Install
$ agentstack add skill-ariaxhan-the-agent-library-write-project-vision-handoff ✓ 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
Write Project Vision Handoff
Turn planning context into documents a coding agent can build from without seeing the original conversation.
You are a planner, not the implementer. Capture intent, constraints, decisions, rejected alternatives, and success criteria. Defer exact code structure and implementation choices unless the user explicitly decided them.
1. Gather the source context
Read the conversation, notes, brief, screenshots, or spec the user supplied. Extract:
- Explicit decisions
- Rejected alternatives
- Hard constraints and anti-requirements
- User intent signals, including repeated frustrations or preferences
- Edge cases and failure modes already discussed
- Success criteria and launch boundaries
If the source is thin, write the missing assumptions as open questions instead of inventing facts.
2. Separate audiences
Write two different documents:
| Document | Audience | Purpose | |---|---|---| | VISION.md | Coding agent | Dense source of truth: what, why, constraints, decisions, task | | FLOWCHARTS.md | Human reader | Plain-English architecture explanation with diagrams and glossary |
Do not duplicate sections between them. VISION.md carries rationale. FLOWCHARTS.md carries comprehension.
3. Write VISION.md
Include:
- What this is
- The problem
- The solution
- Key decisions with rationale and rejected alternatives
- Design constraints
- Anti-requirements
- Planning considerations
- Success criteria
- The coding agent's task
Rules:
- No code or pseudocode.
- No file trees unless already decided.
- No library/framework prescriptions unless already decided.
- Preserve user quotes when they capture intent better than a summary.
4. Write FLOWCHARTS.md
Include:
- Core concept in simple language
- Glossary for technical/domain terms
- ASCII flow diagram
- Scenario walkthroughs
- Component breakdown
- Questions to verify understanding
Every technical term gets a plain-English definition. Prefer diagrams over paragraphs.
5. Add supplementary docs only when needed
Allowed:
DECISIONS.mdfor many complex tradeoffsCONSTRAINTS.mdfor unusual technical or business limitsPRIOR_ART.mdfor existing systems the plan referencesGLOSSARY.mdwhen domain vocabulary is heavy
Do not create README, installation docs, changelog, or implementation guides.
6. Validate the handoff
Before finishing, check:
- Could a coding agent build from this without the original conversation?
- Are all decisions and rejected alternatives captured?
- Are constraints sourced and not invented?
- Are success criteria observable?
- Could a non-technical person understand
FLOWCHARTS.md? - Is there zero meaningful overlap between the two documents?
Use reference/templates-and-examples.md for templates and examples when writing the files.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ariaxhan
- Source: ariaxhan/the-agent-library
- License: MIT
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.