Agent Skills

---

name: prp-issue-contract

description: Creates GitHub issues from conversations, findings, or ideas and runs the precondition check before a planning-capable agent starts work. Use when the user asks to "create an issue from this", "turn this into an issue", "check whether issue #42 is agent-ready", "check this issue before automation", "audit this issue contract", "update this issue to make it agent-ready", or invokes /prp-issue-contract.

---

name: prp-loop

description: Runs the detached, resumable PRP pipeline in fresh headless CLI sessions, cycling plan, implementation, PR, review, and corrections with persisted state and safety bounds. Use only when the user explicitly asks to "run the full PRP loop", "run this detached", "continue across context windows", use headless autonomous execution, resume a saved loop, or invokes /prp-loop. Use prp-issue for ordinary end-to-end delivery.

---

name: prp-maintainer-triage

description: Quickly triages a contributor pull request or reported issue against repository policy and lightweight evidence without full review or root-cause analysis. Publishes the disposition to GitHub, and on a contributor pull request that links no issue it may open a tracking issue and close the pull request. Use when the user asks to "triage this contributor PR", "sanity-check this PR", "triage this issue", "reproduce this reported issue", "check whether this bug still exists", or invokes /prp-maintainer-triage.

---

name: prp-meta-skill

description: Authors, refactors, and consolidates Agent Skills PRP-style. Use when the user wants to "create a skill", "write a new skill", "trim a SKILL.md", "split a skill into references", "consolidate workflow skills", "replace duplicated skill logic with composition", redesign a skill workflow, or invokes /prp-meta-skill.

---

name: prp-orchestrate

description: Turns the current session into the operator's SDLC proxy for parallel PRP workstreams in isolated worktrees. It owns the combined outcome, steers autonomous deliveries, holds human and merge gates, verifies proof, and sequences merges. Use when the user wants to "spawn N agents in separate worktrees", "run prp-issue on these issues in parallel", "orchestrate these features", "act as my orchestrator", "coordinate agents through the PRP pipeline", "ship these issues in parallel", or invokes /prp-orchestrate.

---

name: prp-plan

description: Creates an implementation-ready plan for a feature, bug fix, refactor, or chore from a PRD, issue, document, or description using codebase evidence, first-principles reasoning, and conditional root-cause analysis, research, or spikes. Publishes issue-derived plans back to their source issue. Use when the user asks to "plan this feature", "plan this bug fix", "plan issue X", "create an implementation plan", "turn this PRD into a plan", investigate how a change should be built, link related plans, or invokes /prp-plan.

---

name: prp-pr

description: Creates and opens GitHub pull requests. Always use when creating a PR on GitHub, when the user explicitly asks to create or open a PR, when another PRP workflow reaches its PR-creation step, or when the user invokes /prp-pr.

---

name: prp-prd

description: Interactive PRD generator - problem-first, hypothesis-driven product spec. Use when the user wants to create a PRD, write a product or feature spec, scope a new product, or invokes /prp-prd.

---

name: prp-prd-update

description: Maintains PRD implementation-phase status and artifact links. Always use when a PRP workflow records a planned, implemented, or merged phase in its source PRD, when the user asks to update PRD progress, or when the user invokes /prp-prd-update.

---

name: prp-research-team

description: Design a dynamic research team and plan using agent teams -- analyzes question, composes team, creates executable research plan. Use when the user wants to plan multi-agent research on a question or topic, or invokes /prp-research-team.

---

name: prp-review

description: Reviews GitHub pull requests through specialist review agents, runs repository validation, verifies corrections, aggregates findings, and posts the result. Scales reviewers to risk by default (code review alone for small or mechanical changes; code, seam, and simplification review for contracts, state, and security); the operator can add scopes or explicitly request only selected scopes. Use when the operator asks to review a PR, re-review fixes, check whether a PR is ready to merge, run review agents, or invokes /prp-review.

---

name: prp-spike

description: Prove or disprove an idea by building the smallest throwaway artifact that could falsify it, in an isolated worktree, ending in a PROVEN / DISPROVEN / CONDITIONAL verdict backed by evidence - never a PR. Use when the user wants to "spike this", "build a proof of concept", "POC this", "prototype it to find out", asks "is this possible", "is this feasible", "does this fit our stack", or "would it be worth changing X to allow Y" and wants it settled by building rather than by analysis, wants to compare approaches on evidence before picking one, or invokes /prp-spike.

---

name: prp-technical-writing

description: Writes and edits developer documentation that is easy to act on and hard to misread. Use when writing or reviewing a README, RFC, tutorial, how-to guide, reference document, or technical explanation, when the operator says "write the docs", "improve this README", "edit this RFC", or invokes /prp-technical-writing.

---

name: prp-worklist

description: Render the open work of a repository as something worth looking at, so the maintainer can see what to take next. Deliberate invocation only — /prp-worklist.

---

name: deepcode-self-refer

description: Answers questions about Deep Code CLI itself — including features, configuration options, slash commands, Skills, MCP integration, permissions, notifications, session persistence, and troubleshooting. Use this when users ask how to configure or use Deep Code, how to set up an MCP server, configure notifications (such as Slack/Feishu), manage permissions, view available skills, understand slash commands, configure thinking mode, etc.

---

name: image-generator

description: Generate or edit images from text and local files, image URLs, or data URLs through image API. Use when the user asks to create an image, generate from one or more reference images, combine styles or elements across references, or edit a marked region while blending the result into the original scene.

---

name: skill-digester

description: Reviews and improves another DeepCode skill's SKILL.md description field, and guides Agent Skill installation into user or project .agents/skills roots. Use when the user asks to digest a skill, install an Agent Skill, install a skill to user/project scope, or says "消化技能" or "安装 agent skill".

---

name: skill-writer

description: Guide users through creating, updating, debugging, and validating Agent Skills for AI agents. Use when the user wants to create, write, author, design, troubleshoot, validate, or improve a Skill, or needs help with SKILL.md, frontmatter, or skill structure.

---

name: video-generator

description: 使用AI大模型根据文字、首尾帧图片或图片/视频/音频参考素材生成带对白和环境音的视频。适用于文生视频、图生视频、首尾帧过渡和多模态参考视频生成，通过 Deep Code Plus 试算积分、确认后上传素材并生成视频。

---

name: justhireme-disabled

description: Deprecated placeholder. Do not use as project guidance.

---

name: architecture-workflow

description: Recommends which /arckit:* commands to run, and in what order, for a new or in-flight architecture project, from a short triage of sector, project type, current stage and timeline. Backs /arckit:start. Not needed when the user has already named the command they want, or is asking about the content of an artefact rather than the sequence.

---

name: arckit-build

description: Bulk-builds a project's ArcKit artefacts in parallel from a YAML recipe: computes the artefact dependency DAG, dispatches one subagent per target per wave, validates each output, commits the wave and persists progress to .arckit/state.json so a build can resume. Manual only: run /arckit:arckit-build with --plan, --resume, --target, --refresh or --recipe. Not needed for a single artefact; run that /arckit:* command directly.

---

name: Cloud Security & Compliance

description: Answers a G-Cloud supplier's questions about security certifications and compliance evidence: which certificates each G-Cloud 15 lot requires (Cyber Essentials Plus and ISO 9001/20000-1/27001 for Lots 1a/1b, Cyber Essentials for 2a, 2b and 3), ISO 27001, SOC 2, CSA STAR, PCI DSS, ISO 28000, DSPT, the Carbon Reduction Plan, the NCSC 14 cloud security principles, post-quantum cryptography, the Software Security Code of Practice, UK GDPR, BPSS, SC and DV clearances, and what evidence a submission needs. Not needed when the request is for a security evidence document or an SDD security section; /arckit-uk-gcloud:security and the sdd-lot commands produce those.

---

name: Cloud Security & Compliance

description: Answers a G-Cloud supplier's questions about security certifications and compliance evidence: which certificates each G-Cloud 15 lot requires (Cyber Essentials Plus and ISO 9001/20000-1/27001 for Lots 1a/1b, Cyber Essentials for 2a, 2b and 3), ISO 27001, SOC 2, CSA STAR, PCI DSS, ISO 28000, DSPT, the Carbon Reduction Plan, the NCSC 14 cloud security principles, post-quantum cryptography, the Software Security Code of Practice, UK GDPR, BPSS, SC and DV clearances, and what evidence a submission needs. Not needed when the request is for a security evidence document or an SDD security section; /arckit-uk-gcloud:security and the sdd-lot commands produce those.