Claude Skill

resolve-findings

Choose an implementation path (direct or plan) for evaluated findings and dispatch it. Direct path applies fixes directly; plan path runs $turboplan. Use after $evaluate-findings has tagged findings and they need to be implemented, or when the user asks to "resolve findings", "ap

LLM Mart · 0 points · 19 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download tobihagemann-turbo-codex_skills_resolve-findings-bda508a.zip · 1 KB

tobihagemann/turbo 403 31 forks MIT Updated 1d ago

Part of tobihagemann/turbo — 147 skills

Install

skills CLI npx skills add https://github.com/tobihagemann/turbo/tree/main/codex/skills/resolve-findings

Claude Code claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install tobihagemann-turbo@llmmart

Git git clone https://github.com/tobihagemann/turbo.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole tobihagemann/turbo collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

Resolve Findings

Choose a path for evaluated findings and run it. Direct path applies fixes directly; plan path runs $turboplan.

Task Tracking

At the start, use update_plan to track each step, restating any remaining steps of a parent workflow alongside them:

Choose path
Run the chosen path

Step 1: Choose Path

Present a summary of accepted findings (Apply verdict): count by complexity (mechanical fixes vs. architectural or design changes). Then use request_user_input to let the user choose:

Plan — Run $turboplan for drafting, refinement, approval, implementation, and finalize
Direct — Run $apply-findings, then close out the change

Suggest Plan when findings include complex or architectural changes. Suggest Direct when all findings are mechanical fixes.

Add a Get a second opinion option whenever the findings would establish a pattern others will follow, change an interface, or commit to a data shape, and whenever neither path earns the suggestion with conviction. It runs the $consult-claude skill for which path the findings warrant on technical merit. Then resolve the path with that answer in hand, re-asking when the choice stays the user's.

Step 2: Run the Chosen Path

Read the reference file for the confirmed path and follow its phases:

Direct path — references/direct-path.md
Plan path — references/plan-path.md

State the chosen path before continuing with the reference file.

Then call update_plan to mark this step completed and continue with the next step of the active workflow.

Files (turbo)

references

direct-path.md 808 B

# Resolve Findings: Direct Path

Apply evaluated findings via `$apply-findings`.

## Task Tracking

Use `update_plan` to track each phase:

1. Run `$code-style` skill
2. Run `$apply-findings` skill
3. Close out the change

## Phase 1: Run `$code-style` Skill

Run the `$code-style` skill to load existence, reuse, mirror, and symmetry rules before editing.

## Phase 2: Run `$apply-findings` Skill

Run the `$apply-findings` skill on the evaluated findings.

## Phase 3: Close Out the Change

If no changes were made, skip this phase.

Use `request_user_input` to choose how to close out the change:

- **Full QA** — run the `$finalize` skill
- **Quick close** — run the `$quick-finalize` skill

Then call `update_plan` to mark this step completed and continue with the next step of the active workflow.

plan-path.md 410 B

# Resolve Findings: Plan Path

Run `$turboplan` with the accepted findings as the task description.

## Task Tracking

Use `update_plan` to track each phase:

1. Run `$turboplan` skill

## Phase 1: Run `$turboplan` Skill

Run the `$turboplan` skill with the accepted findings as the task description.

Then call `update_plan` to mark this step completed and continue with the next step of the active workflow.

SKILL.md 2 KB

---
name: resolve-findings
description: "Choose an implementation path (direct or plan) for evaluated findings and dispatch it. Direct path applies fixes directly; plan path runs $turboplan. Use after $evaluate-findings has tagged findings and they need to be implemented, or when the user asks to \"resolve findings\", \"apply evaluated findings\", or \"dispatch findings to implementation\"."
---

# Resolve Findings

Choose a path for evaluated findings and run it. Direct path applies fixes directly; plan path runs `$turboplan`.

## Task Tracking

At the start, use `update_plan` to track each step, restating any remaining steps of a parent workflow alongside them:

1. Choose path
2. Run the chosen path

## Step 1: Choose Path

Present a summary of accepted findings (Apply verdict): count by complexity (mechanical fixes vs. architectural or design changes). Then use `request_user_input` to let the user choose:

- **Plan** — Run `$turboplan` for drafting, refinement, approval, implementation, and finalize
- **Direct** — Run `$apply-findings`, then close out the change

Suggest Plan when findings include complex or architectural changes. Suggest Direct when all findings are mechanical fixes.

Add a **Get a second opinion** option whenever the findings would establish a pattern others will follow, change an interface, or commit to a data shape, and whenever neither path earns the suggestion with conviction. It runs the `$consult-claude` skill for which path the findings warrant on technical merit. Then resolve the path with that answer in hand, re-asking when the choice stays the user's.

## Step 2: Run the Chosen Path

Read the reference file for the confirmed path and follow its phases:

- **Direct path** — [references/direct-path.md](references/direct-path.md)
- **Plan path** — [references/plan-path.md](references/plan-path.md)

State the chosen path before continuing with the reference file.

Then call `update_plan` to mark this step completed and continue with the next step of the active workflow.