with one click
idea
// [Project Management] Use when capturing new ideas, feature requests, or concepts for future refinement.
// [Project Management] Use when capturing new ideas, feature requests, or concepts for future refinement.
[HINT] Download the complete skill directory including SKILL.md and all related files
| name | idea |
| description | [Project Management] Use when capturing new ideas, feature requests, or concepts for future refinement. |
Codex compatibility note:
- Invoke repository skills with
$skill-namein Codex; this mirrored copy rewrites legacy Claude/skill-namereferences.- Prefer the
plan-hardskill 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_agentsubagent(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 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-patterns-reference.md, domain-entities-reference.md, project-structure-reference.mdfrontend-patterns-reference.md, scss-styling-guide.md, design-system/README.mdfeature-docs-reference.mdintegration-test-reference.mde2e-test-reference.mdcode-review-rules.md plus domain docs above based on changed filesDo not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.
[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval. [BLOCKING] Before each step or sub-skill call, update task tracking: set
in_progresswhen step starts, setcompletedwhen step ends. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.
Goal: Capture raw product ideas as structured backlog artifacts with project module context.
MANDATORY IMPORTANT MUST ATTENTION task tracking task to READ project-specific reference doc:
project-structure-reference.mdโ project patterns and structure. Not found โ search: project documentation, coding standards, architecture docs.
Workflow:
IDEA-YYMMDD-NNN) + draft status$refine for PBI creationKey Rules:
team-artifacts/ideas/{YYMMDD}-{role}-idea-{slug}.mdt_shirt_size (XS/S/M/L/XL) in artifact for early sizingAuto-detected: No codebase found (no
src/,app/,lib/,server/,packages/dirs; nopackage.json/*.sln/go.mod; noproject-config.json) โ greenfield mode. Planning artifacts (docs/,plans/,.claude/) don't count โ project must have actual code dirs with content.
When greenfield detected:
project-structure-reference.md read (won't exist).claude/docs/team-artifacts/templates/idea-template.mdIDEA-{YYMMDD}-{NNN} (sequential)draftDynamic Discovery:
Glob("docs/business-features/*/README.md")| Scenario | Action |
|---|---|
| Clear match | Auto-detect โ NEVER show confidence levels |
| Ambiguous / no match | Prompt: "Which project module?" + Glob results + "Cross-cutting/Infrastructure" |
| 2+ modules detected | Load ALL modules, add all to related_features |
If module detected:
docs/business-features/{module}/README.md (first 200 lines)module: {detected_module}, related_features: [Feature1, Feature2]Token Budget: Target 8-12K tokens total.
team-artifacts/ideas/{YYMMDD}-{role}-idea-{slug}.mdUse a direct user question โ 3-5 structured questions. Each MUST ATTENTION have 2-4 options with one marked "(Recommended)".
| Category | Purpose | Example |
|---|---|---|
| Problem Clarity | Distinguish problem from solution | "What problem does this solve?" + options |
| User Persona | Identify primary user | "Who benefits most?" + role options |
| Scope | MVP vs full vision | "What's smallest valuable version?" |
| Testability | Define done? | "How would you verify this works?" |
| Impact | Business value sizing | "How many users/processes affected?" |
| Constraints | Known blockers | "Any technical/business constraints?" |
| Scale | Expected load/growth | "How many users/transactions expected?" |
Greenfield: NEVER include tech stack questions. Focus on business problem, users, scale, constraints.
Testability Question (ALWAYS include): "How would you verify this feature works correctly?" โ Options: manual test steps, automated test criteria, metric thresholds.
Document all answers under ## Discovery Interview.
a direct user question โ 2-3 validation questions:
| Category | Example Question |
|---|---|
| Problem | "Is the problem statement clear and user-focused?" |
| Value | "What's the expected business value or user benefit?" |
| Scope | "Any scope boundaries to clarify now?" |
| Stakeholders | "Who else should review this idea?" |
Document under ## Validation Summary. Update artifact based on answers.
Validation Output Format:
## Validation Summary
**Validated:** {date}
### Confirmed
- {decision}: {user choice}
### Action Items
- [ ] {follow-up if any}
a direct user question after capture:
$refine โ Refine into PBI (Recommended)$tdd-spec โ Jump straight to test spec$plan-hard โ Start implementation planningOutput: "Idea captured! To refine into a PBI, run: $refine {filename}"
Module detected: "Module context from {module} will be used during refinement."
## Domain Context (Project Features)
### Module
{module_name}
### Related Features
- {Feature1} - [docs link]
- {Feature2} - [docs link]
### Domain Entities
- **Primary:** {Entity1}, {Entity2}
- **Related:** {Entity3}
### Existing Business Rules
- BR-{MOD}-XXX: {Brief description}
## UI Sketch
### Layout
{Rough ASCII wireframe โ see UI wireframe protocol}
### Key Components
- **{Component}** โ {purpose} _(tier: common | domain-shared | page/app)_
Search existing libs before proposing new components. Backend-only idea:
## UI SketchโN/A โ Backend-only change. No UI affected.
$idea "Dark mode toggle for settings"
# Creates: team-artifacts/ideas/260119-po-idea-dark-mode-toggle.md
$idea "Add goal progress tracking notification"
# Creates with module context: team-artifacts/ideas/260119-po-idea-goal-progress-notification.md
MANDATORY IMPORTANT MUST ATTENTION โ NO EXCEPTIONS: Not already in workflow โ MUST ATTENTION use a direct user question:
- Activate
idea-to-pbiworkflow (Recommended) โ idea โ refine โ refine-review โ story โ story-review โ prioritize- Execute
$ideadirectly โ run standalone
MANDATORY IMPORTANT MUST ATTENTION โ NO EXCEPTIONS after completing skill, use a direct user question:
[IMPORTANT] task tracking break ALL work into small tasks BEFORE starting โ including tasks each file read. Simple tasks: AI MUST ATTENTION ask user whether to skip.
External Memory: Complex/lengthy work (research, analysis, scan, review) โ write intermediate findings to
plans/reports/โ prevents context loss, serves as deliverable.
Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION โ every claim, finding, recommendation requires
file:lineproof or traced evidence, confidence percentage (>80% act, <80% verify first).
UI Wireframe โ Process visual design input (Figma URLs, screenshots, wireframes) via appropriate tool BEFORE creating wireframes. Use box-drawing ASCII characters for spatial layout. Classify every component into exactly ONE tier: Common (cross-app reusable) / Domain-Shared (cross-domain) / Page (single-page). Duplicate UI code = wrong tier. Search existing component libraries before creating new (>=80% match = reuse). Detail level varies by skill (idea=rough, story=full decomposition).
AI Mistake Prevention โ 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 โ 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 โ never patch symptom site. Assume existing values are intentional โ 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 โ 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 โ 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 โ 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.
Critical Thinking Mindset โ Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact โ cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence โ certainty without evidence root of all hallucination.
Sequential Thinking Protocol โ Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.
Trigger when: complex problem decomposition ยท adaptive plans needing revision ยท analysis with course correction ยท unclear/emerging scope ยท multi-step solutions ยท hypothesis-driven debugging ยท cross-cutting trade-off evaluation.
Format (explicit mode โ visible thought trail):
Thought N/M: [aspect]โ one aspect per thought, state assumptions/uncertaintyThought N/M [REVISION of Thought K]: ...โ when prior reasoning invalidated; state Original / Why revised / ImpactThought N/M [BRANCH A from Thought K]: ...โ explore alternative; converge with decision rationaleThought N/M [HYPOTHESIS]: ...then[VERIFICATION]: ...โ test before actingThought N/N [FINAL]โ only when verified, all critical aspects addressed, confidence >80%Mandatory closers: Confidence % stated ยท Assumptions listed ยท Open questions surfaced ยท Next action concrete.
Stop conditions: confidence <80% on any critical decision โ escalate via ask the user directly ยท โฅ3 revisions on same thought โ re-frame the problem ยท branch count >3 โ split into sub-task.
Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).
Deep-dive: see
$sequential-thinkingskill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (api-design, debug, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).
MUST ATTENTION apply critical thinking โ every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
MUST ATTENTION apply sequential-thinking โ multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see $sequential-thinking skill.
MUST ATTENTION apply AI mistake prevention โ holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.
IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval
IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution
IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence
IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses
IMPORTANT MUST ATTENTION task tracking break ALL work into small tasks BEFORE starting IMPORTANT MUST ATTENTION validate all decisions with user via a direct user question โ NEVER auto-decide IMPORTANT MUST ATTENTION Discovery Interview + Validation NEVER optional โ MANDATORY steps IMPORTANT MUST ATTENTION NEVER ask about tech stack in greenfield mode โ defer to business-evaluation phase IMPORTANT MUST ATTENTION auto-detect module silently โ prompt only when ambiguous IMPORTANT MUST ATTENTION add final review task to verify work quality
Anti-Rationalization:
| Evasion | Rebuttal |
|---|---|
| "Idea is simple, skip interview" | NEVER skip โ discovery uncovers hidden constraints |
| "Module is obvious, skip detection" | Still run Glob() โ confirm with evidence not assumption |
| "Validation is redundant after interview" | ALWAYS run both โ different question categories |
| "Greenfield check is optional" | Auto-detect is MANDATORY โ no manual override |
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.
Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json
$workflow-start <workflowId> for standard; sequence custom steps manually[CRITICAL] Hard-won project debugging/architecture rules. MUST ATTENTION apply BEFORE forming hypothesis or writing code.
Goal: Prevent recurrence of known failure patterns โ debugging, architecture, naming, AI orchestration, environment.
Top Rules (apply always):
ExecuteInjectScopedAsync for parallel async + repo/UoW โ NEVER ExecuteUowTaskwhere python/where py) โ NEVER assume python/python3 resolvesExecuteInjectScopedAsync, NEVER ExecuteUowTask. ExecuteUowTask creates new UoW but reuses outer DI scope (same DbContext) โ parallel iterations sharing non-thread-safe DbContext silently corrupt data. ExecuteInjectScopedAsync creates new UoW + new DI scope (fresh repo per iteration).AccountUserEntityEventBusMessage = Accounts owns). Core services (Accounts, Communication) are leaders. Feature services (Growth, Talents) sending to core MUST use {CoreServiceName}...RequestBusMessage โ never define own event for core to consume.HrManagerOrHrOrPayrollHrOperationsPolicy names set members, not what it guards. Add role โ rename = broken abstraction. Rule: names express DOES/GUARDS, not CONTAINS. Test: adding/removing member forces rename? YES = content-driven = bad โ rename to purpose (e.g., HrOperationsAccessPolicy). Nuance: "Or" fine in behavioral idioms (FirstOrDefault, SuccessOrThrow) โ expresses HAPPENS, not membership.python/python3 resolves โ verify alias first. Python may not be in bash PATH under those names. Check: where python / where py. Prefer py (Windows Python Launcher) for one-liners, node if JS alternative exists.Test-specific lessons โ
docs/project-reference/integration-test-reference.mdLessons Learned section. Production-code anti-patterns โdocs/project-reference/backend-patterns-reference.mdAnti-Patterns section. Generic debugging/refactoring reminders โ System Lessons in.claude/hooks/lib/prompt-injections.cjs.
ExecuteInjectScopedAsync, NEVER ExecuteUowTask (shared DbContext = silent data corruption){CoreServiceName}...RequestBusMessagepython/python3 resolves โ run where python/where py first, use py launcher or nodeBreak work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".
Extract lessons โ ROOT CAUSE ONLY, not symptom fixes:
$learn.$code-review/$code-simplifier/$security/$lint catch this?" โ Yes โ improve review skill instead.$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.