workflow-idea-to-spec Skill

Codex compatibility note:

Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.

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 uses static project-reference loading instead of runtime-injected project docs. 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)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $claude-md-init) before ordinary project-specific work. If Codex mirrors or AGENTS.md are missing/stale, ask the user to run $sync-codex; do not auto-run it.

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 authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
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.

Renamed: formerly workflow-product-discovery — now $workflow-idea-to-spec. The old name no longer resolves as a slash command.

Quick Summary

Goal: [Workflow] Trigger the spec-driven Idea-to-Spec workflow to convert a raw idea — a raw vision or problem → structured brainstorm framing → canonical, provisional Feature Spec (the tech-free 8-section spec + §8 test specs at docs/specs/{Bucket}/README.{Feature}.md, Evidence: TBD until code lands) → reviewed and docs-synced. This workflow STOPS at the reviewed Feature Spec — it does NOT produce a PBI backlog. For a backlog, chain workflow-spec-to-pbi afterward; for idea → full backlog in one pass use workflow-idea-to-pbi; for code→spec (implementation already exists) use workflow-code-to-spec.

Workflow:

Frame — brainstorm the idea, analyze domain, validate the problem framing (why-review).
Author — capture the idea, then author the canonical provisional Feature Spec (spec [mode=draft]) + §8 test specs (spec [mode=tests]).
Review & Sync — review the test specs and the Feature Spec, validate rationale (why-review), sync docs.

Key Rules:

MUST ATTENTION keep claims evidence-based (file:line) with confidence >80% to act.
MUST ATTENTION keep task tracking updated as each step starts/completes.
MUST ATTENTION define success criteria before execution and loop until observable verification passes.
MUST ATTENTION when creating/reviewing specs or tests, name Business Intent / Invariant Guarded or the protected business intent/invariant and ensure the test would fail if that intent breaks.
MUST ATTENTION author the spec via spec [mode=draft] — idea-sourced, no code yet → §8 Evidence: TBD, Status: Planned, frontmatter provisional: true.
NEVER decompose into PBIs/stories/backlog here — that is workflow-spec-to-pbi's job. NEVER skip the Feature Spec authoring core.

When to Use

PO/BA has a raw product vision, problem statement, or "we need to build X" starting point and wants a canonical Feature Spec
Team wants to capture intended behavior as a tech-free spec BEFORE any code exists (spec-first / TDD-first)
A single idea or capability needs a reviewed, AI-implementable Feature Spec as the source of truth for later implementation

When NOT to Use

Implementation already exists and you want a spec FROM code → use workflow-code-to-spec
You want a full grooming-ready PBI backlog from the idea in one pass → use workflow-idea-to-pbi
You already have a Feature Spec and want PBIs from it → use workflow-spec-to-pbi
Implementation work (code writing) → use workflow-feature or workflow-big-feature
Bug fixes → use workflow-bugfix

Key Mechanics

1. Brainstorm → Converge on the Capability to Spec

The $brainstorm step frames the idea using the Double Diamond process:

Problem framing: POV statement, 5 Whys / Fishbone, JTBD job stories, HMW questions
Opportunity framing: Opportunity Solution Tree (enhancement) OR Lean Canvas (new product)
Ideation: SCAMPER, Crazy 8s, Impact Mapping
Convergence: pick the single feature/capability to author as a Feature Spec

Output: the converged capability (or a short list if multiple distinct capabilities emerge). AI presents the framing and confirms scope: "Which capability should we author as a Feature Spec?" If multiple distinct capabilities are in scope, confirm with the user and author one Feature Spec per capability (sub-agent per capability for 4+ — see Scale awareness).

1a. Spec-Discovery (Landscape Investigation — After brainstorm, Before domain-analysis)

$spec-discovery investigates the surrounding system BEFORE authoring: it Globs docs/specs/** to classify every related / overlapping / affected Feature Spec, scouts related code (graph-expanded when .code-graph/graph.db exists), and surfaces gaps, missing test cases / user stories, and the invariant landscape the idea must respect. It ends in a BLOCKING scope-decision gate — author a NEW spec, EXTEND an existing one, or SPLIT into N — so no duplicate / overlapping spec is authored. Greenfield (no specs + no code) short-circuits with a recorded reason.

2. Why-Review Gate (After domain-analysis, Before spec authoring)

Before authoring the spec, validate the idea framing with $why-review:

Challenge prompts:

Is this truly the right problem to solve? What was deprioritized and why?
Pre-mortem: if this is built and misses in 6 months, what was the root cause?
Are there systemic alternatives (infrastructure change, process change) that make this unnecessary?

| Result | Action | | ------ | --------------------------------------------- | | PASS | Proceed to spec authoring | | WARN | Document risk, acknowledge with user, proceed | | FAIL | Revisit brainstorm framing before authoring |

3. Spec Authoring Flow (core mechanic — idea → provisional Feature Spec)

These steps run in sequence. Spec-driven order: idea → draft Feature Spec → test specs → review.

| Step | Purpose | Output | | ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------- | | $idea | Capture the converged idea as a structured artifact | team-artifacts/ideas/{date}-po-idea-{slug}.md | | $spec [mode=draft] | Author the canonical tech-free 8-section Feature Spec §1-7 FROM the idea text (no code grep; provisional: true marker) | docs/specs/{Bucket}/README.{Feature}.md | | $spec [mode=tests] | Author §8 TC-{FEATURE}-{NNN} behavioral test cases (Evidence: TBD, Status: Planned — before any code) | Feature Spec §8 Test Specifications | | $review-artifact --type=spec-tests | Test-spec quality check | Reviewed §8 TCs | | $review-artifact | Feature Spec quality check | Reviewed Feature Spec | | $spec-clarify | Brainstorm open questions, audit non-obvious decisions, confirm with user (BLOCKING) | Clarified spec + Decisions Log | | $why-review | Validate the authored spec's rationale and completeness | Why-Review checklist | | $docs-update | Sync the Feature Spec (§8) and derived bucket indexes | Docs-update report |

Provisional output: because no code exists yet, the spec is provisional — §8 TCs carry Evidence: TBD and Status: Planned, and frontmatter carries provisional: true. The first workflow-code-to-spec / spec [mode=update] run against real code upgrades TBD → real [Source:] anchors and clears the provisional flag.

4. Handoff

At $workflow-end, AI presents:

Session summary: M Feature Specs authored (provisional), §8 TC counts, open questions (confidence < 80%)
Feature Specs authored: docs/specs/{Bucket}/README.{Feature}.md paths
Provisional note: these specs carry Evidence: TBD + provisional: true until code lands — reconcile via workflow-code-to-spec / spec [mode=update] once implemented
Recommended next workflow: $start-workflow workflow-spec-to-pbi (decompose the Feature Spec(s) into a grooming-ready PBI backlog) OR $start-workflow workflow-feature (implement directly from the spec)

Conditional Skip Rules

| Step | Skip When | | -------------------- | ------------------------------------------------------------------------ | | $domain-analysis | No new domain entities or aggregates involved | | $why-review (gate) | User has already validated the idea rationale; no alternatives available |

IMPORTANT MANDATORY Steps: $web-research -> $deep-research -> $brainstorm -> $spec-discovery -> $domain-analysis -> $why-review -> $idea -> $spec [mode=draft] -> $spec [mode=tests] -> $review-artifact --type=spec-tests -> $review-artifact -> $spec-clarify -> $why-review -> $docs-update -> $workflow-end -> $watzup

[BLOCKING] Each step MUST ATTENTION invoke its skill invocation — marking a task completed without skill invocation is a workflow violation. NEVER batch-complete validation gates.

Activate the workflow-idea-to-spec workflow. Run $start-workflow workflow-idea-to-spec with the user's prompt as context.

Steps: $web-research → $deep-research → $brainstorm → $spec-discovery → $domain-analysis → $why-review → $idea → $spec [mode=draft] → $spec [mode=tests] → $review-artifact --type=spec-tests → $review-artifact → $spec-clarify → $why-review → $docs-update → $workflow-end → $watzup

Scale awareness: When the brainstorm converges on multiple distinct capabilities, this workflow authors one Feature Spec per capability. For 4+ capabilities, spawn one spec sub-agent per capability in ONE message (each gets the framing context + output path); the main context assembles and reviews. Use incremental-write patterns to prevent context overrun.

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

Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Nested Task Expansion Contract — For workflow-step invocation, the [Workflow] ... row is only a parent container; the child skill still creates visible phase tasks.

Call the current task list first. If a matching active parent workflow row exists, set nested=true and record parentTaskId; otherwise run standalone.

Create one task per declared phase before phase work. When nested, prefix subjects [N.M] $skill-name — phase.

When nested, link the parent with TaskUpdate(parentTaskId, addBlockedBy: [childIds]).

Orchestrators must pre-expand a child skill's phase list and link the workflow row before invoking that child skill or sub-agent.

Mark exactly one child in_progress before work and completed immediately after evidence is written.

Complete the parent only after all child tasks are completed or explicitly cancelled with reason.

Blocked until: the current task list done, child phases created, parent linked when nested, first child marked in_progress.

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.

Incremental Result Persistence — MANDATORY for all sub-agents or heavy inline steps processing >3 files.

Before starting: Create report file plans/reports/{skill}-{date}-{slug}.md

After each file/section reviewed: Append findings to report immediately — never hold in memory

Return to main agent: Summary only (per SYNC:subagent-return-contract) with Full report: path

Main agent: Reads report file only when resolving specific blockers

Why: Context cutoff mid-execution loses ALL in-memory findings. Each disk write survives compaction. Partial results are better than no results.

Report naming: plans/reports/{skill-name}-{YYMMDD}-{HHmm}-{slug}.md

Sub-Agent Return Contract — When this skill spawns a sub-agent, the sub-agent MUST return ONLY this structure. Main agent reads only this summary — NEVER requests full sub-agent output inline.
## Sub-Agent Result: [skill-name]

Status: ✅ PASS | ⚠️ PARTIAL | ❌ FAIL
Confidence: [0-100]%

### Findings (Critical/High only — max 10 bullets)

- [severity] [file:line] [finding]

### Actions Taken

- [file changed] [what changed]

### Blockers (if any)

- [blocker description]

Full report: plans/reports/[skill-name]-[date]-[slug].md
Main agent reads Full report file ONLY when: (a) resolving a specific blocker, or (b) building a fix plan. Sub-agent writes full report incrementally (per SYNC:incremental-persistence) — not held in memory.

Context budget — the return payload is a SUMMARY, not a transcript: ≤10 finding bullets, no raw file contents / full diffs / verbatim logs inline, no re-pasted source. Everything beyond the summary lives in the Full report on disk. A sub-agent that would exceed the summary shape MUST write the detail to its report and return only the pointer — the orchestrator's context is the scarce resource the whole map-reduce protects.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.

MANDATORY Parent workflow rows do not replace child phase tracking; expand phases and link the parent when nested.
MANDATORY Orchestrators pre-expand child skill phases before invocation; use [N.M] $skill-name — phase prefixes and one-in_progress discipline.

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Ensure spec-driven idea-to-spec converts a raw idea into ONE canonical, provisional Feature Spec — reviewed and docs-synced, ready to hand off for backlog decomposition or implementation.

IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries; each is a signpost to its canonical body above):

AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
Nested Task Creation: expand child phases and link parent when nested; one in-progress.
Critical Thinking: trace every claim, confidence >80% to act, never present guess as fact.
Incremental Persistence: write findings to plans/reports/ per file — never hold in memory.
Sub-Agent Return Contract: return summary only (≤10 bullets) with Full report: path.
MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting — one task per workflow step (per capability when multiple capabilities are in scope)
MANDATORY IMPORTANT MUST ATTENTION brainstorm converges on the capability to spec BEFORE the $idea step
MANDATORY IMPORTANT MUST ATTENTION SPEC-DRIVEN ORDER — author the Feature Spec ($spec [mode=draft] → $spec [mode=tests]) and review it; this workflow STOPS at the reviewed spec
MANDATORY IMPORTANT MUST ATTENTION PROVISIONAL OUTPUT — §8 carries Evidence: TBD / Status: Planned and frontmatter provisional: true; reconcile against code later via workflow-code-to-spec
MANDATORY IMPORTANT MUST ATTENTION NEVER decompose into PBIs/stories/backlog here — chain workflow-spec-to-pbi for a backlog
MANDATORY IMPORTANT MUST ATTENTION why-review runs after domain-analysis — FAIL revisits framing, WARN requires user acknowledgment
MANDATORY IMPORTANT MUST ATTENTION validate decisions with user via a direct user question — never auto-select scope
MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify the authored Feature Spec(s)

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

[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important. Anti-Rationalization:

| Evasion | Rebuttal | | ------------------------------------ | ----------------------------------------------------------------------------- | | "Purpose obvious" | Anchor it anyway — primacy/recency keeps outcome active through long prompts. | | "Existing reminders enough" | Echo Goal in Closing Reminders — bottom anchor prevents drift. | | "Skip evidence for prompt edits" | Cite changed file evidence and verify no stale protocol text remains. | | "Decompose into PBIs while I'm here" | Out of scope — this workflow STOPS at the spec. Chain workflow-spec-to-pbi. |

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs

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

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. Any supported AI tool may execute when this shared context and local docs are available.

DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.

Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.

Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.

Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.

Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.

Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync

If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

SYNC:ai-sdd-artifact-contract:reminder

MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [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.

[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:

Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
Auto-fix gate: "Could $code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
BOTH gates pass → ask user to run $learn. [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. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
When debugging, ask "whose responsibility?" before fixing. Trace caller (wrong data) vs callee (wrong handling). Fix at responsible layer — never patch symptom site.
Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
Assume existing values are intentional — ask WHY before changing. Pattern-matching as "wrong" skips context. Before changing any constant/limit/flag: read comments, git blame, surrounding code.
Verify ALL affected outputs, not just the first. One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
Evaluate fit before copying a nearby pattern. Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
Holistic-first debugging — resist nearest-attention trap. Don't dive into first plausible cause. List EVERY precondition (config, env vars, paths, DB, endpoints, creds, versions, DI, data). Verify each against evidence (grep/query — not reasoning). Ask "what would falsify this?" — if nothing, it's not a hypothesis. Most expensive failure: going deeper in "obvious" layer while bug sits in layer never questioned.
Surgical changes — apply the diff test (context-aware). Two modes: (1) Bug fix → every line traces to the bug; no restyling; orphan cleanup only for imports YOUR changes made unused. (2) Review/enhancement → implement improvements AND announce as "Enhancement beyond main request: [what]". Never silently scope-creep. Diff test: "Would this line exist if I wasn't asked to do X?" — if no, delete or announce.
Surface ambiguity before coding — don't pick silently. Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
[MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding. Match task against workflow catalog + skill list; invoke via skill invocation or $start-workflow <workflowId>. NEVER answer or write code before checking. Skip = protocol violation.
Why-Review adversarial mindset — apply when reviewing any plan, decision, or design. Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
Front-load report-write in sub-agent prompts for large reviews. Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
After context compaction, re-verify all prior phase outcomes before continuing. Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
OOM/memory: check row count before row size. Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
Keep domain concepts out of generic/shared/infrastructure layers. Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.

Agent Skills: workflow-idea-to-spec

Install this agent skill to your local

Skill Files