Install
$ agentstack add skill-organvm-a-i-skills-claude-project-manifest ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Claude Project Manifest
Create structured, annotated documentation of Claude projects that tracks files, conversation threads, and their relationships.
When to Use
- Documenting project contents and structure
- Creating file inventories with annotations
- Tracking conversation history across sessions
- Building navigable knowledge maps
- Onboarding new collaborators to existing projects
Core Concepts
Manifest Structure
A manifest has four primary sections:
- Metadata: Project-level information (ID, version, status)
- Files: Annotated file inventory with provenance
- Threads: Conversation summaries and accomplishments
- Relations: Dependencies and connections between entities
ID System
| Entity | Format | Example | |--------|--------|---------| | Project | PROJ-{YEAR}-{SEQ} | PROJ-2024-001 | | File | FILE-{SEQ} | FILE-042 | | Thread | THR-{SEQ} | THR-017 | | Relation | REL-{SEQ} | REL-123 |
Quick Start
Minimal Manifest
manifest:
id: "PROJ-2024-001"
version: "1.0.0"
created: "2024-01-15T10:30:00Z"
project:
name: "My Project"
description: "Brief description of the project"
status: active
files:
- id: "FILE-001"
path: "src/main.py"
title: "Main Entry Point"
summary: "Application entry and initialization"
Full File Entry
files:
- id: "FILE-001"
path: "src/main.py"
type: source # source | config | doc | asset | generated
thread_id: "THR-001"
title: "Main Entry Point"
summary: "One-line description of purpose"
notes: |
Extended annotation explaining:
- Design decisions made
- Why this approach was chosen
- Key implementation details
- Known limitations or TODOs
tags: [core, initialization]
depends_on: ["FILE-002", "FILE-003"]
created: "2024-01-15T10:30:00Z"
modified: "2024-01-16T14:20:00Z"
Thread Entry
threads:
- id: "THR-001"
started: "2024-01-15T10:30:00Z"
ended: "2024-01-15T12:45:00Z"
title: "Initial Project Setup"
summary: "Created core infrastructure and configuration"
accomplishments:
- "Created directory structure"
- "Implemented Config class with validation"
- "Added logging infrastructure"
files_created: ["FILE-001", "FILE-002"]
files_modified: []
decisions:
- "Chose YAML over JSON for config readability"
- "Used dataclasses instead of Pydantic for simplicity"
tags: [setup, infrastructure]
Relations
relations:
- id: "REL-001"
type: depends_on
source: "FILE-001"
target: "FILE-002"
annotation: "Main imports and uses Config class"
- id: "REL-002"
type: implements
source: "FILE-003"
target: "FILE-004"
annotation: "Repository implements StorageInterface"
Relation types:
depends_on: Source requires target to functionextends: Source builds upon targetimplements: Source implements interface defined in targetreferences: Source refers to target without hard dependencysupersedes: Source replaces target (for versioning)
Writing Annotations
File Annotations
Good annotations answer:
- What: What does this file do?
- Why: Why was this approach chosen?
- How: Key implementation details
- Context: What prompted its creation?
Example:
notes: |
Implements rate limiting using token bucket algorithm.
Chose token bucket over sliding window for better burst handling.
Created during THR-003 when API overload issues emerged.
TODO: Add Redis backend for distributed rate limiting.
Thread Annotations
Capture:
- Goal: What we set out to accomplish
- Outcome: What we actually achieved
- Decisions: Key choices made and rationale
- Artifacts: Files created or modified
Workflow
Starting a New Project
- Create manifest file (
manifest.yaml) - Add project metadata
- Set initial status to
active
During Development
- Log new threads as conversations happen
- Add files with annotations when created
- Record relations as dependencies form
- Update thread accomplishments
Project Handoff
- Review all thread summaries
- Verify file annotations are current
- Validate all relations are documented
- Export to markdown report if needed
Output Formats
YAML (Primary)
Best for editing and version control. See assets/templates/manifest.yaml.
JSON (Machine-Readable)
For programmatic access. See assets/templates/manifest.json.
Markdown Report
Human-readable export for documentation. See assets/templates/manifest-report.md.
References
references/manifest-schema.md— Full schema specificationreferences/annotation-guidelines.md— Writing effective annotationsreferences/id-systems.md— ID generation strategiesreferences/workflow-integration.md— Integration patterns
Related Skills
- knowledge-graph-builder: For more complex relationship modeling
- documentation-generator: For generating docs from manifests
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: organvm
- Source: organvm/a-i--skills
- License: Apache-2.0
- Homepage: https://organvm.github.io/a-i--skills/
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.