Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
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
  • Authors
  • 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
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Project Status

ASecurity

Maintain machine-readable project status snapshots for instant context at the start of any session, eliminating the need to re-derive project state from package.json, Cargo.toml, or git history. A lightweight PROJECT.md convention in every project root: YAML frontmatter for machine parsing (status, phase, version, last_session, tech_stack, blockers, focus) plus a brief prose section for human context. Triggered: automatically at session start (read PROJECT.md first, then work), when starting ...

3 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentstypescriptrustgoreactgitfrontendbackend

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add Tekkiiiii/the-agency --skill project-status --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project Status?

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

Security grade badge for Project Status
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tekkiiiii-project-status/badge)](https://www.skillsdirectory.com/skills/tekkiiiii-project-status)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: project-status
description: >
  Maintain machine-readable project status snapshots for instant context at the
  start of any session, eliminating the need to re-derive project state from
  package.json, Cargo.toml, or git history. A lightweight PROJECT.md convention
  in every project root: YAML frontmatter for machine parsing (status, phase,
  version, last_session, tech_stack, blockers, focus) plus a brief prose section
  for human context. Triggered: automatically at session start (read PROJECT.md
  first, then work), when starting work on a project after time away (check if
  last_session is stale), during handoffs (what's the current state?), when
  planning new work (what are the blockers?), and when onboarding to a codebase.
  Key capabilities: a single file that replaces reading package.json + git log +
  several docs, a focus list that tells you what to work on immediately, a blockers
  field that surfaces what genuinely stopped progress, and a derived-vs-human-
  maintained field table so contributors know when to update. Ideal for anyone
  working across multiple projects, anyone inheriting a codebase, and teams that
  want a shared understanding of project state without a project management tool.
  Also for writing better commit messages (know the phase/status), assessing build
  health at a glance before running tests, and quickly comparing tech stacks across
  a portfolio.
---

# Project Status — Instant Context

A lightweight convention for capturing project state in a single `PROJECT.md` file that an AI can read in one pass, eliminating the need for re-exploration on every session.

---

## Format

Every project should have a `PROJECT.md` in its root directory. The format uses YAML frontmatter for machine-readability, followed by a brief prose summary.

```yaml
---
name: [project-name]
status: active          # active | paused | archived | completed
phase: mvp             # bootstrap | mvp | feature | polish | maintenance
version: 0.1.0         # mirrors package.json/Cargo.toml

last_session: 2026-03-19

tech_stack:
  frontend: [React 19, TypeScript, Vite, Tailwind]
  backend: [Rust, Tauri 2, tokio, reqwest]
  packaging: [Tauri bundler, macOS app]

build: passing         # passing | failing | unknown

blockers: []           # empty = clear; list blockers only when present

focus:                 # current work in progress or next priority
  - Feature X
  - Feature Y
---

## What This Project Is

One-paragraph description of the project's purpose.

## Current Status

Brief status summary (2-3 sentences).

## Key Architecture

- `src/` — frontend
- `src-tauri/` — backend

## Open Questions

- Question 1
- Question 2
```

---

## When to Read PROJECT.md

**Before exploring any project for the first time in a session**, check for and read `PROJECT.md` in the project root. This is the single source of truth for project state — do not re-derive it from package.json, Cargo.toml, or git history unless the file is missing or stale.

---

## Session Workflow (Session Start)

1. Read `medium-term.md` at `~/.claude/memory/medium-term.md`
2. Identify the current project and its stacks from the Active Projects table
3. Read `{project}/PROJECT.md`
4. Sync lessons for all stacks: run `/lessons-sync` (all stacks)

## When to Update PROJECT.md

### At Session End
1. Update `last_active` in `medium-term.md` for the current project
2. Sync lessons: for each stack in the project, diff root `~/.claude/memory/lessons/{stack}.md` against `{project}/memory/lessons/{stack}.md`, append new entries from root
3. Append session log to `{project}/memory/sessions/YYYY-MM-DD.md`
4. Update `last_session` in `{project}/PROJECT.md` to today's date
5. Update `focus` if work shifted from what was listed
6. Update `status` or `phase` only if a genuine milestone was hit
7. Update `blockers` only if something genuinely blocked progress

### At Session Start
- Read PROJECT.md first
- Use `focus` to immediately understand what to work on
- If `last_session` is stale (more than a few days ago), ask if the file needs updating

### Never Update For
- Package version bumps (those live in package.json/Cargo.toml)
- Individual commits or minor code changes
- Git history (git log is the source of truth for activity)

---

## Derived vs. Human-Maintained Fields

| Field | Source | Update Frequency |
|-------|--------|-----------------|
| `name` | human | only on rename |
| `status` | human | on phase change |
| `phase` | human | on milestone |
| `version` | package.json / Cargo.toml | on release |
| `last_session` | human (session end) | every session |
| `tech_stack` | package.json / Cargo.toml | on stack change |
| `build` | human (after build) | after builds |
| `blockers` | human | only when present |
| `focus` | human | at session end |

---

## Adding a New Project

When a new project is created:

1. Create `{project}/PROJECT.md` with the standard format
2. Run `/skill-import` for the project's stack
3. Update `medium-term.md` at `~/.claude/memory/medium-term.md`: add the project to the Active Projects table with its stacks and location
4. Sync lesson files: `/lessons-sync`

Attribution

TekkiiiiiTekkiiiii
View sourceSee grades on GitHubMore from Tekkiiiii →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

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

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 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', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 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.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →