Loading...
Loading...
Found 4,920 Skills
Break down large tasks into smaller, actionable items. Use when planning sprints, estimating work, or creating implementation plans. Covers task breakdown strategies.
Edit opencode.json, AGENTS.md, and config files. Use proactively for provider setup, permission changes, model config, formatter rules, or environment variables. Examples: - user: "Add Anthropic as a provider" → edit opencode.json providers, add API key baseEnv var, verify with opencode run test - user: "Restrict this agent's permissions" → add permission block to agent config, set deny/allow for tools/fileAccess - user: "Set GPT-5 as default model" → edit global or agent-level model preference, verify model name format - user: "Disable gofmt formatter" → edit formatters section, set languages.gofmt.enabled = false
Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and brevity matter.
Convert vague or high-level requests into a concrete engineering plan with goals, constraints, steps, success criteria, and validation. Stop and wait for human confirmation.
Combined command for OpenHarmony XTS compilation and execution. Complete the compilation and execution of XTS test projects in one stop. Use this Skill when you need to execute the full XTS test process: (1) Compile the XTS test project to generate HAP files, (2) Run the XTS test and display the results. Supports passing --package and --api parameters to the execution phase.
Create a Product Requirements Document (PRD) for your MVP. Use when the user wants to define product requirements, create a PRD, or says "help me write requirements", "create PRD", or "define my product".
[Fix & Debug] Investigate and explain how existing features or logic work. READ-ONLY exploration with no code changes.
[Tooling & Meta] Compress conversation context to optimize tokens
Clarify requirements before implementing by asking the minimum must-have questions. Use when a request is underspecified or ambiguous, when the user asks to “ask clarifying questions”, or when multiple plausible interpretations exist and you risk doing the wrong work.
Review and fix PR review bot findings on current PR, loop until resolved. Fetches unanswered bot comments, evaluates each finding, fixes real bugs, dismisses false positives, and replies to every comment with the outcome.
Dynamic orchestration engine that plans multi-step agent work as DAGs with Mermaid visualization.
Capture explored work as a backlog item for future implementation. Use when you've explored an enhancement, alternative approach, or feature but decided to defer it. Creates comprehensive plan files in backlog/ directory with enough context for a future session to execute efficiently.