kyaulabs/prism/executing-plans
- community
Checking that the SKILL.md file is still in the repository.
Use to carry out an authorized multi-task plan in tested slices, committing verified logical changes and continuing without routine approval pauses.
Install
npx vskill@latest install kyaulabs/prism/executing-plansSKILL.md
Executing Plans
Execute the requested work, not a parallel workflow engine.
- Read the plan and inspect current repository state. Resume from the first
incomplete slice; do not assume an earlier edit or check succeeded.
- Use
tddfor each development slice: one failing behavior test, minimal
implementation, passing verification, then refactor while green.
- Check that the slice meets its acceptance criteria and integrates with its
callers. Adapt file choices and implementation details to evidence. Ask for direction only if requirements, material scope or consequential trade-offs change.
- Run relevant checks using
verification-before-completion. Commit verified
logical changes with conventional-commits; update the existing checklist.
- Continue to the next slice automatically. If progress stalls, explain the
blocker and propose a next step instead of repeating the same failing loop.
- At non-trivial task completion, use
code-review, repair concrete defects and
verify affected behavior. Finish according to user/project publication instructions.
Continuity
Keep a short progress note for long work: completed slices, actual test evidence, current changes, unresolved decisions and the next task. Use Pi's normal session continuity. Honor pause requests after leaving recoverable state; no receipt or attempt counter is needed across resumption.
Gotchas
- Do not run verification twice merely because two skills mention it; reuse fresh
evidence for unchanged code and rerun checks affected by later edits.
- Passing a focused test does not prove the entire plan is done.
- Keep useful specs/plans and preserve unrelated user changes.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingpackages/prism-core/skills/executing-plans/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/kyaulabs/prism/executing-plans)