← Browse

@gradion-ai/task-planning

A

Structured task planning workflow with user feedback loops. Use when the user explicitly requests planning (e.g., "make a plan", "plan first", "create a plan"). Covers creating plans with actionable steps, iterating based on feedback, saving confirmed plans, and executing step-by-step with progress tracking.

skillclaude

Install

agr install @gradion-ai/task-planning --target claude

Writes 1 file into .claude/skills/, pinned to git-88907961.

  • .claude/skills/task-planning/SKILL.md

Document


name: task-planning description: Structured task planning workflow with user feedback loops. Use when the user explicitly requests planning (e.g., "make a plan", "plan first", "create a plan"). Covers creating plans with actionable steps, iterating based on feedback, saving confirmed plans, and executing step-by-step with progress tracking.

Task Planning

Structured workflow for planning and executing tasks when explicitly requested by the user.

Planning Phase

1. Create Initial Plan

Draft a plan with clear, actionable steps using markdown checklist format:

- [ ] Step 1: Description
- [ ] Step 2: Description
- [ ] Step 3: Description

2. Request Feedback

Present the plan to the user and ask for feedback. Do not proceed until feedback is received.

3. Iterate Until Confirmed

Revise the plan based on user feedback. Continue the proposal-feedback loop until the user confirms.

4. Save Confirmed Plan

Write the confirmed plan to {plans_rel_dir}/<task-name>.md where:

  • <task-name> is a descriptive kebab-case name
  • Example: {plans_rel_dir}/add-user-authentication.md
  • The {plans_rel_dir}/ directory already exists

Execution Phase

5. Execute Step-by-Step

Work through the plan sequentially:

  • First unchecked item is the current task
  • After completing each step, mark with checkmark: - [x] Step description
  • Update the plan file to reflect progress

6. Revise as Needed

If execution reveals the need for plan adjustments:

  • Update the plan file with revised steps
  • Inform the user of significant changes

7. Request Feedback During Execution

If encountering uncertainty or needing user input during execution, ask for feedback before proceeding.

Plan File Format

# <Task Title>

## Steps

- [x] Completed step
- [ ] Pending step
- [ ] Another pending step

## Notes

Optional section for context, decisions made, or issues encountered.

Trustgrade A

  • passBody integrity

    Whether the stored document is plausibly the kind of file the artifact declares, rather than something fetched by mistake.

  • passType matchnot applicable to this artifact type

    Whether the artifact is really the kind of thing its metadata claims it is.

  • passFreshness

    How long since the source repository was last pushed to.

  • passPrompt injection

    Scans the artifact's own text for instructions aimed at your agent rather than at you.

  • passLicense

    Whether the source repository declares an SPDX license permissive enough to redistribute.

How the grade is calculated

Each check contributes 0 points when it passes, 1 when it warns, and 2 when it fails. The total maps to a letter:

  • Aevery check passed
  • Bone warning
  • Ctwo warnings
  • Dprompt injection or body integrity failed, or three warnings
  • Fone of those failed, and something else is wrong

These are automated hygiene checks, not a security audit, and not a dependency or vulnerability scan. A grade of A means nothing was flagged — not that the artifact is safe.

Versions

  • git-88907961fa262026-07-31