shadow-plan
Skill1 starsChanged yesterdayMITView on GitHub
Agile Sprint & Delivery Planning. Use when decomposing approved PRD/SRS specs into Epics, User Stories, Sprint Tasks, dependency graphs, and DoR/DoD. Do NOT use for contractual Paid CR evaluation, PERT/Monte Carlo P80, or EVM (/shadow-pmo).
In this repository51 other files it gives its agents.
- antislop-codeSkill
- antislop-copywritingSkill
- antislop-humanSkill
- antislop-layoutmobileSkill
- antislopSkill
- antislop-uiSkill
- context7Skill
- handoffSkill
- shadow-accessibilitySkill
- shadow-apiSkill
- shadow-architectSkill
- shadow-authSkill
- shadow-bootstrapSkill
- shadow-browserSkill
- shadow-cacheSkill
- shadow-compatSkill
- shadow-concurrencySkill
- shadow-dataSkill
- shadow-dbSkill
- shadow-debugSkill
- shadow-designSkill
- shadow-discoverySkill
- shadow-docSkill
- shadow-domainSkill
- shadow-eaSkill
- shadow-evalSkill
- shadow-finopsSkill
- shadow-gitSkill
- shadow-grcSkill
- shadow-handoverSkill
- shadow-integrateSkill
- shadow-maintainSkill
- shadow-mobileSkill
- shadow-modernizeSkill
- shadow-monarchSkill
- shadow-observeSkill
- shadow-opsSkill
- shadow-perfSkill
- shadow-pmoSkill
- shadow-presalesSkill
- shadow-privacySkill
- shadow-qualitySkill
- shadow-realtimeSkill
- shadow-refactorSkill
- shadow-releaseSkill
- shadow-resilienceSkill
- shadow-searchSkill
- shadow-secSkill
- shadow-supplychainSkill
- shadow-testSkill
- shadow-uatSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 0 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use this skill to translate approved requirements (/shadow-discovery) and system architecture (/shadow-architect) into an executable, …
- Very specific: line 22
Use User Stories (As a <role>, I want <capability>, so that <measurable outcome>) when role permissions drive behavior.
- Very specific: line 23
Use Job Stories (When <situational trigger>, I want to <motivation/action>, so I can <expected outcome>) when context/urgency drives …
- Very specific: line 40
Always provide a Mermaid flowchart LR dependency graph showing execution waves so foundational tasks never block downstream features:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Shadow Plan (/shadow-plan) — Task Decomposition & Delivery Roadmap (SDLC Stage 2 -> 3 Bridge)
Use this skill to translate approved requirements (/shadow-discovery) and system architecture (/shadow-architect) into an executable, dependency-ordered engineering backlog.
1. Work Breakdown Hierarchy & End-to-End Traceability (EPIC -> FR -> US/JOB -> FLOW -> SCR/STATE -> AC -> TASK -> TEST -> METRIC)
Foreign-Key Reference Routing:
- User Stories & Job Stories (JTBD):
pm-execution/skills/user-stories/SKILL.md&pm-execution/skills/job-stories/SKILL.md- Pre-Mortem Risk Analysis (
Tigers | Paper Tigers | Elephants):pm-execution/skills/pre-mortem/SKILL.md- Outcome Roadmap & Sprint Planning:
pm-execution/skills/outcome-roadmap/SKILL.md&pm-execution/skills/sprint-plan/SKILL.md- Traceability & Design Ops Handoff:
10-handoff-and-measurement.md&designer-skills/design-ops/skills/handoff-spec/SKILL.md
- Epics (
EPIC-01): High-level business capability or outcome module (e.g., Identity & Multi-Tenant RBAC, Order & Approval Workflow, Executive Reporting & Export). - User Stories (
US-01.1) & Job Stories (JOB-01.1):- Use User Stories (
As a <role>, I want <capability>, so that <measurable outcome>) when role permissions drive behavior. - Use Job Stories (
When <situational trigger>, I want to <motivation/action>, so I can <expected outcome>) when context/urgency drives behavior. - Preserve stable IDs (
US-ID -> FLOW-ID -> SCR-ID / STATE-ID -> AC-ID -> TASK-ID -> TEST-ID -> METRIC-ID) across revisions (CONFIRMED | PROPOSED | UNKNOWN | DEFERRED).
- Use User Stories (
- Technical Tasks (
TASK-01.1.A): Concrete layer implementation steps:[DB]Schema migration & seed (/shadow-data)[API]Backend service, validation, controller, asyncHTTP 202contract & OpenAPI/Postman sync (/shadow-api)[UI]Frontend screen, 9-state machine (Initial, Empty, Loading, Partial, Success, Validation Error, 403 Denied, Offline, 409/ETag Conflict), responsive mobile layout & state wiring (/shadow-design+antislop+/shadow-cache)[QA]Automated unit/integration tests with ephemeral Docker teardown (/shadow-test) & E2E verification (/shadow-browser)
- Pre-Mortem Risk Table (Before Wave Execution):
Classify delivery and architectural risks into:
- Tigers: Genuine, high-probability/high-impact threats requiring immediate design/code mitigation before coding.
- Paper Tigers: Loud concerns that appear scary but have low actual impact or are already mitigated.
- Elephants: Unspoken organizational, data-quality, or legacy-system truths that the team might avoid discussing.
2. Dependency Graph & Critical Path
Always provide a Mermaid flowchart LR dependency graph showing execution waves so foundational tasks never block downstream features:
- Wave 0 (Foundation):
/shadow-bootstrap+/shadow-auth+ core DB migrations (/shadow-data). - Wave 1 (Core Master Data & CRUD): Primary domain entities and reference tables.
- Wave 2 (Core Transactions & Workflows): State machines, approvals, and external integrations (
/shadow-integrate). - Wave 3 (Reporting, Dashboards & Exports): Aggregations, Data Warehouse/ETL (
/shadow-db), and document exports (/shadow-doc). - Wave 4 (Pre-UAT Hardening, Staging UAT & Release):
/shadow-quality,/shadow-sec,/shadow-perf,/shadow-uat,/shadow-release,/shadow-handover.
3. Mandatory Governance Gates: DoR & DoD
Definition of Ready (DoR — Required Before Starting Any Story)
- Requirement ID (
FR-*),US-ID, and Given/When/Then acceptance criteria (AC-ID) are locked. - Database schema impact, API endpoint contract, and async behavior (
HTTP 200/201vsHTTP 202 Acceptedqueued/processing) are defined. - All 9 UI States (Initial, Empty [No-Data / No-Results / Error], Loading, Partial, Success, Validation Error, 403 Permission-Denied, Offline, and 409/ETag Stale Conflict) are specified (
/shadow-design). - Pre-Mortem Tigers and Elephants have assigned mitigations and owners.
- Blocking upstream tasks are completed.
Definition of Done (DoD — Required Before Marking Any Story Complete)
- Code adheres to strict typing (
0 any,0 as Typecasting) and zero dead code (shadow_gate.py). - Backend endpoints updated in
openapi.yamlandpostman_collection.json(/shadow-api). - Automated unit & integration tests (
/shadow-test) pass (100%green on happy path, 400/401/403/404/409/422) with zero leftover ephemeral Docker test containers/images (--check-docker-leaks). - Responsive UI verified at
320px/375pxmobile and1440pxdesktop +200%zoom across all 9 states (/shadow-browser+antislop). - Lint, typecheck, and build succeed with zero errors (
/shadow-quality).
4. Execution Approval & Intent Boundary (L0–L4)
- Planning and decomposition are
L0_READ_ONLY. Never treat a planned recommendation as Monarch authorization: tag allL2(broad E2E),L3(/shadow-perfload/stress/high-cost eval), andL4(destructive migrations/prod deploy) backlog tasks with[APPROVAL-REQUIRED]undershadow-monarch/reference/EXECUTION-APPROVAL-PROTOCOL.md(execution_approval_gate.py).
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

