Organize Long AI Tasks with Planning Files
Long AI sessions can lose goals, decisions, and progress. This skill guides Claude, Codex, and Claude Code to store plans, findings, and logs in project files.
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "planning-with-files" from https://skillstore.io/skills/zhanlincui-planning-with-files.md and its manifest at https://skillstore.io/api/skills/zhanlincui-planning-with-files/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Using "planning-with-files". Start a feature build that needs research, implementation, and testing.
Expected outcome:
A task plan with phases, a findings log for research, and a progress log for actions and tests.
Using "planning-with-files". Resume a project after a long session gap.
Expected outcome:
Using "planning-with-files". Check whether the task is ready to finish.
Expected outcome:
A completion review that compares completed phases with pending or in-progress sections.
The static findings are benign in context. The shell scripts use fixed local commands for planning setup and status checks. The markdown backtick detections are formatting examples. No prompt injection, data exfiltration intent, destructive behavior, or unauthorized network activity was found.
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
https://skillstore.io/skills/zhanlincui-planning-with-files/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/zhanlincui-planning-with-files?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/zhanlincui-planning-with-files?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhanlincui-planning-with-files/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/zhanlincui-planning-with-files.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>ZhanlinCui. (2026). planning-with-files security audit report (audit version 4) [Author version 2.1.2]. Skillstore. https://skillstore.io/skills/zhanlincui-planning-with-files/audits/4@techreport{zhanlincui-zhanlincui-planning-with-files-2026,
author = {ZhanlinCui},
title = {planning-with-files security audit report (audit version 4)},
institution = {Skillstore},
year = {2026},
number = {4},
url = {https://skillstore.io/skills/zhanlincui-planning-with-files/audits/4},
note = {Author version 2.1.2}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "planning-with-files security audit report (audit version 4)"
version: "2.1.2"
type: report
authors:
- name: "ZhanlinCui"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/zhanlincui-planning-with-files/audits/4"
identifiers:
- type: other
value: "skillstore:zhanlincui-planning-with-files:audit:4"
description: "Skillstore immutable audit report identifier"
Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.
Why this variant is first
zhanlincui-planning-with-files
2026-08-21
ammarcodes-planning-with-files
2026-08-21
othmanadi-planning-with-files
2026-08-21
sickn33-planning-with-files
2026-08-21
Break a coding task into phases, decisions, tests, and delivery steps before work begins.
Capture sources, discoveries, and open questions during long investigation tasks.
Reload goals, current phase, findings, and prior errors after a context reset or break.
Use planning-with-files for this task. Create task_plan.md, findings.md, and progress.md before beginning.
Use planning-with-files. After each phase, update the plan status, findings, errors, and test results.
Use planning-with-files to resume this project. Read the planning files, summarize current status, and continue from the next phase.
Use planning-with-files to manage a complex task with research, implementation, verification, and delivery phases. Keep decisions and failed attempts documented.
Author
ZhanlinCuiLicense
MIT
Author version
v2.1.2
Skillstore revision
r1
Repository
https://github.com/ZhanlinCui/Ultimate-Agent-Skills-Collection/tree/main/planning-with-filesRef
88a205c7f635a966e31156313b590d59007c5caa
Maintenance freshness
7/18/2026
Usage
238 downloads · 381 views
Generate Bilingual GitHub Release READMEs
Release notes and README updates can take time before each GitHub release. This skill generates bilingual release documentation and guides review, commit, and push steps.
Organize Obsidian Notes with AI
Obsidian vaults can become hard to review and update consistently. This skill helps Claude and Codex create daily notes, capture ideas, and summarize recent work.
Process PDFs with Extraction and Form Tools
PDF work often requires separate tools for text, tables, pages, and forms. This skill gives Claude, Codex, and Claude Code guided workflows and helper scripts for PDF tasks.
Build Distinctive Frontend Interfaces
Generic web interfaces can feel unfinished and forgettable. This skill guides Claude, Codex, and Claude Code toward polished frontend work with clear visual direction.
Plan Creative Work Before Building
Teams often start implementation before goals, constraints, and trade-offs are clear. This skill guides Claude, Codex, and Claude Code through structured brainstorming before design work begins.
Draft Reader-Tested Documentation
Complex documents often fail when readers lack the author's context. This skill guides context gathering, section drafting, iterative edits, and reader testing.
Optimize AI Context Windows
by ChakshuGautam
Long AI sessions can waste tokens, slow responses, and lose important context. This skill gives Claude, Codex, and Claude Code practical patterns for compacting, masking, caching, and budgeting context.
Track Long Tasks With a Portable State Ledger
by glenskii
Long technical tasks lose decisions, evidence, and next actions across sessions. This skill maintains a concise Markdown state file with reviewed local evidence references.
Track Feature Requirements in YAML
by Chemiseblanc
Teams lose project intent when requirements live only in chat or task lists. This skill keeps scope, tests, decisions, and progress in a persistent features.yml file.
Organize Conductor Tracks
by sickn33
Track work can become unclear when specs, plans, status, and metadata drift apart. This skill gives Claude, Codex, and Claude Code structured guidance for Conductor track workflows.
Verify Agent Completion With Evidence
by CleanExpo
AI agents can mark work complete without proof, which creates false completion risk. This skill requires independent evidence before task completion is accepted.
Plan Requirements with Interactive Questions
by DNYoussef
Ambiguous project requests often lead to missing requirements and rework. This skill guides Claude, Codex, and Claude Code through structured question batches.