examples/reference-agent/skills/soleri-writing-plans/SKILL.md
Use when the user says "create a plan", "break this down", or "plan the implementation". Creates structured implementation plans when requirements are already known. For exploration, use brainstorming.
npx skillsauth add adrozdenko/soleri soleri-writing-plansInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Write implementation plans assuming the engineer has zero codebase context. Document everything: which files to touch, code, testing, expected output. Bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Save plans to: docs/plans/YYYY-MM-DD-<feature-name>.md
salvador_core op:memory_search
params: { query: "<plan topic>", crossProject: true }
salvador_core op:search_intelligent
params: { query: "<feature being planned>" }
salvador_core op:brain_strengths
salvador_core op:vault_domains
salvador_core op:vault_tags
If vault lacks guidance: libraries, reference implementations, API docs, known pitfalls.
Incorporate vault insights and web findings. Reference specific entries.
salvador_core op:create_plan
params: {
objective: "<one-sentence goal>",
scope: { included: [...], excluded: [...] },
steps: [{ title: "Step 1", description: "details" }, ...]
}
salvador_core op:plan_grade params: { planId: "<id>" }
salvador_core op:plan_auto_improve params: { planId: "<id>" }
salvador_core op:plan_meets_grade params: { planId: "<id>", targetGrade: "A" }
Iterate with: op:plan_iterate params: { planId: "<id>", feedback: "<improvement>" }
After approval: salvador_core op:plan_split params: { planId: "<id>" }
Each step is one action (2-5 minutes): write failing test, run it, implement, run tests, commit.
# [Feature] Implementation Plan
> **For Claude:** REQUIRED SUB-SKILL: Use executing-plans to implement this plan task-by-task.
**Goal:** [One sentence]
**Architecture:** [2-3 sentences]
**Tech Stack:** [Key technologies]
salvador_core op:approve_plan params: { planId: "<id>" }
Offer execution choice: subagent-driven (this session) or parallel session with executing-plans.
| Op | When to Use |
| ---------------------------------- | ---------------------------------- |
| memory_search | Cross-project plan precedents |
| search_intelligent | Find patterns before planning |
| brain_strengths | Proven approaches |
| create_plan | Create tracked plan |
| plan_grade / plan_auto_improve | Grade and improve |
| plan_iterate | Iterate with feedback |
| plan_split | Split into tasks |
| approve_plan | Lock in approved plan |
testing
Triggers: "terse mode", "be brief", "less tokens", "fewer tokens", "compress output", "caveman", or invokes /terse. Token-efficient responses with full technical accuracy.
tools
Triggers: "compress this file", "compress CLAUDE.md", "compress memory", "shrink this", "reduce tokens in file", or invokes /compress. Compresses natural language files to save input tokens.
testing
Triggers: "release", "bump version", "publish packages", "cut a release", "version bump", "npm publish". Bumps monorepo versions, commits, tags, pushes to trigger CI release. Use deliver-and-ship for quality gates.
development
Triggers: "implement X", "build Y", "fix Z", "add feature", or any work task needing planning + execution. Full orchestration loop: plan, execute, complete with vault context and brain recs.