Agent Skills: Documentation Enhancement

Codex compatibility note:

• Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
• Prefer the plan-hard skill for planning guidance in this Codex mirror.
• Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
• User-question prompts mean to ask the user directly in Codex.
• Ignore Claude-specific mode-switch instructions when they appear.
• Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
• Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
• Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
• For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
• If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (No Hooks)

Codex does not receive Claude hook-based doc injection. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

• docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
• docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
• docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Situation-based docs:

• Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
• Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
• Spec/test-case planning or TC mapping: feature-docs-reference.md
• Integration test implementation/review: integration-test-reference.md
• E2E test implementation/review: e2e-test-reference.md
• Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

Quick Summary

Goal: Enhance code documentation, API docs, README files, and technical writing with verified accuracy.

Workflow:

1. Analysis — Build knowledge model: discover APIs, components, structure, documentation gaps
2. Plan — Generate detailed documentation plan with priorities and outline
3. Approval Gate — Present plan for explicit user approval before writing
4. Execute — Write documentation following anti-hallucination protocols

Key Rules:

• Never proceed without explicit user approval of the documentation plan
• Verify every documented feature against actual code (no assumptions)
• For business feature docs, use feature-docs skill instead
• Include practical examples and copy-pasteable code snippets

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Skill Variant: Use this skill for interactive documentation tasks including code docs AND README files.

Disambiguation

• For business feature docs → use feature-docs
• This skill covers code documentation and README files

Documentation Enhancement

You are to operate as an expert technical writer and software documentation specialist to enhance documentation.

IMPORTANT: Always thinks hard, plan step by step to-do list first before execute. Always remember to-do list, never compact or summary it when memory context limit reach. Always preserve and carry your to-do list through every operation.

README Structure Template

Use this structure when creating or improving README files:

# Project Name

Brief description of the project.

## Table of Contents

- [Features](#features)
- [Prerequisites](#prerequisites)
- [Installation](#installation)
- [Configuration](#configuration)
- [Usage](#usage)
- [Development](#development)
- [Testing](#testing)
- [Deployment](#deployment)
- [Troubleshooting](#troubleshooting)
- [Contributing](#contributing)
- [License](#license)

## Features

- Feature 1
- Feature 2

## Prerequisites

- Node.js >= 18
- .NET 9 SDK

## Installation

```bash
# Clone the repository
git clone [url]

# Install dependencies
npm install
dotnet restore
```

## Configuration

[Configuration details]

## Usage

[Usage examples]

## Development

[Development setup]

## Testing

[Testing instructions]

## Troubleshooting

[Common issues and solutions]

PHASE 1: EXTERNAL MEMORY-DRIVEN DOCUMENTATION ANALYSIS

Build a structured knowledge model in .ai/workspace/analysis/[task-name].analysis.md.

PHASE 1A: INITIALIZATION AND DISCOVERY

1. Initialize the analysis file with standard headings
2. Discovery searches for all related files

DOCUMENTATION-SPECIFIC DISCOVERY

DOCUMENTATION_COMPLETENESS_DISCOVERY: Focus on documentation-relevant patterns:

1. API Documentation Analysis: Find API endpoints and identify missing documentation. Document under ## API Documentation.

2. Component Documentation Analysis: Find public classes/methods and identify complex logic needing explanation. Document under ## Component Documentation.

3. Basic Structure Analysis: Find key configuration files and main application flows. Document under ## Structure Documentation.

PROJECT_OVERVIEW_DISCOVERY (README-specific): Focus on README-relevant patterns:

1. Project Structure Analysis: Find entry points, map key directories, identify technologies
2. Feature Discovery: Find user-facing features and map API endpoints
3. Setup Requirements Analysis: Find package files, map dependencies, identify configuration needs

PHASE 1B: SYSTEMATIC FILE ANALYSIS FOR DOCUMENTATION

IMPORTANT: Must do with todo list.

For each file, document in ## Knowledge Graph:

• Standard fields plus documentation-specific:
• documentationGaps: Missing or incomplete documentation
• complexityLevel: How difficult to understand (1-10)
• userFacingFeatures: Features needing user documentation
• developerNotes: Technical details needing developer docs
• exampleRequirements: Code examples or usage scenarios needed
• apiDocumentationNeeds: API endpoints requiring documentation
• configurationOptions: Configuration parameters needing explanation
• troubleshootingAreas: Common issues requiring troubleshooting docs

README-specific fields (when analyzing for README documentation):

| Field | Description | | -------------------- | ------------------------------------------ | | readmeRelevance | How component should be represented (1-10) | | userImpact | How component affects end users | | setupRequirements | Prerequisites for this component | | configurationNeeds | Configuration required | | featureDescription | User-facing features provided | | exampleUsage | Usage examples for README | | projectContext | How it fits into overall project |

PHASE 1C: OVERALL ANALYSIS

Write comprehensive summary showing:

• Complete end-to-end workflows discovered
• Documentation gaps identified
• Priority areas for documentation
• Key features and capabilities (README)
• Setup and configuration requirements (README)

PHASE 2: DOCUMENTATION PLAN GENERATION

Generate detailed documentation plan under ## Documentation Plan:

• Focus on completeness
• Ensure clarity
• Include examples
• Maintain consistency

For README plans, generate a detailed outline covering: Project Overview, Installation, Usage, Configuration, Development guidelines.

PHASE 3: APPROVAL GATE

CRITICAL: Present documentation plan for explicit approval. DO NOT proceed without it.

PHASE 4: DOCUMENTATION EXECUTION

Once approved, execute the plan using all DOCUMENTATION_SAFEGUARDS.

SUCCESS VALIDATION

Verify documentation is:

• Accurate (matches actual code)
• Complete (covers all public APIs)
• Helpful (includes examples)

README-specific checks:

• [ ] Accurate: All instructions work
• [ ] Comprehensive: Covers all setup needs
• [ ] Helpful: New users can get started
• [ ] Tested: Commands verified to work

Document under ## Documentation Validation.

Documentation Guidelines

• Accuracy-first approach: Verify every documented feature with actual code
• User-focused content: Organize documentation based on user needs
• Example-driven documentation: Include practical examples and usage scenarios
• Consistency maintenance: Follow established documentation patterns
• No assumptions: Always verify behavior before documenting

README Guidelines

• User-first approach: Organize content for new users; start with what the project does and why; provide clear getting-started path
• Verified instructions: Test all setup and installation instructions; include exact commands that work; document version requirements
• Practical examples: Include working examples users can follow; show common use cases; provide copy-pasteable code snippets
• No assumptions: Don't assume user knowledge; explain acronyms and domain terms; link to prerequisite documentation

⚠️ MUST ATTENTION READ: CLAUDE.md for code pattern examples (backend/frontend) when writing code documentation. See .claude/docs/ for existing documentation structure.

Anti-Hallucination Protocols

ASSUMPTION_VALIDATION_CHECKPOINT

Before every major operation:

1. "What assumptions am I making about [X]?"
2. "Have I verified this with actual code evidence?"

EVIDENCE_CHAIN_VALIDATION

Before claiming any relationship:

• "I believe X calls Y because..." → show actual code
• "This follows pattern Z because..." → cite specific examples

TOOL_EFFICIENCY_PROTOCOL

• Batch multiple Grep searches into single calls with OR patterns
• Use parallel Read operations for related files

CONTEXT_ANCHOR_SYSTEM

Every 10 operations:

1. Re-read the original task description
2. Verify the current operation aligns with original goals

Related

• feature-docs
• changelog
• release-notes

Task Planning Notes (MUST ATTENTION FOLLOW)

• Always plan and break work into many small todo tasks
• Always add a final review todo task to verify work quality and identify fixes/enhancements

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

AI Mistake Prevention — Failure modes to avoid on every task:

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Evidence-Based Reasoning — Speculation is FORBIDDEN. Every claim needs proof.

1. Cite file:line, grep results, or framework docs for EVERY claim
2. Declare confidence: >80% act freely, 60-80% verify first, <60% DO NOT recommend
3. Cross-service validation required for architectural changes
4. "I don't have enough evidence" is valid and expected output

BLOCKED until: - [ ] Evidence file path (file:line) - [ ] Grep search performed - [ ] 3+ similar patterns found - [ ] Confidence level stated

Forbidden without proof: "obviously", "I think", "should be", "probably", "this is because" If incomplete → output: "Insufficient evidence. Verified: [...]. Not verified: [...]."

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim. Confidence >80% to act, <60% = do NOT recommend. <!-- /SYNC:evidence-based-reasoning:reminder -->

MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

Closing Reminders

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting:

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

1. DETECT: Match prompt against workflow catalog
2. ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
3. ASK (REQUIRED FORMAT): Use a direct user question with this structure:
   • Question: "Which workflow do you want to activate?"
   • Option 1: "Activate [BestMatch Workflow] (Recommended)"
   • Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
4. ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
5. CREATE TASKS: task tracking for ALL workflow steps
6. EXECUTE: Follow each step in sequence [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows.

Learned Lessons

Lessons Learned

[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.

Quick Summary

Goal: Prevent recurrence of known failure patterns — debugging, architecture, naming, AI orchestration, environment.

Top Rules (apply always):

• MUST ATTENTION verify ALL preconditions (config, env, DB names, DI regs) BEFORE code-layer hypothesis
• MUST ATTENTION fix responsible layer — NEVER patch symptom sites with caller-specific defensive code
• MUST ATTENTION use ExecuteInjectScopedAsync for parallel async + repo/UoW — NEVER ExecuteUowTask
• MUST ATTENTION name by PURPOSE not CONTENT — adding member forces rename = abstraction broken
• MUST ATTENTION persist sub-agent findings incrementally after each file — NEVER batch at end
• MUST ATTENTION Windows bash: verify Python alias (where python/where py) — NEVER assume python/python3 resolves

Debugging & Root Cause Reasoning

• [2026-04-11] Holistic-first: verify environment before code. Failure → list ALL preconditions (config, env vars, DB names, endpoints, DI regs, credentials, permissions, data prerequisites) → verify each via evidence (grep/cat/query) BEFORE code-layer hypothesis. Worst rabbit holes: diving nearest layer while bug sits elsewhere — e.g., hours debugging "sync timeout", real cause: test appsettings pointing wrong DB. ALWAYS cheapest check first.
• [2026-04-01] Ask "whose responsibility?" before fixing. Trace: bug caller (wrong data) or callee (wrong handling)? Fix responsible layer — NEVER patch symptom site masking real issue.
• [2026-04-01] Trace data lifecycle, not error site. Follow data: creation → transformation → consumption. Bug usually where data created wrong, not consumed.
• [2026-04-01] Code caller-agnostic. Functions/handlers/consumers don't know who invokes them. Comments/guards/messages describe business intent — NEVER reference specific callers (tests, seeders, scripts).

Architecture Invariants

• [2026-05-09] User name materialization MUST ATTENTION go through User.UpdateName(firstName, middleName, lastName). Domain method (src/Services/bravoTALENTS/Employee.Domain/AggregatesModel/User.cs:202-209) recomputes FullName as single source of truth. Three sites still manually patch user.FullName = user.GetFullName() after assigning name fields — src/Services/bravoTALENTS/Employee.Application/Factories/UserFactory.cs:50, src/Services/bravoSURVEYS/LearningPlatform.Application/ApplyPlatform/MessageBus/Consumers/AccountUserDeletedEventBusConsumer.cs:102, src/Services/bravoINSIGHTS/Analyze/Analyze.Application/MessageBus/Consumers/AccountUserDeletedEventBusConsumer.cs:66. Next time touching any: replace manual patch with user.UpdateName(...) to maintain invariant.
• [2026-03-31] ParallelAsync + repo/UoW MUST ATTENTION use ExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) — parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).
• [2026-03-31] Bus message naming MUST ATTENTION include service name prefix — core services NEVER consume feature events. Prefix declares schema ownership (AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) leaders. Feature services (Growth, Talents) sending to core MUST ATTENTION use {CoreServiceName}...RequestBusMessage — NEVER define own event for core to consume.

Naming & Abstraction

• [2026-04-12] Name PURPOSE not CONTENT — "OrXxx" anti-pattern. HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what guards. Add role → rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad → rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine behavioral idioms (FirstOrDefault, SuccessOrThrow) — expresses HAPPENS, not membership.

Environment & Tooling

• [2026-04-20] Windows bash: NEVER assume python/python3 resolves — verify alias first. Python may not be bash PATH under those names. Check: where python / where py. ALWAYS prefer py (Windows Python Launcher) one-liners, node if JS alternative exists.

Test-specific lessons → docs/project-reference/integration-test-reference.md Lessons Learned section. Production-code anti-patterns → docs/project-reference/backend-patterns-reference.md Anti-Patterns section. Generic debugging/refactoring reminders → System Lessons .claude/hooks/lib/prompt-injections.cjs.

Closing Reminders

• IMPORTANT MUST ATTENTION holistic-first: verify ALL preconditions (config, env, DB names, endpoints, DI regs) BEFORE code-layer hypothesis — cheapest check first
• IMPORTANT MUST ATTENTION fix responsible layer — NEVER patch symptom site; trace caller (wrong data) vs callee (wrong handling), fix root owner
• IMPORTANT MUST ATTENTION parallel async + repo/UoW → ALWAYS ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption)
• IMPORTANT MUST ATTENTION bus message prefix = schema ownership; feature services NEVER define events for core services — use {CoreServiceName}...RequestBusMessage
• IMPORTANT MUST ATTENTION name by PURPOSE — adding/removing member forces rename = broken abstraction
• IMPORTANT MUST ATTENTION sub-agents MUST write findings after each file/section — NEVER batch all findings into one final write
• IMPORTANT MUST ATTENTION Windows bash: NEVER assume python/python3 resolves — run where python/where py first, use py launcher or node
• IMPORTANT MUST ATTENTION every claim needs file:line evidence — confidence >80% to act, NEVER speculate

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
6. Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
7. BOTH gates pass → ask user to run $learn. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.