review-checklists
Quality review checklists for AL solution plans, code implementations, and test suites. Auto-load when reviewing agent output before presenting to user.
What this skill does
# Review Checklists
Use these checklists when reviewing output from planning, coding, or testing before presenting results to the user. Every piece of agent output must pass the relevant checklist. If it does not, send it back with specific feedback before the user ever sees it.
## Review Process
1. **Read the output** carefully and completely.
2. **Check against the relevant checklist** below.
3. **If issues exist**: send the output back to the originating step with specific, actionable feedback. Do not present flawed work to the user.
4. **If quality is good**: synthesize the results and present them to the user clearly.
---
## Checklist: Solution Plans
Before presenting a solution plan to the user, verify:
- [ ] **Addresses all requirements** -- every stated requirement has a corresponding design element
- [ ] **BC integration is sound** -- uses standard BC patterns (posting routines, event subscribers, standard tables) rather than reinventing platform functionality
- [ ] **Edge cases identified** -- plan acknowledges boundary conditions, error scenarios, and concurrent usage
- [ ] **Follows project patterns** -- consistent with existing codebase conventions (naming, architecture, module boundaries)
- [ ] **Object IDs specified** -- all new objects have assigned IDs that do not conflict with existing ranges
- [ ] **No over-engineering** -- plan solves what was asked, not a hypothetical future problem
- [ ] **Dependencies noted** -- any required base app or third-party dependencies are called out
---
## Checklist: Code Implementations
Before presenting code to the user, verify:
- [ ] **Matches the plan** -- implementation follows the agreed solution design; deviations are explained
- [ ] **AL coding standards met** -- PascalCase, namespaces, affix rules, SetLoadFields, FieldCaption errors, DataClassification, ApplicationArea (see al-coding-standards skill)
- [ ] **Consistent naming** -- identifiers follow the same conventions throughout; no mix of styles
- [ ] **Compiles cleanly** -- no obvious syntax errors, missing semicolons, undeclared variables, or type mismatches
- [ ] **Minimal changes** -- only the code necessary to fulfill the requirement; no unrelated refactoring
- [ ] **No empty triggers** -- all trigger bodies contain code or are removed
- [ ] **XML documentation** -- public procedures have `/// <summary>` comments
- [ ] **Events raised** -- meaningful extension points have IntegrationEvents
- [ ] **Error messages use FieldCaption** -- no hardcoded field names in error strings
---
## Checklist: Test Suites
Before presenting tests to the user, verify:
- [ ] **Main scenarios covered** -- happy path for each primary use case is tested
- [ ] **Edge cases covered** -- boundary values, empty inputs, invalid data, permission scenarios
- [ ] **bc-test passes** -- tests run successfully (or failures are explained and tracked)
- [ ] **Meaningful assertions** -- each test asserts specific expected outcomes, not just "no error occurred"
- [ ] **No object ID conflicts** -- test codeunit and helper object IDs are in the designated test range
- [ ] **Test isolation** -- tests do not depend on execution order or shared mutable state
- [ ] **Readable test names** -- procedure names describe the scenario and expected outcome
---
## Review Attitude: Challenge, Don't Rubber-Stamp
### Wrong: Rubber-stamping
```
Agent produces code → Reviewer glances at it → "Looks good" → Present to user
Result: User finds a missing SetLoadFields, a prefix affix on a table extension
field, and a hardcoded field name in an error message. Trust erodes.
```
### Right: Challenging
```
Agent produces code → Reviewer checks against checklist → Finds:
1. Line 42: SetLoadFields missing before FindSet
2. Line 67: Field "ABC Status" uses prefix affix, should be "Status ABC"
3. Line 89: Error('Status must be Open') should use FieldCaption
→ Sends specific feedback back to the coding step:
"Fix these 3 issues: (1) Add SetLoadFields before the FindSet on line 42,
loading No. and Status. (2) Rename 'ABC Status' to 'Status ABC' -- suffix
only. (3) Replace hardcoded 'Status' with FieldCaption(Status) in the
error on line 89."
→ Agent fixes → Reviewer re-checks → Clean → Present to user
Result: User receives polished, standards-compliant code on the first delivery.
```
The goal is to catch every issue before the user does. A review that finds nothing wrong should be the exception, not the default.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.