personal-project-planner
Shape a personal tool or side-project into a small, buildable plan and write back the durable outcomes into the llm-os project docs.
Skill by armin-haghi
Chalk Labs
Need help deploying personal-project-planner?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/armin-haghi-personal-project-planner
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: ml, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/personal-project-planner
What's inside
- Skill name
personal-project-planner- Description
- Shape a personal tool or side-project into a small, buildable plan and write back the durable outcomes into the llm-os project docs.
- License
- MIT
- Instructions
- 199 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Personal Project Planner Use this skill when the user wants to build a personal tool, script, automation, bot, dashboard, extension, or other side project for their own use rather than as a business. This is an early-stage skill. It fits best inside: - `Opportunity framing` - `Solution shaping` - early `Prototype` This skill should bias toward simplicity and actual shipping. ## Output modes Choose one output mode before writing back. ### `Status-surface` Use when: - there is no repo yet - the user wants comments and lightweight feedback - the project is still being scoped Write to one canonical status surface. That surface may be Notion, Confluence, markdown, a tracker record, or another durable workspace. Do not treat the tool choice as the operating model. Minimum top block: - `Status` - `Stage` - `Freshness` - `Last reviewed` - `Next decision` - `Owner` - `Canonical repo` - `Execution surface` Recommended sections: 1. `Summary` 2. `What this is` 3. `Who it is for` 4. `Why it matters now` 5. `Simplest version` 6. `Dependencies and blockers` 7. `Scope cuts` 8. `Current recommendation` 9. `Next decision` 10. `Next action` If the chosen status-surface tool is unavailable, produce structured markdown so it can be pasted into the canonical concept surface. ### `Repo-writeback` Use when: - a repo exists - a bounded first build slice exists - implementation is starting Write to the repo's live project-doc surface and keep the external status surface as summary, review, comment, run-dispatch, and human-decision support rather than a second execution surface. ## Read path Use the repo's live project-doc surface. The default layout is `docs/`, but follow any repo-local override declared in `AGENTS.md`. Read only the smallest sufficient context: 1. `project-spine.md` on the live project-doc surface if it exists 2. `current-milestone.md` on the live project-doc surface if it exists 3. `open-questions.md` on the live project-doc surface only if needed 4. `session-brief.md` on the live project-doc surface only if needed If the repo is not yet initialized: - use the user's prompt as the working source - prefer `Status-surface` output mode - switch to `Repo-writeback` once the repo exists ## Goal Turn a personal itch into: 1. the simplest version worth building 2. a clear technical approach 3. a bounded build spec or first milestone that can be handed off cleanly ## Phase 1 — Clarify and cut scope Trigger: - the user describes something they want to build for themselves - the user describes a workflow problem they want to automate Do: - restate what is actually being built - choose the most likely interpretation if the prompt is ambiguous - define the simplest version that would genuinely solve the problem - identify needed data, APIs, permissions, runtime, and setup - identify blockers and likely showstoppers early - list explicit scope cuts for version one Keep this lean. Do not let a personal tool inflate into a product roadmap. ## Phase 2 — Approach and components Trigger: - the user confirms the interpretation - or says to proceed Do: - recommend a stack and runtime based on speed and simplicity - define a one-sentence architecture - identify a credible alternative only if it materially changes effort - break the build into small components - identify the few design decisions that actually matter Prefer local, simple, and low-ops defaults unless the user clearly needs more.
From armin-haghi/llm-os, MIT.
More from armin-haghi/llm-os
- 0.497score
pitch-deck-builder
armin-haghi
Build a complete, polished pitch or reference deck from scratch.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
business-case-analyzer
armin-haghi
Analyze a business or product idea through opportunity framing and solution shaping, then write back the durable outcomes into the llm-os project docs.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
morning-status-brief
armin-haghi
Produce a read-only morning project status from the LLM-OS Project Control Tower and Agent Run Queue.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
orchestrator
armin-haghi
Use the single cross-interface orchestration path for project sweeps and selected-project agent work.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
project-audit
armin-haghi
Audit one project for LLM-OS readiness, gaps, compatibility, and source-of-truth drift.
SkillCFreshness: C★ 1Claude Code +9 - 0.426score
surface-human-topics
armin-haghi
Surface decision-worthy and uncertainty-heavy topics inside one project's active context.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
capture-human-input
armin-haghi
Capture lightweight human input and write it to the smallest correct durable artifact.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
project-refresh
armin-haghi
Refresh canonical project context and tighten milestone clarity.
SkillDFreshness: D★ 1Claude Code +9 - 0.426score
review-gate
armin-haghi
Review milestone output and produce a durable pass / conditional pass / fail result.
SkillDFreshness: D★ 1Claude Code +9 - 0.422score
agent-run
armin-haghi
Pick up and advance one bounded run from the Agent Run Queue.
SkillDFreshness: D★ 1Claude Code +9 - 0.422score
repo-initialize
armin-haghi
Initialize or retrofit a consuming repo into the llm-os working model.
SkillDFreshness: D★ 1Claude Code +9 - 0.422score
llm-os-session
armin-haghi
Start or continue serious work using the canonical llm-os core.
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 16, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/armin-haghi/llm-os
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from armin-haghi
- 0.497score
pitch-deck-builder
armin-haghi
Build a complete, polished pitch or reference deck from scratch.
SkillCFreshness: C★ 1Claude Code +9 - 0.494score
business-case-analyzer
armin-haghi
Analyze a business or product idea through opportunity framing and solution shaping, then write back the durable outcomes into the llm-os project docs.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
project-audit
armin-haghi
Audit one project for LLM-OS readiness, gaps, compatibility, and source-of-truth drift.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
morning-status-brief
armin-haghi
Produce a read-only morning project status from the LLM-OS Project Control Tower and Agent Run Queue.
SkillCFreshness: C★ 1Claude Code +9 - 0.491score
orchestrator
armin-haghi
Use the single cross-interface orchestration path for project sweeps and selected-project agent work.
SkillCFreshness: C★ 1Claude Code +9 - 0.426score
capture-human-input
armin-haghi
Capture lightweight human input and write it to the smallest correct durable artifact.
SkillDFreshness: D★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get personal-project-planner running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
personal-project-planner skill. Agent Mart. https://agentmart.dev/skills/armin-haghi-personal-project-planner (last updated 2026-10-24)