Install
$ agentstack add skill-prodazhang-aigd-aigd-system ✓ 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
AIGD · system (single-system design) [minimal skeleton]
> Package contract: install the whole aigd package (the orchestrator aigd/+references/ and the 6 sub-skills (including aigd-ui-capture) placed at the same level in this environment's skills directory, following the host agent, e.g. Claude Code's .claude/skills/), don't copy this skill alone — the body's ../aigd/references/ depends on aigd/ at the same level, copying it alone breaks the link.
Positioning
Phase 2. One pass per system. Produces only the three "cheap, will-change-during-iteration" things: rules / config (test data) / system prototype. Interface contract / acceptance cases / backend algorithms are not in this phase — deferred to aigd-handoff (after finalization), to avoid locking things down while the design is still changing and wasting churn.
Read / produce / write back
- Read: this system's entry in the
manifest(dependencies, referenced shared sources of truth), theproject charter;../aigd/references/methodology.md(it is authoritative). - Produce — the paths below are an engineering-layout example, the actual directories/filenames defer to the
project charter "directory layout · naming conventions"(same source as the manifest cross-layer index): docs/systems//rules.md(-01, tagged with R-numbers, prose with no bare numerals).config/source/.xlsx(with test data) + config spec.docs/prototypes/.html(single file, zero-dependency, clickable; illustrative data on the same scale as the config).- Write back: this system's cross-layer index in the
manifest+ Status = Draft; new enums / R-numbers registered in place into the global spec.
Methodology
Defers to ../aigd/references/methodology.md (this skeleton does not copy it). Be sure to remember: contract / acceptance / backend belong to handoff, not produced in this phase.
Admission / exit
- Admission: this system's status in the manifest =
Draft, and all its dependency systems are at leastDraft(otherwise the base map is missing, go back to concept to fill it in first). - Exit: rules.md + config table (test data) + system prototype.html complete, manifest cross-layer index written → move to
aigd-iterate.
Boundary
Doesn't lock the contract, doesn't write acceptance, doesn't do balancing (filling in test values for numbers is enough; deep balancing is an out-of-package discipline).
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ProdaZhang
- Source: ProdaZhang/aigd
- 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.