Install
$ agentstack add skill-akshay-diwadkar-skills-diagram ✓ 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
Diagram
Purpose and authority
Ground a shared model, obtain approval, then build one self-contained HTML diagram with the bundled template. Default to narrative-architecture. Minimum payload: title, fidelity, nodes, labeled edges, and agent metadata. Use exact-code-graph only for code-symbol review and executive-concept-map only for business ownership and outcomes.
Do not create, overwrite, save, or verify diagram files in conversational Plan Mode. Model approval, directory creation, overwrite permission, and execution authority are separate decisions. Never hand-code an alternate renderer for normal output.
Start
After approval and outside Plan Mode, use absolute paths:
python /absolute/skill-root/scripts/cli.py --repo-root /absolute/repo \
--input fidelity=narrative-architecture --input data=/absolute/payload.json \
--input output=/absolute/diagram.html --input create_dirs=no \
--input overwrite=no --format json run
Run each returned next_command.argv with its returned cwd. Read only required_reads, write only allowed_writes, and stop on every blocking_reason. Never change create_dirs or overwrite to yes without the matching user permission.
Next-step loop
Inspect repository evidence before asking questions. Follow the phased [Diagram Output Guide](references/diagram-output-guide.md) until purpose, audience, fidelity, entities, relationships, omissions, evidence policy, output path, and verification are confirmed. Emit one approved plan before creating files.
Build the approved diagram and metadata payload using the taxonomy and shape in [Diagram Output Guide](references/diagram-output-guide.md). Obtain explicit permission for a missing directory or existing target, then run each returned command until validation reaches phase complete.
Completion and recovery
Complete only at phase complete, after validate_diagram.py passes and the browser checks in the output guide confirm readability, labels, legend, walkthrough, details, drag, pan, zoom, theme, and reset behavior.
Repair validator errors before opening the output. Review non-blocking warnings. If permission, fidelity, or the approved model changes, return to planning and regenerate the payload; do not patch generated HTML around the builder.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: akshay-diwadkar
- Source: akshay-diwadkar/skills
- 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.