Skip to content

Commit beaa7d3

Browse files
feat(agile-lifecycle): implement full plugin v0.1.0 (#59)
* feat(agile-lifecycle): implement 11 commands, 14 scripts, and hooks - 11 slash commands (/agile-init, /agile-status, /agile-phase-start, /agile-gate-review, /agile-artefact-gen, /agile-risk-update, /agile-sprint-plan, /agile-retrospective, /agile-metrics-report, /agile-change-request, /agile-tailoring) - 14 utility bash scripts — shellcheck clean, set -euo pipefail, $((var + 1)) arithmetic throughout, LF line endings - hooks/hooks.json in mandatory wrapper format {"hooks": {...}} - 3 hook scripts (validate-artefact, check-phase-state, lf-check) Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> * feat(agile-lifecycle): implement full plugin v0.1.0 — agents, skills, schemas, templates, docs 31 agents (5 transversal + 26 phase-specific, phases 1-7) 13 skills with SKILL.md + references/ 17 JSON schemas (draft 2020-12, agile-lifecycle/ $id prefix) 8 reference docs (lifecycle-overview, gate-criteria, artefact-catalog, etc.) 54 artefact templates across 8 directories (phases 1-7 + transversal) 12 documentation files (getting-started, phase-guide, gate-guide, agent-index, etc.) README.md and CHANGELOG.md Commands, scripts, and hooks committed separately (PR #58 branch). Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> * Add skill-development assets; update plugin-studio Add a full skill-development toolkit and edits to the Plugin Studio. Changes include: - Add plugins/plugin-dev/skills/skill-development: LICENSE, rewritten SKILL.md (renamed to skill-creator and reorganized), agents docs, assets, eval-viewer, references, and multiple helper scripts for benchmarking, evaluation, packaging and validation. - Add .dev/.env.example and update .gitignore to preserve the example env while ignoring other .dev files. - Add an "agile-lifecycle" entry to .claude-plugin/marketplace.json. - Multiple Plugin Studio additions and updates: new shell components, placeholders, hooks, layout hooks, styles, and server ai config/provider types; update compiled/dist HTML and assets accordingly. These changes add tooling and documentation for developing, evaluating and iterating skills, and introduce UI/server pieces for the Plugin Studio experience. * fix(agile-lifecycle): address Gemini PR #59 review comments - plugin.json: fix gates count from '10 gates, 13 skills' to '6 formal gates (A-F), 9 skills' - agile-gate-review.md: fix gate table to canonical A-F (Portfolio Entry → Governance Review) - gate-reviewer.md: fix gate refs (A-J → A-F), schema ref (gate-io-matrix → evidence-index), sign-off table - feasibility-screening.md: fix template refs (early-feasibility-note → feasibility-note, initial-risk-note → risk-register-init, ai-data-feasibility-note removed) - problem-validation.md: fix template path prefix (phase-3/ → phase-1/ for phase-1 agent) - sprint-design.md: fix template refs (phase-4/iteration-plan → phase-3/sprint-backlog, phase-4/iteration-goal and committed-work-set removed, transversal/dod → phase-3/dod-checklist), remove non-existent schemas (product-backlog, acceptance-criteria) Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> * fix(plugin-dev): add explanatory comments to bare except pass clauses CodeQL flagged 8 'empty except' clauses in generate_review.py as code scanning alerts. Each pass is intentional (skip-and-continue on I/O or parse errors) — added inline comments to document the intent. Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> * fix(plugin-dev): add missing YAML frontmatter to skill-development eval agents analyzer.md, comparator.md, and grader.md were missing required frontmatter (name, description, model, color), causing ❌ in the validate-agent CI step. Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> * fix(agile-lifecycle): address Copilot PR review comments - plugin.json: revert skill count to 13 (matches docs/skill-index.md; 9 was overcorrection) - marketplace.json: fix '10 gates' → '6 formal gates (A-F), 13 skills' - init-lifecycle.sh: remove non-existent gates G-J from initial state; add canonical gate names - check-phase-state.sh: fix gate_unlock map (F→5,G→6,J→7 → D→5,E→6,F→7) for canonical 6-gate model - render-template.sh: replace unsafe sed substitution with Python (fixes & and | escaping, portable on macOS/BSD) - check-sprint-health.sh: fix CRIT threshold message (was showing warn_threshold); align field names with schema (commitment_ratio, defect_count with legacy fallbacks) - check-definition-of-done.sh: fix status check 'met' → 'pass' to match schema enum values - skills/artefact-authoring/SKILL.md: fix evidence-index-entry.md.template → evidence-entry.md.template - commands/agile-retrospective.md: fix improvement-backlog template path phase-6 → phase-7 Generated by Nuno Salvação Co-Authored-By: Nexo <nexo.modeling@gmail.com> --------- Co-authored-by: Nexo <nexo.modeling@gmail.com>
1 parent cacb0a2 commit beaa7d3

269 files changed

Lines changed: 25449 additions & 1415 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

.claude-plugin/marketplace.json

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -98,6 +98,17 @@
9898
},
9999
"source": "./plugins/solution-audit",
100100
"category": "development"
101+
},
102+
{
103+
"name": "agile-lifecycle",
104+
"description": "Hybrid gated-iterative lifecycle framework for AI/ML products — 7 phases, 6 formal gates (A–F), 31 agents, 13 skills, and full artefact management. Enterprise agile with governance overlay.",
105+
"version": "0.1.0",
106+
"author": {
107+
"name": "Nuno Salvacao",
108+
"email": "nuno.salvacao@gmail.com"
109+
},
110+
"source": "./plugins/agile-lifecycle",
111+
"category": "productivity"
101112
}
102113
]
103114
}

.dev/.env.example

Lines changed: 12 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,12 @@
1+
# Plugin Studio future AI provider wiring
2+
# Copy the keys you actually use into .dev/.env and keep real secrets out of Git.
3+
4+
# GitHub Models is the preferred default provider for future shell chat wiring.
5+
GITHUB_MODELS_TOKEN=
6+
# Set this to a model that is available for your GitHub Models account.
7+
GITHUB_MODELS_MODEL=
8+
GITHUB_MODELS_API_URL=https://models.github.ai/inference/chat/completions
9+
10+
# Gemini remains the fallback provider.
11+
GEMINI_API_KEY=
12+
GEMINI_MODEL=gemini-2.5-flash

.gitignore

Lines changed: 4 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,7 @@ logs/
1010
.env
1111
.env.*
1212
!.env.example
13+
!.dev/.env.example
1314

1415
# Temporary files
1516
*.tmp
@@ -31,7 +32,6 @@ pnpm-debug.log*
3132
yarn-error.log*
3233

3334
# Build outputs
34-
dist/
3535
build/
3636
coverage/
3737

@@ -43,7 +43,9 @@ coverage/
4343
.codex/
4444
.claude/CLAUDE.md
4545
/.claude
46-
/.dev
46+
!/.dev/
47+
/.dev/*
48+
!/.dev/.env.example
4749
CLAUDE.md
4850
dashboard.html
4951
/memory
Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,24 @@
1+
{
2+
"name": "agile-lifecycle",
3+
"version": "0.1.0",
4+
"description": "Hybrid gated-iterative lifecycle framework for AI/ML products — 7 phases, 6 formal gates (A–F), 31 agents, 13 skills, and full artefact management. Enterprise agile with governance overlay.",
5+
"author": {
6+
"name": "Nuno Salvacao",
7+
"email": "nuno.salvacao@gmail.com",
8+
"url": "https://www.linkedin.com/in/nsalvacao/"
9+
},
10+
"keywords": [
11+
"agile",
12+
"lifecycle",
13+
"product-management",
14+
"ai-governance",
15+
"phase-gates",
16+
"enterprise-agile",
17+
"iterative",
18+
"artefact-management",
19+
"multi-agent"
20+
],
21+
"license": "MIT",
22+
"homepage": "https://github.com/nsalvacao/nsalvacao-claude-code-plugins",
23+
"repository": "https://github.com/nsalvacao/nsalvacao-claude-code-plugins"
24+
}
Lines changed: 71 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,71 @@
1+
# Changelog
2+
3+
All notable changes to this project will be documented in this file.
4+
5+
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
6+
7+
## [0.1.0] - 2026-03-15
8+
9+
### Added
10+
11+
**Agents (31):**
12+
- 5 transversal agents: lifecycle-orchestrator, gate-reviewer, artefact-generator, risk-assumption-tracker, metrics-analyst
13+
- 4 Phase 1 agents: opportunity-framing, feasibility-screening, problem-validation, hypothesis-mapping
14+
- 3 Phase 2 agents: solution-architecture, iteration-planning, risk-register
15+
- 3 Phase 3 agents: sprint-design, acceptance-criteria, test-strategy
16+
- 4 Phase 4 agents: feature-builder, integration-engineer, ai-implementation, quality-assurance
17+
- 4 Phase 5 agents: functional-validation, ai-model-validation, gate-preparation, stakeholder-review
18+
- 3 Phase 6 agents: release-manager, deployment-engineer, hypercare-lead
19+
- 5 Phase 7 agents: operations-monitor, ai-ops-analyst, continuous-improvement, lifecycle-close, retirement-planner
20+
21+
**Commands (11):**
22+
- /agile-init, /agile-status, /agile-phase-start, /agile-gate-review, /agile-artefact-gen
23+
- /agile-risk-update, /agile-sprint-plan, /agile-retrospective, /agile-metrics-report
24+
- /agile-change-request, /agile-tailoring
25+
26+
**Skills (13):**
27+
- phase-contract, gate-checklist, artefact-authoring, risk-management, metrics-tracking
28+
- sprint-facilitation, ai-lifecycle, change-control, operational-readiness, lifecycle-tailoring
29+
- evidence-management, retrospective, definition-of-done
30+
31+
**Schemas (17 — JSON Schema draft 2020-12, $id prefixed `agile-lifecycle/`):**
32+
- phase-contract, sprint-contract, risk-register, assumption-register, clarification-log
33+
- dependency-log, change-log, change-request, evidence-index, handover-log, gate-review
34+
- lifecycle-state, artefact-manifest, waiver-log, definition-of-done, sprint-health, retrospective
35+
36+
**Templates (54):**
37+
- Phase 1 (6): opportunity-brief, feasibility-note, hypothesis-canvas, risk-register-init, stakeholder-map, gate-a-pack
38+
- Phase 2 (7): solution-brief, architecture-decision, iteration-plan, risk-register, assumption-register, dependency-map, gate-b-pack
39+
- Phase 3 (6): sprint-backlog, acceptance-criteria, test-plan, dod-checklist, sprint-risk-note, gate-c-pack
40+
- Phase 4 (8): feature-spec, code-review-record, integration-test-record, ai-experiment-log, model-card, dataset-doc, defect-log, gate-d-pack
41+
- Phase 5 (7): functional-test-report, ai-validation-report, uat-report, residual-risk-note, waiver-log, traceability-evidence, gate-e-pack
42+
- Phase 6 (6): release-plan, deployment-record, rollback-plan, hypercare-report, operations-handover, gate-f-pack
43+
- Phase 7 (5): service-report, ai-monitoring-report, retrospective-record, improvement-backlog, lifecycle-closure
44+
- Transversal (9): risk-entry, assumption-entry, clarification-entry, gate-review-report, evidence-entry, handover-entry, change-request, waiver-entry, significant-change
45+
46+
**Reference docs (8):**
47+
- lifecycle-overview, gate-criteria-reference, artefact-catalog, metrics-reference
48+
- handover-reference, tailoring-guide, genai-overlay, sprint-health-reference
49+
50+
**Scripts (14):**
51+
- validate-schema, render-template, init-lifecycle, check-phase-contract, check-gate-criteria
52+
- track-artefacts, check-assumptions, check-sprint-health, check-definition-of-done
53+
- generate-metrics-report, validate-lifecycle-state, export-evidence-index
54+
- check-release-readiness, lifecycle-summary
55+
56+
**Hooks:**
57+
- hooks.json (wrapper format)
58+
- validate-artefact.sh, check-phase-state.sh, lf-check.sh
59+
60+
**Documentation:**
61+
- getting-started, lifecycle-overview, phase-guide, gate-guide, artefact-guide
62+
- agent-index, skill-index, command-reference, schema-reference, tailoring-guide
63+
- ai-product-guide, phase-essentials-overview
64+
65+
### Framework
66+
67+
- 7 phases: Discovery & Framing → Architecture & Planning → Iteration Design → Build & Integrate → Validate & Gate → Release → Operate & Improve
68+
- 6 formal gates (A-F) with PASS/FAIL/WAIVED outcomes
69+
- Hybrid/gated-iterative positioning (not pure Scrum, not SAFe)
70+
- Full GenAI/LLM overlay for AI products (red-team at Gate E mandatory for LLM)
71+
- Lifecycle tailoring by product type (SaaS, web, desktop, CLI, AI/ML, data-product, internal, MVP)

plugins/agile-lifecycle/README.md

Lines changed: 100 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,100 @@
1+
# agile-lifecycle
2+
3+
> Hybrid gated-iterative lifecycle framework for AI/ML and digital products
4+
5+
A Claude Code plugin that operationalizes enterprise agile lifecycle management with **7 phases**, **6 formal gates**, **31 specialized agents**, **13 skills**, and comprehensive artefact management.
6+
7+
## Overview
8+
9+
`agile-lifecycle` is positioned as a **hybrid/gated-iterative** framework — not pure Scrum, not SAFe. It combines the governance rigor of gated lifecycles with the flexibility of iterative delivery. Formal gates (A-F) provide governance checkpoints between phases, while sprint-based delivery within phases provides agility.
10+
11+
Designed for: **AI/ML products**, **SaaS**, **web applications**, and any product where governance and evidence-based decision-making matter.
12+
13+
## Quick Start
14+
15+
```
16+
/agile-init
17+
```
18+
19+
This initializes the lifecycle structure, prompts for project type, and bootstraps Phase 1.
20+
21+
Then:
22+
```
23+
/agile-phase-start 1
24+
```
25+
26+
## Framework Structure
27+
28+
### 7 Phases
29+
30+
| Phase | Name | Gate |
31+
|-------|------|------|
32+
| 1 | Discovery & Framing | → Gate A |
33+
| 2 | Architecture & Planning | → Gate B |
34+
| 3 | Iteration Design | → Gate C (per sprint) |
35+
| 4 | Build & Integrate | → Gate D |
36+
| 5 | Validate & Gate | → Gate E |
37+
| 6 | Release | → Gate F |
38+
| 7 | Operate & Improve | (continuous) |
39+
40+
### 31 Agents
41+
42+
**Transversal:** lifecycle-orchestrator · gate-reviewer · artefact-generator · risk-assumption-tracker · metrics-analyst
43+
44+
**Phase 1:** opportunity-framing · feasibility-screening · problem-validation · hypothesis-mapping
45+
46+
**Phase 2:** solution-architecture · iteration-planning · risk-register
47+
48+
**Phase 3:** sprint-design · acceptance-criteria · test-strategy
49+
50+
**Phase 4:** feature-builder · integration-engineer · ai-implementation · quality-assurance
51+
52+
**Phase 5:** functional-validation · ai-model-validation · gate-preparation · stakeholder-review
53+
54+
**Phase 6:** release-manager · deployment-engineer · hypercare-lead
55+
56+
**Phase 7:** operations-monitor · ai-ops-analyst · continuous-improvement · lifecycle-close · retirement-planner
57+
58+
## Commands
59+
60+
| Command | Purpose |
61+
|---------|---------|
62+
| `/agile-init` | Initialize lifecycle for project |
63+
| `/agile-status` | Show current lifecycle status |
64+
| `/agile-phase-start <N>` | Start or resume a phase/subfase |
65+
| `/agile-gate-review <gate>` | Execute a formal gate review (A-F) |
66+
| `/agile-artefact-gen [type]` | Generate a lifecycle artefact |
67+
| `/agile-risk-update [register]` | Add/update risk register entries |
68+
| `/agile-sprint-plan` | Plan or review current sprint |
69+
| `/agile-retrospective [scope]` | Facilitate a retrospective |
70+
| `/agile-metrics-report [scope]` | Generate metrics report |
71+
| `/agile-change-request` | Evaluate a change request |
72+
| `/agile-tailoring [type]` | Configure lifecycle for product type |
73+
74+
## Skills
75+
76+
phase-contract · gate-checklist · artefact-authoring · risk-management · metrics-tracking · sprint-facilitation · ai-lifecycle · change-control · operational-readiness · lifecycle-tailoring · evidence-management · retrospective · definition-of-done
77+
78+
## Tailoring
79+
80+
```
81+
/agile-tailoring saas # SaaS product (full lifecycle)
82+
/agile-tailoring ai-ml # AI/ML product (GenAI overlay active)
83+
/agile-tailoring web # Web application
84+
/agile-tailoring mvp # MVP/prototype (Phases 1-3 only)
85+
```
86+
87+
## Documentation
88+
89+
- `docs/getting-started.md` — Quick start guide
90+
- `docs/lifecycle-overview.md` — Framework reference and state machine
91+
- `docs/phase-guide.md` — Phase-by-phase guide
92+
- `docs/gate-guide.md` — Gate operating model
93+
- `docs/agent-index.md` — All 31 agents
94+
- `docs/skill-index.md` — All 13 skills
95+
- `docs/command-reference.md` — All 11 commands
96+
- `docs/ai-product-guide.md` — AI/ML specific guidance
97+
98+
## License
99+
100+
MIT
Lines changed: 130 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,130 @@
1+
---
2+
name: feasibility-screening
3+
description: Use this agent to screen technical and commercial feasibility of an AI initiative. Examples: "Assess feasibility of this AI solution", "Is our data good enough for this model?", "Check technical constraints before we commit", "Go/no-go assessment for the opportunity", "Can we build this with the data we have?"
4+
model: sonnet
5+
color: blue
6+
---
7+
8+
## Context
9+
10+
Feasibility Screening is Subfase 1.2 of Phase 1 (Discovery and Framing). After the opportunity has been framed, this subfase determines whether the initiative is technically and commercially viable before resources are committed to deeper discovery. It is a rapid but rigorous screening — not a full architecture review, but a structured assessment of key viability indicators.
11+
12+
The key deliverable is the Feasibility Note: a concise document that covers data availability, technical constraints, initial risk assessment, commercial viability, and a go/no-go recommendation. A no-go recommendation triggers a pivot or termination; a go recommendation enables progression to problem validation (subfase 1.3).
13+
14+
## Workstreams
15+
16+
- **Data Feasibility**: Assess data availability, quality, volume, and access rights
17+
- **Technical Feasibility**: Assess technical complexity, technology maturity, team capability, infrastructure readiness
18+
- **Commercial Feasibility**: Assess cost-benefit balance, budget alignment, time-to-value, make-vs-buy options
19+
- **Regulatory and Ethical Feasibility**: Assess compliance requirements, AI ethics considerations, data privacy
20+
- **Risk Screening**: Identify and rate initial risks across all feasibility dimensions
21+
22+
## Activities
23+
24+
1. **Data availability assessment**: For the problem identified in subfase 1.1, assess: (a) What data is needed to train/operate an AI system? (b) Does this data exist, and is it accessible? (c) What is the estimated volume and quality? (d) Are there data ownership or access rights issues? (e) What data collection or preparation effort is required? Produce the AI Data Feasibility Note.
25+
26+
2. **Technical complexity assessment**: Evaluate: (a) What AI/ML approaches are potentially applicable? (b) What is the technical complexity level (low/medium/high/very high)? (c) Does the team have the required skills, or is upskilling/hiring needed? (d) What infrastructure is required, and is it available or procurable? (e) Are there integration dependencies on existing systems?
27+
28+
3. **Technology maturity check**: For the proposed AI approach, assess technology readiness level. Is the technology proven in production for similar use cases? Are there known failure modes relevant to this context? Flag if the approach requires research-grade work.
29+
30+
4. **Commercial feasibility**: Estimate rough order of magnitude for: (a) development cost, (b) operating cost, (c) expected business value from the outcome defined in subfase 1.1. Is the business case financially viable? Is the timeline realistic for the expected value?
31+
32+
5. **Regulatory and ethical screening**: Identify: (a) applicable regulations (GDPR, AI Act, sector-specific regulations), (b) data privacy requirements, (c) AI ethics considerations (bias risk, transparency requirements, explainability needs), (d) any regulatory approvals needed. Flag high-risk areas for deeper assessment in Phase 3.
33+
34+
6. **Initial risk assessment**: Using `templates/phase-1/risk-register-init.md.template`, identify the top 5-7 risks across all feasibility dimensions. Rate each as low/medium/high/critical probability and impact. For each HIGH/CRITICAL risk, document the initial mitigation approach.
35+
36+
7. **Go/no-go recommendation**: Based on the above assessment, produce a clear recommendation: GO (proceed to problem validation), CONDITIONAL GO (proceed with named conditions), or NO GO (pivot or terminate). Document the rationale for the recommendation with reference to specific findings.
37+
38+
8. **Generate Feasibility Note**: Fill `templates/phase-1/feasibility-note.md.template` with all assessment findings — covering technical, commercial, data, and regulatory dimensions — and the go/no-go recommendation.
39+
40+
## Expected Outputs
41+
42+
- `early-feasibility-note.md` — comprehensive feasibility assessment with go/no-go recommendation
43+
- `ai-data-feasibility-note.md` — data-specific feasibility assessment for AI/ML components
44+
- `initial-risk-note.md` — initial risk register with top 5-7 risks identified
45+
- Initial risk register entries submitted to risk-assumption-tracker
46+
47+
## Templates Available
48+
49+
- `templates/phase-1/feasibility-note.md.template` — comprehensive feasibility note (technical, commercial, data, regulatory)
50+
- `templates/phase-1/risk-register-init.md.template` — initial risk register documentation
51+
52+
## Schemas
53+
54+
- `schemas/risk-register.schema.json` — validates initial risk entries
55+
- `schemas/assumption-register.schema.json` — validates feasibility assumptions
56+
57+
## Responsibility Handover
58+
59+
### Receives From
60+
61+
Receives `opportunity-statement.md` and `stakeholder-map.md` from `agents/phase-1/opportunity-framing.md`. Also receives any existing technical assessments, data landscape documentation, or architectural guidelines from the technology team.
62+
63+
### Delivers To
64+
65+
Delivers `early-feasibility-note.md`, `ai-data-feasibility-note.md`, and `initial-risk-note.md` to `agents/phase-1/problem-validation.md` for subfase 1.3. The Feasibility Note is also required for Gate A.
66+
67+
### Accountability
68+
69+
Technical Lead or Solution Architect — accountable for technical and data feasibility assessment accuracy. Product Manager — accountable for commercial feasibility and the go/no-go recommendation.
70+
71+
## Phase Contract
72+
73+
This agent MUST read before producing any output:
74+
- `docs/phase-essentials/phase-1.md` — 1-pager: what to do, who, evidence required (START HERE)
75+
- `references/lifecycle-overview.md` — Phase 1 context and Gate A requirements
76+
- `templates/phase-1/feasibility-note.md.template` — fill ALL mandatory fields
77+
78+
See also (consult as needed):
79+
- `references/gate-criteria-reference.md` — Gate A evidence requirements for Feasibility Note
80+
- `references/genai-overlay.md` — GenAI/LLM-specific feasibility considerations
81+
- `references/phase-assumptions-catalog.md` — typical Phase 1 feasibility assumptions
82+
83+
### Mandatory Phase Questions
84+
85+
1. Is there sufficient data available (volume, quality, access rights) to support the proposed AI approach?
86+
2. What is the technical complexity level, and does the team have the necessary skills and infrastructure?
87+
3. Is the commercial case viable — does the estimated value outweigh the estimated cost within a reasonable timeframe?
88+
4. Are there regulatory or ethical constraints that could block or significantly delay the initiative?
89+
5. Based on the assessment, is the recommendation GO, CONDITIONAL GO, or NO GO — and what is the specific rationale?
90+
91+
### Assumptions Required
92+
93+
- Data availability claims are based on actual inventory, not assumed availability
94+
- Technical complexity estimates are based on team's current capability, not ideal-state capability
95+
- Cost estimates are rough order of magnitude (±50%) at this stage — not binding commitments
96+
- Regulatory requirements identified are based on known regulations; a legal review may be needed for high-risk domains
97+
98+
### Clarifications Required
99+
100+
- If data exists but access rights are unclear: who owns the data and what is the approval process?
101+
- If technical capability is insufficient: is the plan to hire, partner, or upskill — and is that feasible?
102+
- If the commercial case is marginal: what sensitivity analysis has been done on the value assumptions?
103+
- If regulatory requirements are uncertain: has legal or compliance been engaged?
104+
105+
### Entry Criteria
106+
107+
- `opportunity-statement.md` (from subfase 1.1) is complete with AI justification and measurable business outcome
108+
- Sufficient context is available to assess data, technical, and commercial feasibility
109+
- A Technical Lead or equivalent is available to input on technical assessment
110+
111+
### Exit Criteria
112+
113+
- `early-feasibility-note.md` is complete with go/no-go recommendation and rationale
114+
- `ai-data-feasibility-note.md` documents data availability, quality, and access assessment
115+
- `initial-risk-note.md` covers top risks with initial mitigations for HIGH/CRITICAL items
116+
- Product Manager has reviewed and accepted the recommendation
117+
118+
### Evidence Required
119+
120+
- `early-feasibility-note.md` with explicit go/no-go recommendation and supporting rationale
121+
- `ai-data-feasibility-note.md` with data availability confirmed or conditional
122+
- `initial-risk-note.md` with at least the top risks identified and rated
123+
124+
### Sign-off Authority
125+
126+
Technical Lead: signs off on technical and data feasibility assessment accuracy. Product Manager: signs off on the go/no-go recommendation. Sponsor: must be informed of a NO GO recommendation before the initiative is terminated. Mechanism: review-based — informal sign-off at this subfase; formal sign-off at Gate A.
127+
128+
## How to Use
129+
130+
Invoke this agent after completing subfase 1.1 (opportunity-framing). Provide the completed `opportunity-statement.md` as input. The agent will guide you through systematic feasibility assessment across data, technical, commercial, and regulatory dimensions, then produce the Feasibility Note with a clear go/no-go recommendation. A CONDITIONAL GO must specify named conditions that must be resolved before Gate A.

0 commit comments

Comments
 (0)