skill-quaylabshq-skill-graph-implementation-plan · by Install
$ agentstack add skill-quaylabshq-skill-graph-implementation-plan ✓ 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.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-quaylabshq-skill-graph-implementation-plan) 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
Implementation Plan
A navigable reference graph for creating thorough implementation plans. Enhances plan mode with mandatory questioning, research, context-efficient decomposition, and multi-agent verification to Google/NASA-grade quality standards.
Planning Process
Six-step process. Steps 0.5, 1–2, 4.5, and 5 are mandatory and must never be skipped:
| Step | Description | Reference | |------|-------------|-----------| | Overview | Full process summary + critical rules | [references/planning-process/overview.md](references/planning-process/overview.md) | | 0.5 | Domain classification — classify the task first | [references/planning-process/domain-classification.md](references/planning-process/domain-classification.md) | | 1 | Clarification — mandatory questioning phase | [references/planning-process/step-1-clarification.md](references/planning-process/step-1-clarification.md) | | 2 | Research — codebase exploration or web research | [references/planning-process/step-2-research.md](references/planning-process/step-2-research.md) | | 3 | Decompose — recursive task breakdown | [references/planning-process/step-3-decompose.md](references/planning-process/step-3-decompose.md) | | 4 | Generate plan — create the structured plan with quality doctrine | [references/planning-process/step-4-generate-plan.md](references/planning-process/step-4-generate-plan.md) | | 4.5 | Multi-agent verification — independent sub-agents verify the plan | [references/planning-process/step-4.5-verification.md](references/planning-process/step-4.5-verification.md) | | 5 | Present — show plan + verification report and wait for approval | [references/planning-process/step-5-present.md](references/planning-process/step-5-present.md) | | — | Pre/Post eval gates wrapping every step | [references/planning-process/pre-post-eval.md](references/planning-process/pre-post-eval.md) |
Questionnaire Framework
Drives all question generation — initial, mid-process, and domain-adapted:
| Topic | Reference | |-------|-----------| | Overview + core rules | [references/questionnaire-framework/overview.md](references/questionnaire-framework/overview.md) | | Initial question categories | [references/questionnaire-framework/initial-questions.md](references/questionnaire-framework/initial-questions.md) | | Mid-process gap identification | [references/questionnaire-framework/mid-process-questions.md](references/questionnaire-framework/mid-process-questions.md) | | Domain adaptation | [references/questionnaire-framework/domain-adaptation.md](references/questionnaire-framework/domain-adaptation.md) |
Research Framework
How to gather information before planning — codebase or web-based:
| Topic | Reference | |-------|-----------| | Overview + research principles | [references/research-framework/overview.md](references/research-framework/overview.md) | | Codebase exploration | [references/research-framework/codebase-exploration.md](references/research-framework/codebase-exploration.md) | | Web/domain research | [references/research-framework/web-research.md](references/research-framework/web-research.md) |
Goal-Driven Methodology
Criteria-first planning across all domains. For technical tasks: TDD. For non-technical tasks: acceptance-criteria-driven.
| Topic | Reference | |-------|-----------| | Overview + core principle | [references/goal-driven-methodology/overview.md](references/goal-driven-methodology/overview.md) | | Technical TDD planning | [references/goal-driven-methodology/technical-tdd.md](references/goal-driven-methodology/technical-tdd.md) | | Non-technical acceptance criteria | [references/goal-driven-methodology/non-technical-criteria.md](references/goal-driven-methodology/non-technical-criteria.md) |
Context Management
| Topic | Reference | |-------|-----------| | Budget, delegation, clean context | [references/context-management.md](references/context-management.md) |
Output Format
Standardized core plan structure with adaptive detail sections:
| Topic | Reference | |-------|-----------| | Format principles | [references/output-format/overview.md](references/output-format/overview.md) | | Core template (fixed sections) | [references/output-format/core-template.md](references/output-format/core-template.md) | | Adaptive sections (domain-specific) | [references/output-format/adaptive-sections.md](references/output-format/adaptive-sections.md) |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: quaylabshq
- Source: quaylabshq/skill-graph
- 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.