agentleFS
mustafahasanainmustafahasanain/frappe-workflow/skills/task-planning/SKILL.md

task-planning

Skill0 starsChanged 3 months agoMITView on GitHub

Turn a ready plan or plain task description into a validated, repository-aware TASK_PLAN.md. Detects existing/related features, verifies paths, plans normal tasks and complete projects, and prevents silent scope expansion.

8 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use code-review.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • GoogleSkill

    code-review

    Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every implementation step must be specific and verifiable (template step format).

    line 50

“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Task Planning Skill

Produces exactly one active docs/ai-context/TASK_PLAN.md (template: templates/task/TASK_PLAN.md in the plugin) from either a prepared plan or a plain description. The plan is repository-aware: every stated path and fact is verified or explicitly marked for verification.

When to Use

  • The start action, with either input type.
  • Resuming a planning-stage workflow.

Inputs

  • Raw user input (ready plan or description).
  • docs/ai-context/PROJECT_CONTEXT.md, docs/ai-context/FEATURE_CHANGELOG.md (searched via the feature-changelog skill before writing the plan).
  • Detection facts (bin/frappe-workflow detect --json), current Git state.

Outputs

  • docs/ai-context/TASK_PLAN.md passing bin/frappe-workflow validate task-plan (references/plan-validation.md).
  • Frontmatter filled: deterministic task_id (TASK-YYYY-NNN — next number from prior plans/Git history, never reusing a found ID; start at 001 when none found), task_type, status: planned, app/bench/site facts, suggested_branch, related_features.

Procedure

  1. Active-task rule: an unfinished task is never silently replaced — the frappe-task router enforces this before delegating here.
  2. Feature search first (existing-feature-analysis.md).
  3. For ready plans: treat as input, not truth — verify every path, add missing technical/validation/security/migration steps, convert to the standard format; report every correction made.
  4. For descriptions: analyze the repository, then draft the full plan.
  5. For task_type: project, additionally follow complete-project-planning.md.
  6. Every implementation step must be specific and verifiable (template step format). Vague steps ("Update backend") are forbidden.
  7. Validate, then hand back to the router for the planning gate.

Preconditions

  • Detection succeeded; no unfinished active task.

Stopping Conditions

  • Plan validates and the user has seen it (plus the corrections list for ready plans) → done; implementation starts only after the planning gate.
  • Input intent unclear (not a development task) → ask, don't guess.

Prohibited

  • Silently changing the business objective, adding unrelated features, or expanding product scope (allowed silently: path corrections, missing technical validation, security/migration steps — each recorded).
  • Starting implementation before the plan is complete and accepted.
  • Inventing paths, DocTypes, or Sites — unverified locations say Requires repository verification.

Shared Rules

shared-workflow-rules.md, frappe-project-detection.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.