Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Orchestrate Deliver

ASecurity

Orchestrated Delivery O2: run sdd-spec then sdd-plan per approved US/TS; human-approve PRD/PLAN; emit multi-path handoff. No app code. Use when invoking /orchestrate-deliver.

6 stars
0 votes
0 copies
0 views
Added 9/25/2026
ai-agentsshellrails

Works with

cursor

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/25/2026

$npx -y skills add tibursocampos/agent-dev-toolkit --skill orchestrate-deliver --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Orchestrate Deliver?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Orchestrate Deliver
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tibursocampos-orchestrate-deliver-a62ebd59/badge)](https://www.skillsdirectory.com/skills/tibursocampos-orchestrate-deliver-a62ebd59)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: orchestrate-deliver
description: Orchestrated Delivery O2: run sdd-spec then sdd-plan per approved US/TS; human-approve PRD/PLAN; emit multi-path handoff. No app code. Use when invoking /orchestrate-deliver.
---

## STOP - Read before ANY tool call

1. Read `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/rules/guardrails.mdc`
2. Read `_shared/sdd-artifacts/SESSION.md`; load session-state for `$Cwd`
3. If the relevant gate is not approved: **STOP** - ask user **(pt-BR)** - do **NOT** Write/Shell
4. SDD/develop skills: after **ONE** step/task, **STOP** session - handoff only
5. This skill body is **English**; user-facing prompts may be **(pt-BR)**

### Step -1 - Gate check (report in chat before continuing)

```
Gate check:
[ ] guardrails.mdc read
[ ] SESSION.md read; session-state loaded
[ ] PIPELINE.md read (required for orchestrate-*)
[ ] User confirmed current action (sim)
-> If any unchecked: STOP
```

---

# Skill: orchestrate-deliver

## Trigger

Invoke when the user asks for: `/orchestrate-deliver`, `orchestrate deliver`, `/orchestrate-deliver`, or Orchestrated Delivery O2 after an approved O1 backlog.

Required: full feature path (or resolvable `features/NNN-slug/`).

## Outcome

Under each approved story folder (`USnn` / `TSnn`):

1. `PRD/NNN_*.md` - via **`sdd-spec` contract** (what, not how)
2. `PLAN/PLAN_NNN_*.md` - via **`sdd-plan` contract** (baby steps)
3. Feature-root `CHANGE.md` - **required when FEATURE Nature is brownfield** (ADDED \| MODIFIED \| REMOVED vs current `memory-bank/` docs; **greenfield** must not force an empty stub) — `CHANGE-CONTRACT.md` / `sdd-spec`
4. Feature `CONTINUITY.md` - phase `deliver`, decisions, typed multi-path handoff, **Memory-bank** path + status

**Mental map (ids unchanged):** O2 ≈ **FEATURE + PRD + CHANGE** (then PLAN). O1 ≈ explore; O3 ≈ apply. Skill ids stay `orchestrate-*`.

**Step 0 (required):** Memory Bank Gate (`MEMORY-BANK.md`, policy `auto`) **before** mode selection / story contracts. Resolve `bank_root` via `STORAGE.md` - never under `features/`. CONTINUITY remains the feature phase/handoff source; bank does not replace it.

**Human gate:** PRD/PLAN approval per story **or** batch (`sim` / `ajustar` / `cancelar`). Silence ≠ approval (RN01).

Orchestrator **does not** implement application code. **Does not** rewrite `sdd-spec` / `sdd-plan` process - load those skills and run their contracts per story. **Does not** call trackers.

## Lazy-load (only when needed)

| When | Path (after `scripts/sync-cursor.ps1`) |
|------|----------------------------------------|
| Caveman Mode (if active) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/caveman/CAVEMAN.md` - **Lite cap** |
| Pipeline Orchestrated Delivery, confirm, paths | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/PIPELINE.md` |
| Storage, manifest, feature tree | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/STORAGE.md` |
| Step 0 Memory Bank Gate | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/MEMORY-BANK.md` |
| Memory-bank create/refresh | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/memory-bank-init/SKILL.md` |
| CONTINUITY / FEATURE templates | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/templates/features/` |
| Spec contract | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-spec/SKILL.md` (+ `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-spec/reference.md` as needed) |
| Plan contract | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-plan/SKILL.md` (+ `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-plan/reference.md` as needed) |
| CHANGE brownfield / current | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/sdd-artifacts/CHANGE-CONTRACT.md` |
| Process details, modes, approval, Must not | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/orchestrate-deliver/reference.md` |
| Spawn native vs fallback (capability `subagents`) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/agents/SPAWN.md` |
| Task subagent model (default omit; rare premium gate) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/_shared/agents/SUBAGENT-MODEL.md` |
| Context pressure | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/rules/context-management.mdc` |

**Never by default:** do not preload both `sdd-spec` and `sdd-plan` full bodies plus all templates and SPAWN/SUBAGENT-MODEL before mode selection. Load contracts when running that story stage; load SPAWN only when choosing paralelo / spawning drafts.

**Progressive load:** `PIPELINE.md` + `STORAGE.md` first; fan-out to `MEMORY-BANK.md` at Step 0, then `sdd-spec` → `sdd-plan` per story, and `orchestrate-deliver/reference.md` for Process step details / mode / approval / Must not when needed.

## Reference routing

| Situation | Path |
|-----------|------|
| Gate / Orchestrated Delivery / siblings STOP | `PIPELINE.md` |
| Feature / bank roots | `STORAGE.md` |
| Step 0 Memory Bank | `MEMORY-BANK.md` |
| Before paralelo Task wave | `SPAWN.md` |
| Write PRD (after **sim**) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-spec/SKILL.md` |
| Write PLAN (after **sim**) | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/sdd-plan/SKILL.md` |
| Process steps / mode / batch approval / Must not | `E:/Source/Repos/agent-dev-toolkit/scripts/validation/fixtures/cursor-install-root/skills/orchestrate-deliver/reference.md` |

## Process

Read `reference.md` for procedural tables, prompts, and checklists under each step. Do not skip gates.

### Step -1b - Caveman Mode (Lite cap)
Apply Lite caveman prefs when active. Details: `reference.md` § Process — Caveman (Lite cap).

### 1. Gate check
Report the Step -1 gate checklist in chat. Load `PIPELINE.md` (Orchestrated Delivery) and `SESSION.md`. **STOP** if any gate unchecked.

### 2. Resolve feature and storage
Load `STORAGE.md`; resolve feature + bank roots; path sanitize; **STOP** if FEATURE/CONTINUITY missing. Details: `reference.md` § Process — Resolve feature and storage.

### 3. Step 0 - Memory Bank Gate
Follow `MEMORY-BANK.md` (policy default **`auto`**). Bank root = resolved `bank_root` - **not** under `features/`. Update CONTINUITY Memory-bank fields; pass `bank_path` into parallel draft Tasks read-only. Details: `reference.md` § Step 0 - Memory Bank Gate.

### 4. Preconditions (approved backlog)
Verify backlog **sim**/approved; discover stories; **STOP** if flag-gated `ANALYSIS|ARCH|SEC` missing. Details: `reference.md` § Process — Preconditions + § Preconditions checklist.

### 5. Choose mode (RF03)
Ask série vs paralelo (never assume); load `SPAWN.md` before paralelo; omit Task `model` by default. Details: `reference.md` § Process — Choose mode + § Mode comparison (RF03).

### 6. Per-story contracts (reuse, do not rewrite)
Run `sdd-spec` then `sdd-plan` per story (série in-parent, or paralelo draft-only children + parent Write after **sim**). Per-story STOP if required siblings missing. Details: `reference.md` § Process — Per-story contracts + § Contract reuse + § Task child prompt skeleton.

### 7. Approval - per story or batch (RN01)
Present summary; **sim** / ajustar / cancelar (por história | lote). Details: `reference.md` § Process — Approval answers + § Approval gates.

### 8. CONTINUITY + multi-path handoff (RF04)
Update CONTINUITY phase `deliver`; run **cross-artifact analyze** (`CHANGE-CONTRACT.md`: Nature↔CHANGE, complexity↔TASKS, validate-change when CHANGE exists); emit manual `sdd-develop` + O3 handoff paths. Details: `reference.md` § Process — CONTINUITY + multi-path handoff + § Example handoff + § Cross-artifact analyze.

### 9. Context pressure (TE02 / RNF02)
Honor `context-management.mdc`; persist CONTINUITY; resume invoke. Details: `reference.md` § Process — Context pressure.

## Must not

Enforce the full list in `reference.md` § Must not (full). Critical always-on: no app code; no PRD/PLAN without required siblings; no child disk Write of PRD/PLAN; no silence-as-**sim**; no hard-fail when Task unavailable (fallback série in-parent); portable paths only.

## Handoff

| Situation | Next |
|-----------|------|
| All stories approved | `/orchestrate-develop - <portable-feature-path>` **or** per-story `sdd-develop` |
| Context pause mid-O2 | `/orchestrate-deliver - <portable-feature-path>` |
| Backlog not approved | `/orchestrate-analyze - <portable-feature-path>` |
| Required siblings missing | `/orchestrate-analyze - <portable-feature-path>` (do not Write PRD/PLAN) |
| Single story only (skip O2) | `/sdd-spec` then `sdd-plan` (Classic SDD) |

### Canonical develop handoffs

```text
/sdd-develop - <portable-plan-path> - Step 1
```

```text
/orchestrate-develop - <portable-feature-path>
```

Attribution

tibursocampostibursocampos
View sourceSee grades on GitHubMore from tibursocampos →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →