Feature Planning with zfeats

VerifiedSafe

Plan and execute complex features using markdown checklists stored in the `zfeats/` directory. The skill creates a structured breakdown of tasks as actionable checkboxes, guides step-by-step implementation with progress tracking, and updates the checklist in real time. Ideal for large tasks that need clear organization and traceability.

Sby Skills Guide Bot
DevelopmentBeginner
3/4/2026
Claude CodeCursorWindsurfCodex
#planning#checklists#markdown#task-breakdown#feature-development

Recommended for

Automated summary

This skill creates and maintains a markdown checklist file (under `zfeats/`) to plan and then execute a complex feature step by step.

Strengths

  • Enforces a strict checkbox format (`- [ ]` / `- [x]`) so progress is readable at a glance
  • Splits large steps until each one can be completed in a single pass
  • Preserves history: new work is appended and invalid items are annotated rather than deleted
  • Treats the checklist as the source of truth while coding, marking steps done only after verification

Limitations

  • Ships no scripts or tooling; correctness depends on the agent consistently updating the file
  • The `zfeats/` folder convention and checkbox format are not automatically validated
  • Does not cover prioritisation, estimation, or multi-person tracking
When to use it

Use it when a feature needs to be broken into tracked steps and executed incrementally with a written record.

When not to use it

Skip it for a one-off fix or a single small task that doesn't warrant a dedicated plan file.

Security analysis

Safe
Quality score74/100

The skill is purely a documentation/checklist workflow: it creates and edits markdown files under a zfeats/ directory and asks the agent to mark checkboxes as work completes. There is no network access, no secret handling, no destructive commands, no obfuscation, and no instruction to bypass safety checks. Bash is listed as allowed but never used by the instructions, so the only residual concern is over-broad tool declaration and unrestricted file naming, both of which are low severity.

Findings
  • •Bash is declared in allowed-tools but no instruction actually invokes shell commands (minor least-privilege over-declaration)
  • •Writes/edits files under zfeats/ with no path restriction, so filenames from user input are not sanitized
How this analysis is made

Examples

Plan a multi-platform feature
Write a zfeats plan for multi-platform support in zfeats/multi-platform.md, then start executing the first step and tick it off.
Break down a queue optimisation
Break the send-queue optimisation into a checklist under zfeats/msg-queue.md, complete step one, and mark it done with a short note.
Check progress on an existing plan
Open zfeats/msg-queue.md and update the completion status of each checklist item based on what has been implemented.

name: use-zfeats description: Plan and execute complex features using markdown checklists. Use when the user asks to "plan a feature", "create a checklist", or "break down a task". allowed-tools: Read, Write, Edit, Glob, Bash

Use zfeats for plans

Instructions

  1. Create or open a zfeats markdown file named after the feature (kebab-case) under zfeats/ (e.g., zfeats/new-feature.md).
  2. At the top, add a short context/goal, then enumerate steps as checkbox lines only: - [ ] step detail (no unchecked bullets without boxes).
  3. Steps should be actionable, scoped, and ordered; avoid vague items. Split big steps until each can be finished in one go.
  4. When implementing, work from the checklist in order. After completing a step, immediately update the same file to - [x] ... with any brief note if useful.
  5. If new work is discovered, append new - [ ] items; do not delete history unless invalid—strike or annotate instead.
  6. Keep the checklist as the source of truth while coding; ensure code changes correspond to items and mark them done only after verification/tests for that step.
  7. When finished, ensure all planned items are - [x] or explicitly documented as deferred.

Example prompts

  • "为多平台支持写一份 zfeats 计划并开始执行"
  • "把发送队列优化拆分为清单,完成第一步并勾选"
  • "查看并更新 zfeats/msg-queue.md 的完成情况"

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/feature-planning-with-zfeats-mmbizjm4' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/feature-planning-with-zfeats-mmbizjm4/download' --output '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md.part' && mv '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md.part' '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Write, Edit, Glob, Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && test -s '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/use-zfeats' && cp -R '.skill-downloads/feature-planning-with-zfeats-mmbizjm4' '.claude/skills/use-zfeats'

Cursor
test -f '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && test -s '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/use-zfeats' && cp -R '.skill-downloads/feature-planning-with-zfeats-mmbizjm4' '.cursor/skills/use-zfeats'

Codex
test -f '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && test -s '.skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/use-zfeats' && cp -R '.skill-downloads/feature-planning-with-zfeats-mmbizjm4' '.agents/skills/use-zfeats'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/feature-planning-with-zfeats-mmbizjm4'

openskills read 'feature-planning-with-zfeats-mmbizjm4'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/feature-planning-with-zfeats-mmbizjm4/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills