Agent SkillsZhanlinCui/Agent-Skills-Hunter › planning-with-files

planning-with-files

GitHub

实现类Manus的文件式规划,通过持久化task_plan.md、findings.md和progress.md作为工作记忆。适用于复杂多步骤任务或需多次工具调用的场景,确保关键信息不丢失并规范错误处理流程。

planning/planning-with-files/SKILL.md ZhanlinCui/Agent-Skills-Hunter

Trigger Scenarios

启动复杂的多步骤任务 执行研究项目 需要超过5次工具调用的操作

Install

npx skills add ZhanlinCui/Agent-Skills-Hunter --skill planning-with-files -g -y
More Options

Non-standard path

npx skills add https://github.com/ZhanlinCui/Agent-Skills-Hunter/tree/main/planning/planning-with-files -g -y

Use without installing

npx skills use ZhanlinCui/Agent-Skills-Hunter@planning-with-files

指定 Agent (Claude Code)

npx skills add ZhanlinCui/Agent-Skills-Hunter --skill planning-with-files -a claude-code -g -y

安装 repo 全部 skill

npx skills add ZhanlinCui/Agent-Skills-Hunter --all -g -y

预览 repo 内 skill

npx skills add ZhanlinCui/Agent-Skills-Hunter --list

SKILL.md

Frontmatter
{
    "name": "planning-with-files",
    "hooks": {
        "Stop": [
            {
                "hooks": [
                    {
                        "type": "command",
                        "command": "${CLAUDE_PLUGIN_ROOT}\/scripts\/check-complete.sh"
                    }
                ]
            }
        ],
        "PreToolUse": [
            {
                "hooks": [
                    {
                        "type": "command",
                        "command": "cat task_plan.md 2>\/dev\/null | head -30 || true"
                    }
                ],
                "matcher": "Write|Edit|Bash"
            }
        ],
        "PostToolUse": [
            {
                "hooks": [
                    {
                        "type": "command",
                        "command": "echo '[planning-with-files] File updated. If this completes a phase, update task_plan.md status.'"
                    }
                ],
                "matcher": "Write|Edit"
            }
        ],
        "SessionStart": [
            {
                "hooks": [
                    {
                        "type": "command",
                        "command": "echo '[planning-with-files] Ready. Auto-activates for complex tasks, or invoke manually with \/planning-with-files'"
                    }
                ]
            }
        ]
    },
    "version": "2.1.2",
    "description": "Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.",
    "allowed-tools": [
        "Read",
        "Write",
        "Edit",
        "Bash",
        "Glob",
        "Grep",
        "WebFetch",
        "WebSearch"
    ],
    "user-invocable": true
}

Planning with Files

Work like Manus: Use persistent markdown files as your "working memory on disk."

Important: Where Files Go

When using this skill:

  • Templates are stored in the skill directory at ${CLAUDE_PLUGIN_ROOT}/templates/
  • Your planning files (task_plan.md, findings.md, progress.md) should be created in your project directory — the folder where you're working
Location What Goes There
Skill directory (${CLAUDE_PLUGIN_ROOT}/) Templates, scripts, reference docs
Your project directory task_plan.md, findings.md, progress.md

This ensures your planning files live alongside your code, not buried in the skill installation folder.

Quick Start

Before ANY complex task:

  1. Create task_plan.md in your project — Use templates/task_plan.md as reference
  2. Create findings.md in your project — Use templates/findings.md as reference
  3. Create progress.md in your project — Use templates/progress.md as reference
  4. Re-read plan before decisions — Refreshes goals in attention window
  5. Update after each phase — Mark complete, log errors

Note: All three planning files should be created in your current working directory (your project root), not in the skill's installation folder.

The Core Pattern

Context Window = RAM (volatile, limited)
Filesystem = Disk (persistent, unlimited)

→ Anything important gets written to disk.

File Purposes

File Purpose When to Update
task_plan.md Phases, progress, decisions After each phase
findings.md Research, discoveries After ANY discovery
progress.md Session log, test results Throughout session

Critical Rules

1. Create Plan First

Never start a complex task without task_plan.md. Non-negotiable.

2. The 2-Action Rule

"After every 2 view/browser/search operations, IMMEDIATELY save key findings to text files."

This prevents visual/multimodal information from being lost.

3. Read Before Decide

Before major decisions, read the plan file. This keeps goals in your attention window.

4. Update After Act

After completing any phase:

  • Mark phase status: in_progresscomplete
  • Log any errors encountered
  • Note files created/modified

5. Log ALL Errors

Every error goes in the plan file. This builds knowledge and prevents repetition.

## Errors Encountered
| Error | Attempt | Resolution |
|-------|---------|------------|
| FileNotFoundError | 1 | Created default config |
| API timeout | 2 | Added retry logic |

6. Never Repeat Failures

if action_failed:
    next_action != same_action

Track what you tried. Mutate the approach.

The 3-Strike Error Protocol

ATTEMPT 1: Diagnose & Fix
  → Read error carefully
  → Identify root cause
  → Apply targeted fix

ATTEMPT 2: Alternative Approach
  → Same error? Try different method
  → Different tool? Different library?
  → NEVER repeat exact same failing action

ATTEMPT 3: Broader Rethink
  → Question assumptions
  → Search for solutions
  → Consider updating the plan

AFTER 3 FAILURES: Escalate to User
  → Explain what you tried
  → Share the specific error
  → Ask for guidance

Read vs Write Decision Matrix

Situation Action Reason
Just wrote a file DON'T read Content still in context
Viewed image/PDF Write findings NOW Multimodal → text before lost
Browser returned data Write to file Screenshots don't persist
Starting new phase Read plan/findings Re-orient if context stale
Error occurred Read relevant file Need current state to fix
Resuming after gap Read all planning files Recover state

The 5-Question Reboot Test

If you can answer these, your context management is solid:

Question Answer Source
Where am I? Current phase in task_plan.md
Where am I going? Remaining phases
What's the goal? Goal statement in plan
What have I learned? findings.md
What have I done? progress.md

When to Use This Pattern

Use for:

  • Multi-step tasks (3+ steps)
  • Research tasks
  • Building/creating projects
  • Tasks spanning many tool calls
  • Anything requiring organization

Skip for:

  • Simple questions
  • Single-file edits
  • Quick lookups

Templates

Copy these templates to start:

Scripts

Helper scripts for automation:

  • scripts/init-session.sh — Initialize all planning files
  • scripts/check-complete.sh — Verify all phases complete

Advanced Topics

Anti-Patterns

Don't Do Instead
Use TodoWrite for persistence Create task_plan.md file
State goals once and forget Re-read plan before decisions
Hide errors and retry silently Log errors to plan file
Stuff everything in context Store large content in files
Start executing immediately Create plan file FIRST
Repeat failed actions Track attempts, mutate approach
Create files in skill directory Create files in your project

Version History

  • 849c38a Current 2026-07-05 09:21

Same Skill Collection

agent/dispatching-parallel-agents/SKILL.md
agent/subagent-driven-development/SKILL.md
agent/using-superpowers/SKILL.md
agent/writing-skills/SKILL.md
creative/algorithmic-art/SKILL.md
creative/brand-guidelines/SKILL.md
creative/canvas-design/SKILL.md
creative/frontend-design/SKILL.md
creative/slack-gif-creator/SKILL.md
creative/theme-factory/SKILL.md
dev/deploying-to-production/SKILL.md
dev/internationalizing-websites/SKILL.md
dev/mcp-builder/SKILL.md
dev/skill-creator/SKILL.md
dev/web-artifacts-builder/SKILL.md
dev/webapp-testing/SKILL.md
docs/doc-coauthoring/SKILL.md
docs/docx/SKILL.md
docs/github-release-assistant/SKILL.md
docs/internal-comms/SKILL.md
docs/pdf/SKILL.md
docs/pptx/SKILL.md
docs/xlsx/SKILL.md
git-workflow/finishing-a-development-branch/SKILL.md
git-workflow/using-git-worktrees/SKILL.md
integration/daily-news/SKILL.md
integration/doc-sync-tool/SKILL.md
integration/notebooklm/SKILL.md
integration/web-access/SKILL.md
integration/x-article-publisher/SKILL.md
obsidian/json-canvas/SKILL.md
obsidian/obsidian-bases/SKILL.md
obsidian/obsidian-helper/SKILL.md
obsidian/obsidian-markdown/SKILL.md
obsidian/project-to-obsidian/SKILL.md
planning/brainstorming/SKILL.md
planning/chat-compactor/SKILL.md
planning/executing-plans/SKILL.md
planning/writing-plans/SKILL.md
quality/receiving-code-review/SKILL.md
quality/requesting-code-review/SKILL.md
quality/systematic-debugging/SKILL.md
quality/test-driven-development/SKILL.md
quality/verification-before-completion/SKILL.md
seo/google-official-seo-guide/SKILL.md
seo/web-performance-seo/SKILL.md
vercel/vercel-deploy/SKILL.md
vercel/vercel-react-best-practices/SKILL.md
vercel/vercel-web-design-guidelines/SKILL.md
creative/ui-ux-pro-max/SKILL.md

Metadata

Files
0
Version
849c38a
Hash
33533aac
Indexed
2026-07-05 09:21

Accueil - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-07-09 00:39
浙ICP备14020137号-1 $Carte des visiteurs$