buiducnhat/agent-skills
9 skills3k installs468 starsGitHub
Install
npx skills add https://github.com/buiducnhat/agent-skillsSkills in this repo
1Brainstormbrainstorm is a Claude skill from buiducnhat/agent-skills (MIT license) for collaborative discovery and design framing on ambiguous or high-risk work. The skill runs a structured dialogue to clarify requirements and constraints, explore alternatives with trade-offs, and produce a concrete validated design brief or handoff to planning. Developers reach for brainstorm when requirements are unclear, multiple approaches are possible, or an idea needs validation before implementation. The workflow moves from gathering context through alternative exploration to a reviewable design output.543installs2Execute Planexecute-plan is a buiducnhat agent-skills workflow for running an already-approved ExecPlan or implementation checklist in batch or interactive mode. Each phase records implemented work, verification commands, and notes, then aggregates results into an execution report with a verification matrix covering lint, type check, tests, build, and manual QA status. The skill logs approved deviations, blockers with resolutions, and follow-up tasks when work completes with caveats. Developers reach for execute-plan after planning is signed off and they want disciplined, gate-checked delivery instead of ad-hoc task jumping. Output follows a structured Execution Report template with per-phase pass or warning markers.487installs3Write Planwrite-plan is an agent skill from buiducnhat/agent-skills that produces structured implementation plans before coding begins. The skill breaks a feature or refactor into milestones, risks, dependencies, file-level tasks, sequencing, and acceptance criteria so both humans and coding agents share one execution blueprint. Developers reach for write-plan when a ticket is underspecified, a large change spans many files, or an agent session needs an explicit plan to avoid scope drift. Output reads like a technical design brief with actionable steps rather than vague to-do bullets, making it useful for greenfield features, migrations, and multi-PR refactors.451installs4Docsdocs is a workflow skill from buiducnhat's CoBrew plugin that creates or refreshes project documentation inside docs/. It scans README, config files, source directories, and recent git history, then either initializes four topic folders—architecture, codebase, code-standard, and project-pdr—or surgically updates existing files without full rewrites. Every run regenerates docs/SUMMARY.md with an Agent Context Guide and syncs README links. The skill enforces content-named detail files, bans generic overview.md names, and validates that listed files exist on disk. Developers invoke docs when onboarding agents to a repo, after major refactors, or when docs/SUMMARY.md is missing or stale relative to the current implementation.425installs5Quick Implementquick-implement is a buiducnhat agent-skills workflow for rapidly implementing small, well-defined code changes. Before coding, the skill enforces a scope gate: explicit expected behavior, no major architecture ambiguity, and a small change surface—typically five or fewer files with no broad cross-module refactors. Developers reach for quick-implement when a task has clear acceptance criteria, low risk, and can be completed safely without a formal planning phase. The skill favors working code, tight scope, and fast iteration over heavy design documents. Tasks that fail the scope gate should escalate to fuller planning workflows instead of proceeding under quick-implement.378installs6Askask is a MIT-licensed Claude Code skill for structured clarification and requirements gathering through focused dialogue. The skill loads only task-relevant project context—prioritizing docs/SUMMARY.md, Code Standard docs, and detail files—then asks targeted questions until scope, conventions, and user intent are explicit. Developers invoke ask when a ticket lacks acceptance criteria, conflicting docs appear in the repo, or an agent might otherwise guess implementation details. The workflow deliberately blocks planning and coding: Step 1 gathers project context, then the agent questions the user until inputs are sufficient. argument-hint supports passing an initial question. Reach for ask at the start of ambiguous refactors, integrations, or feature requests where wrong assumptions would waste diffs.240installs7FixGeneral-purpose agent fix skill from buiducnhat for debugging and repairing code defects, guiding agents through reproduction, root-cause analysis, targeted patches, and verification across typical application codebases.221installs8ReviewAgent-oriented review skill from buiducnhat/agent-skills that inspects code changes on branches, local diffs, or pull requests and returns structured quality feedback to catch bugs, regressions, and maintainability issues before merge.221installs9VisualizeThis skill creates source-adjacent HTML visualizations from repository documentation, markdown files, and standardized plan folders. A user invokes it to turn docs into readable maps, timelines, process flows, risk blocks, and Mermaid diagrams. It writes visualize.html next to the source, copies a fixed theme CSS, and stays factual by labeling assumptions rather than inventing facts. It is not for brand sites, product prototypes, or slide decks.34installs