Skill Estimation logo

Skill Estimation

Community
javiarmesto
skill-estimation

AL project estimation for Business Central. Use when estimating development effort, creating cost models, SWOT analysis, or structuring project proposals.

Overview

Publisherjaviarmesto
RepositoryALDC-AL-Development-Collection
Skill nameskill-estimation
Stars
115
Forks
37
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by javiarmesto on GitHub. Read the source before you install it.

Installation

Install the Skill Estimation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/.claude/skills/skill-estimation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git /tmp/ALDC-AL-Development-Collection
mkdir -p .claude/skills
cp -r /tmp/ALDC-AL-Development-Collection/.claude/skills/skill-estimation .claude/skills/skill-estimation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Estimation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Estimation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Estimation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill: AL Project Estimation

Purpose

Estimate AL/Business Central projects: complexity scoring, PERT 3-point estimation, SWOT/DAFO risk analysis, cost breakdown by phase, resource allocation, and structured presales documentation.

When to Load

This skill should be loaded when:

  • A new BC/AL project needs time and cost estimation
  • A feasibility assessment or SWOT analysis is required before commitment
  • A presales proposal or technical assessment document is being created
  • Resource allocation and team composition need to be defined
  • A project plan with milestones and payment schedule is needed

Core Patterns

Pattern 1: Intake Questions (Mandatory)

Before any estimation, gather these parameters:

markdown
## Project Intake — Required Information

### 1. Project Identity
- Project name (will be used for folder structure)
- Brief description: What problem does it solve?

### 2. Cost Parameters (MANDATORY)
- Hourly rate (e.g., €75/hour, $100/hour)
- Currency (EUR, USD, GBP)
- Contingency buffer: Yes/No (default 15-20%)
- Risk buffer: Low (10%), Medium (20%), High (30%)

### 3. Technical Context
- Target BC version: SaaS, On-Premise, or both?
- Target delivery date
- Existing codebase? (repository URL or workspace path)
- Reference repositories for similar functionality?

### 4. Team (optional)
- Available developers: Junior, Mid, Senior?
- BC experience level: New, Experienced, Expert?

PAUSE — do NOT proceed without cost parameters. Estimation without rates is meaningless.

Pattern 2: Complexity Scoring

Score each dimension 1-10 to derive overall project complexity:

markdown
## Complexity Assessment

| Dimension | Score (1-10) | Criteria |
|---|---|---|
| Data Model | /10 | Tables, relations, migration needs |
| Business Logic | /10 | Codeunits, validations, calculations |
| UI Complexity | /10 | Pages, customizations, RoleCenter |
| Integrations | /10 | External APIs, events, webhooks |
| Reporting | /10 | Reports, queries, analytics |
| Security | /10 | Permissions, data sensitivity, audit |
| Testing | /10 | Test coverage needed, edge cases |
| Migration/Upgrade | /10 | Data migration, version compatibility |

**Overall Complexity**: (sum / 80) × 10 = X/10

Object count estimation:

Object TypeLow ComplexityMediumHigh
Table2-4 hrs4-8 hrs8-16 hrs
Page (Card/List)2-4 hrs4-8 hrs8-16 hrs
Page (Document)4-8 hrs8-16 hrs16-32 hrs
Codeunit2-8 hrs8-16 hrs16-40 hrs
Report4-8 hrs8-16 hrs16-32 hrs
Integration8-16 hrs16-32 hrs32-80 hrs

Pattern 3: PERT 3-Point Estimation

Use the Program Evaluation and Review Technique for each task:

markdown
## PERT Formula

E = (O + 4M + P) / 6

Where:
- O = Optimistic (best case, everything goes right)
- M = Most Likely (normal case, typical obstacles)
- P = Pessimistic (worst case, major obstacles)
- E = Expected duration

Apply per development phase:

markdown
## Phase Breakdown

### Phase 1: Analysis & Design
| Task | O (hrs) | M (hrs) | P (hrs) | E (hrs) |
|---|---|---|---|---|
| Requirements analysis | 8 | 16 | 24 | 16 |
| Technical design | 8 | 12 | 20 | 13 |
| Architecture review | 4 | 8 | 12 | 8 |
| **Subtotal** | **20** | **36** | **56** | **37** |

### Phase 2: Development
| Task | O (hrs) | M (hrs) | P (hrs) | E (hrs) |
|---|---|---|---|---|
| Tables & data model | X | X | X | X |
| Pages & UI | X | X | X | X |
| Business logic | X | X | X | X |
| Integrations | X | X | X | X |
| **Subtotal** | **X** | **X** | **X** | **X** |

### Phase 3: Testing & QA
| Task | O (hrs) | M (hrs) | P (hrs) | E (hrs) |
|---|---|---|---|---|
| Unit tests | X | X | X | X |
| Integration tests | X | X | X | X |
| UAT support | X | X | X | X |
| Bug fixes | X | X | X | X |
| **Subtotal** | **X** | **X** | **X** | **X** |

### Phase 4: Deployment & Documentation
| Task | O (hrs) | M (hrs) | P (hrs) | E (hrs) |
|---|---|---|---|---|
| Technical documentation | X | X | X | X |
| Training materials | X | X | X | X |
| Deployment | X | X | X | X |
| Post-go-live support | X | X | X | X |
| **Subtotal** | **X** | **X** | **X** | **X** |

Pattern 4: SWOT/DAFO Analysis

Structured risk and opportunity assessment:

markdown
## SWOT Analysis

### Strengths (Internal Positive)
| ID | Strength | Impact |
|---|---|---|
| S1 | [e.g., Team has BC experience] | High/Medium/Low |

### Opportunities (External Positive)
| ID | Opportunity | Impact |
|---|---|---|
| O1 | [e.g., Standard BC API available] | High/Medium/Low |

### Weaknesses (Internal Negative)
| ID | Weakness | Impact | Mitigation |
|---|---|---|---|
| W1 | [e.g., No existing test suite] | High | Implement TDD from start |

### Threats (External Negative)
| ID | Threat | Probability | Impact | Mitigation |
|---|---|---|---|---|
| T1 | [e.g., BC version upgrade mid-project] | Medium | High | Pin BC version |

## Feasibility Score

| Criterion | Score (1-10) |
|---|---|
| Technical Feasibility | /10 |
| Resource Feasibility | /10 |
| Timeline Feasibility | /10 |
| Economic Feasibility | /10 |
| **Overall** | **/10** |

### Recommendation
- [ ] **GO** — Project viable, proceed
- [ ] **CAUTION** — Viable with conditions
- [ ] **NO-GO** — Not recommended currently

Pattern 5: Cost Summary and Payment Milestones

Consolidate estimation into a financial summary:

markdown
## Cost Summary

| Concept | Hours | Rate | Cost |
|---|---|---|---|
| Analysis & Design | X | [RATE] | [TOTAL] |
| Development | X | [RATE] | [TOTAL] |
| Testing & QA | X | [RATE] | [TOTAL] |
| Deployment & Docs | X | [RATE] | [TOTAL] |
| **Subtotal** | **X** | | **[TOTAL]** |
| Contingency ([%]%) | X | | [TOTAL] |
| Risk Buffer ([%]%) | X | | [TOTAL] |
| **TOTAL** | **X** | | **[CURRENCY] [TOTAL]** |

## Payment Milestones

| Milestone | % | Amount | Deliverable |
|---|---|---|---|
| Project Start | 20% | [X] | SOW signed, project plan |
| Design Approved | 20% | [X] | Architecture approved |
| Development Complete | 30% | [X] | Code delivered, tests pass |
| UAT Approved | 20% | [X] | User acceptance sign-off |
| Go-Live | 10% | [X] | Production deployment |

Workflow

Step 1: Intake

  1. Ask mandatory intake questions (Pattern 1)
  2. Confirm cost parameters — do NOT skip this
  3. If reference repositories provided, analyze them for scope comparison

Step 2: Analyze

  1. Score complexity dimensions (Pattern 2)
  2. Count estimated objects (tables, pages, codeunits, reports)
  3. Identify integration points and external dependencies
  4. If existing codebase, use al_search_objects to measure current scope

Step 3: Estimate

  1. Apply PERT 3-point estimation per phase (Pattern 3)
  2. Use complexity-based hour ranges for object estimation
  3. Apply standard ratios:
    • Testing = 30-40% of development
    • Documentation = 10-15% of total
    • Integration = typically underestimated by 50% — adjust accordingly
    • Data migration = 15-20% of total (if applicable)
    • BC version testing = 5-10% for compatibility

Step 4: Risk Assessment

  1. Conduct SWOT analysis (Pattern 4)
  2. Calculate feasibility score
  3. Provide clear GO / CAUTION / NO-GO recommendation

Step 5: Deliver Proposal

  1. Create cost summary with payment milestones (Pattern 5)
  2. Define resource allocation (roles, FTE, duration)
  3. Compile all sections into presales documentation
  4. Store in Technical_PreSales/{project-slug}/ folder structure

PAUSE — present proposal for stakeholder review before commitment.

Estimation Guidelines

RuleGuideline
Testing effortAlways 30-40% of development hours
DocumentationNever skip — 10-15% of total hours
Integration complexityUsually underestimated — add 50% buffer
Data migrationAdd if mentioned — 15-20% of total
BC version testingAdd 5-10% for compatibility verification
Training8-16 hours per user group
Contingency15-20% standard, 25-30% for high uncertainty

References

Constraints

  • This skill covers project estimation, risk analysis, and presales documentation
  • Do NOT estimate without cost parameters (hourly rate, currency) — ask first
  • Do NOT build, compile, or deploy code — estimation only
  • Do NOT modify production source code — analysis and documentation only
  • Do NOT skip the SWOT analysis for any project — risk awareness is mandatory
  • Architecture design → al-architect agent | Technical specifications → al-spec.create workflow | Implementation → al-conductor agent

Frequently asked questions

What does the Skill Estimation AI skill do?

AL project estimation for Business Central. Use when estimating development effort, creating cost models, SWOT analysis, or structuring project proposals.

Why use Skill Estimation on TypingMind?

Because you install it once and use it with any model. Skill Estimation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Estimation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/.claude/skills/skill-estimation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Skill Estimation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Estimation?

As many as you like. As long as a model supports skills, you can use Skill Estimation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Estimation AI skill free?

Yes. It is published on GitHub by javiarmesto under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇