SkillsAdd

dpolivaev/spec-loop

spec-loop-prepare-execution-approval

Mandatory only on the task-file path of `spec-loop-plan-task`. Use when an active task file already exists and the next user-facing action would otherwise present task-file work for evaluation, feedback, review, or execution approval.

First seen Jun 28, 2026

Installation

$ npx skills add https://github.com/dpolivaev/spec-loop
View on skills.sh ↗ GitHub repository ↗
Feature your product here Skill page unit · reach builders installing agent skills View pricing →

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

find-skills Same topic
vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…

18.6K installs
agent-browser Same topic
vercel-labs/agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…

11.9K installs
vercel-react-best-practices Same topic
vercel-labs/agent-skills

React and Next.js performance optimization guidelines from Vercel Engineering. This skill shoul…

3.7K installs
web-design-guidelines Same topic
vercel-labs/agent-skills

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…

4.7K installs
microsoft-foundry Same topic
microsoft/azure-skills

Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …

1.7K installs
azure-prepare Same topic
microsoft/azure-skills

Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…

1.5K installs

Also in this package

Other skills from dpolivaev/spec-loop · top by installs.

npx skills add https://github.com/dpolivaev/spec-loop
spec-loop-plan-task 1 spec-loop-write-glossary 1 spec-loop-implementation-flow 1 spec-loop-assess-pull-request 53 spec-loop-setup-doc-rendering 1 spec-loop-clarify-task 1 spec-loop-compact-task-file 1 spec-loop-write-adr 1 spec-loop-prepare-implementation-approval 45 spec-loop-plan-work-breakdown 1

Browse all from dpolivaev/spec-loop

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 34
License LICENSE.md
Default branch main
Open issues 0
Status Active

History

  1. First seen on skills.sh
  2. First recorded snapshot · 11 installs

SKILL.md

This skill is mandatory only on the task-file path of the spec-loop-plan-task workflow. It is not used for chat-only planning path work kept in chat.

Before work: read [spec-loop-plan-task/SKILL.md](../spec-loop-plan-task/SKILL.md), follow all files it requires, and apply the full spec-loop-plan-task bundle as shared convention guidance. Then read [execution-approval-guidance.md](execution-approval-guidance.md).

Update the same active task file for user-facing review readiness. Do not create a second task artifact or a new pre-execution task status.

Use [execution-approval-guidance.md](execution-approval-guidance.md) as the authoritative source for readiness checks, diagram-first preparation, duplication removal, user-facing review gating, and approval-seeking output.

Follow [execution-approval-guidance.md](execution-approval-guidance.md) for the allowed user-facing outcomes and response rules.

If readiness checks find directly fixable task defects, update the active task in place and re-run the readiness checks before producing user-facing output, except for structural decomposition changes handled specially by [execution-approval-guidance.md](execution-approval-guidance.md).

If readiness checks find issues that can be resolved from existing evidence, update the active task in place and re-run the readiness checks before producing user-facing output.

If readiness checks show that task-file compaction is needed, use [spec-loop-compact-task-file/SKILL.md](../spec-loop-compact-task-file/SKILL.md) and then resume this skill.

If any important open decision remains and it is user-preference-sensitive, needed to choose the next path, or could materially change scope, constraints, design, or test specification, do not end with a blocker list. Invoke [spec-loop-clarify-task/SKILL.md](../spec-loop-clarify-task/SKILL.md) in the same turn, then resume this skill after clarification before seeking execution approval.

After task-file execution approval:

  • implementation work is governed by

[spec-loop-implementation-flow/SKILL.md](../spec-loop-implementation-flow/SKILL.md);

  • investigation work stays under the spec-loop-plan-task task-file

path: perform only the approved investigation, record final output in Findings, satisfy any Test specification, and move the task or subtask to review.

If no active task file exists, if the current increment is unclear, or if chat-only planning is in use, do not use this skill. Continue task work under the spec-loop-plan-task bundle instead.