Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

6 Close

ASecurity

Phase 6 — Close out the project: document results, actuals, and create a Logseq wiki page.

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
ai-agents

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill 6-close --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of 6 Close?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for 6 Close
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-6-close/badge)](https://www.skillsdirectory.com/skills/tstapler-6-close)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
description: "Phase 6 — Close out the project: document results, actuals, and create a Logseq wiki page."
user-invocable: true
---

# home:6-close

Document the completed project, record final costs, extract lessons learned, and create a Logseq wiki page as the permanent record.

## Instructions

1. **Follow [SETUP.md](SETUP.md)** — identify PROJECT_NAME, and mark this stage's task `in_progress` if a task tool is available (Check 3).

2. **Entry gate — read all project artifacts:**
   - `home_plans/<PROJECT_NAME>/scope.md`
   - `home_plans/<PROJECT_NAME>/plan.md`
   - `home_plans/<PROJECT_NAME>/execution-log.md` — halt if missing; the project isn't tracked as executed yet

3. **Calculate actuals.** From the execution log:
   - Total actual cost vs estimated cost
   - Total actual duration vs estimated duration
   - Count of surprises/issues encountered

4. **Ask one closing question:**
   ```
   header: "Outcome"
   question: "How did the project turn out?"
   options:
     - "Complete success — everything went to plan"
     - "Done, but with notable issues or changes from the plan"
     - "Partially done — some tasks deferred to later"
     - "Abandoned or significantly descoped"
   ```

5. **Write the Logseq wiki page** to `logseq/pages/home-project-<PROJECT_NAME>.md`:

```markdown
---
title: Home Project- <Human-Readable Project Name>
tags: home-project, [[Home Improvement]]
date-completed: <YYYY-MM-DD>
---

- **Project**: [[<PROJECT_NAME>]]
- **Completed**: <YYYY-MM-DD>
- **Area**: <kitchen | bathroom | bedroom | outdoor | etc.>
- **Type**: <repair | installation | renovation | maintenance>

## Summary
<2-3 sentence summary of what was done and the outcome>

## Cost
| | Estimated | Actual |
|--|-----------|--------|
| Materials | $<X> | $<X> |
| Labor/Contractor | $<X> | $<X> |
| Permits | $<X> | $<X> |
| Contingency used | — | $<X> |
| **Total** | **$<X>** | **$<X>** |

## Duration
- Estimated: <X>
- Actual: <X>

## What Went Well
- <bullet>

## What to Do Differently Next Time
- <bullet>

## Surprises & Issues
<List significant issues from the execution log, or "None">

## Resources & References
<Products, contractors, or techniques worth remembering for future projects. Link to the product/retailer wiki pages created during research (e.g. `[[Product Name]]`) instead of plain text where one exists — check `home_plans/<PROJECT_NAME>/research/materials.md` for pages created/updated during Phase 2>

## Related Projects
- [[<any related home projects>]]
```

6. **Check for follow-up maintenance.** Based on the project, note any recurring maintenance items:
   - If paint was applied: "Touch up in 3–5 years"
   - If caulk was applied: "Inspect annually, replace as needed"
   - If a mechanical system was serviced: "Next service in X months"

   If maintenance items exist, ask:
   ```
   header: "Maintenance reminders"
   question: "Do you want to add recurring maintenance reminders to your Todoist Home project?"
   options:
     - "Yes — add them to Todoist"
     - "No — just document them in the wiki page"
   ```

7. **Exit gate**: confirm the wiki page was written and is non-empty. Mark this stage's task `completed` if a task tool is available (this closes out the project's whole task chain). **Output the close summary:**
   ```
   ✅ Phase 6 complete — project closed

   Final cost: $<X> (estimated: $<X>) — <over/under/on budget>
   Duration: <X> (estimated: <X>)
   Wiki page: logseq/pages/home-project-<PROJECT_NAME>.md

   Project archive: home_plans/<PROJECT_NAME>/ (keep for reference)
   ```

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →