Skip to content
Skills Library
Programming · Automation

executing-plans

/executing-plans

Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.

Repository
ai-settings ↗
Licence
MIT
Last repository change
14.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 14.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.

Original author description

Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.

How it works

  1. Process
  2. Stop and Ask
Original SKILL.md headings · 32 lines, 161 words
SKILL.md preview
---
name: executing-plans
version: 6.2.0
category: workflow
description: Use when implementing an approved written plan with dependent tasks in the current session. Do NOT use when the plan is missing, unapproved, or naturally parallel.
---

# Executing Plans

Execute the plan in the current agent by default.

## Process

1. Read the plan and applicable project instructions.
2. Confirm the workspace and existing user changes are safe.
3. Flag only gaps that block or materially change the outcome.
4. Track tasks by useful deliverable, not every command.
5. For each task, implement the scoped outcome and run its risk-appropriate
   verification.
6. Update the plan or canonical backlog when reality changes.
7. Review the complete diff once at the end.

Read `../using-superpowers/references/risk-policy.md`.

Do not switch to subagent-driven development merely because subagents exist.
Delegate only when the user requests it or tasks are independent enough to
benefit from parallel work.

## Stop and Ask

Stop when authority is missing, a destructive action is newly required, a
critical requirement is ambiguous, or repeated evidence invalidates the plan.
Ordinary implementation details are resolved from the codebase.

When implementation is verified, use
`superpowers:finishing-a-development-branch` only if an integration decision is
actually needed.
Files in this package (2)
  • CHANGELOG.md 1 KB
  • SKILL.md 1 KB

Versions

RepositoryScoreLicence
This page · tsergeytovarov/ai-settings90MIT
nikospavlopoulos/devops-mutant-powers100MIT
arklab/ark.tools100MIT
arklab/ark.tools100MIT
ongtungduong/legion100MIT
osmontero/opencode-skills100MIT
GanyuanRan/Aegis100MIT
seaworld008/commonly-used-high-value-skills100MIT
FrancoStino/opencode-skills-collection100MIT

Database snapshot: 13.11.2026 · package version 6916bd159faa (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100assemble
    Use when executing implementation plans with independent tasks in the current session
  • 100subagent-driven-development
    Use when executing implementation plans with independent tasks in the current session
  • 90sr-executing-plans
    Use when you have a written implementation plan to execute in a separate session with review checkpoints

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.