directory. The skill is human-first (direct `/script-builder` use) and sub-skill-capable (callable from `planning`, `qa`, `verifying`), supports TypeScript/Python/Bash with auto-detection, enforces a context-optimal PASS/FAIL + `/tmp` log output convention, scans for existing scripts to dedup, and auto-edits target `CLVotes: 0GitHub stars: 36
- ResearchHow should a QA skill be designed for `cc-plugin/base/` that: 1. Fits into the existing skill chain (brainstorm → research → plan → implement → verify → **qa**) 2. Creates files in `thoughts/.../qa/YYYY-MM-DD-<name>.md` 3. Supports a clear template with references (images, links, videos) 4. Works standalone but also integrates naturally after planning/verificationVotes: 0GitHub stars: 36
- ResearchHow should we add a new `/desplega:question` skill to `cc-plugin/base/` that provides one-shot answers using the research process, without generating a document, and offers follow-up handoff to brainstorm or research?Votes: 0GitHub stars: 36