Execute
Execute the active plan's task groups in order, delegating to software-engineer/platform-engineer/quality-reviewer/technical-writer subagents. Use when asked to execute, run, or build out the current plan or its tasks.
Install
npx skills add aws-samples/sample-kiro-cli-multiagent-development --skill executegit clone --depth 1 https://github.com/aws-samples/sample-kiro-cli-multiagent-development.git /tmp/sample-kiro-cli-multiagent-development
mkdir -p ~/.claude/skills
cp -r /tmp/sample-kiro-cli-multiagent-development/skills/execute ~/.claude/skills/executePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Execute Current Plan Read `.kiro/delivery/current.md` to resolve the active plan slug. Read the plan at `.kiro/delivery/<slug>/plan.md` and the task list at `.kiro/delivery/<slug>/tasks.md`. **Read the plan's depth first.** Take `depth` from the `plan.md` YAML frontmatter; if absent, it is `standard`. Depth determines which gates are mandatory — see the mandatory-gate matrix in `## Plan Depth Levels` of `~/.kiro/steering/delivery-workflow.md`. Enforce gates per that matrix: - `prototype` — research + a runnable check; skip the code-review and documentation gates. The safety floor can still force a security review. - `standard` *(default)* — the full sequence below, unchanged: research → impl → code review → security review → docs. - `production` — run the **design-review gate before construction** (two parts, sequential: `quality-reviewer` in design mode reviews `plan.md` architecture/feasibility/test-strategy/risks, then `security-reviewer` in design mode reviews the Threat Model; both write to `design-review.md`; PASS from both required), then run the standard construction loop **per phase** across `phases/phase-N-*/tasks.md`, and finish with the operational-readiness gate.
Details
- Skill name
execute- Path
skills/execute/SKILL.md- License
- MIT-0
- Repo updated
- 9 September 2026
FAQ
What does the Execute skill do?
Execute the active plan's task groups in order, delegating to software-engineer/platform-engineer/quality-reviewer/technical-writer subagents. Use when asked to execute, run, or build out the current plan or its tasks.
How do I install the Execute skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add aws-samples/sample-kiro-cli-multiagent-development --skill execute. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Execute popular?
It lives in aws-samples/sample-kiro-cli-multiagent-development, which has 43 GitHub stars and 9 forks.
Related skills
Agentcore Patterns
43aws-samples/sample-kiro-cli-multiagent-development
Verified Amazon Bedrock AgentCore patterns for Runtime handlers, Gateway MCP clients with SigV4/IAM auth, Memory session management with Strands, and Bedrock cross-region inference-profile IAM policies. Use when building or debugging AgentCore-based agents.
AWS Technical Docs
43aws-samples/sample-kiro-cli-multiagent-development
AWS technical documentation patterns covering procedures, lists, tables, titles, error messages, and content patterns. Use when writing AWS service documentation, procedures, troubleshooting guides, tutorials, or getting started content.
CLI Execution
43aws-samples/sample-kiro-cli-multiagent-development
CLI execution best practices covering RTK token compression, AWS discover-then-execute patterns, output control, and bash/zsh scripting with logging. Use when running CLI commands, querying AWS resources, writing automation scripts, or working with shell tooling.
Meeting Pyramid Minutes
107Dimon94/skills
将会议录音转文字梳理为金字塔结构的会议纪要。用于处理会议录音、转写文本、汇报记录,产出决策、问题、行动、关键对话的结构化纪要。触发:会议纪要、梳理会议、录音转文字、金字塔结构、汇报总结。
Do Not Repeat Yourself
107Dimon94/skills
Find and reuse the nearest correct mechanism before adding another. Use when a change would add reusable code, policy, or workflow meaning.
I Have Adhd
66aparente/claude-skills
Make responses easy to start, scan, and complete - action first, numbered steps, minimal cognitive load, no repetition or filler. Use for ANY request that would otherwise get a long or multi-part answer: how-to and setup questions, multi-step tasks, comparing options, planning work, debugging walkthroughs, or explaining a system. Also use when the user invokes it directly, says they have ADHD, asks to be brief or to cut the fluff, or shows signs of executive dysfunction, overwhelm, decision paralysis, or task paralysis ("I don't know where to start", "this is too much", "I keep putting this of
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.