Prd V08 Release Planning

What it does

When your agent uses it

• Requests to plan releases
• Define deployment criteria
• User asks how do we deploy?
• Release criteria

Example prompts

• “how do we deploy?”
• “release criteria”
• “deployment plan”
• “/prd-v08-release-planning”

Requirements

• Pre-approved tools (allowed-tools): Read, Write, Edit, Glob, Grep, Bash

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Inventory completed EPICs
2. 2Define deployment environments
3. 3Establish release criteria
4. 4Define rollback triggers
5. 5Document validation steps
6. 6Create DEP- entries with full traceability

What it can do on your machine

Read from SKILL.md and the folder at commit 30ed1b0. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Glob
  • Grep
  • Bash

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Prd V08 Release Planning loads about 3.1k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 96 tokens; SKILL.md has 796 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~96

When it runs · the whole SKILL.md, loaded when a task matches

~3.1k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: Read, Write, Edit, Glob, Grep, Bash

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mattgierhart/PRD-driven-context-engineering at commit 30ed1b0, republished under its MIT licence (© mattgierhart). 796 words, ~3,065 tokens.

name

prd-v08-release-planning

description

Define release criteria, deployment environments, and rollback strategies during PRD v0.8 Deployment & Ops. Triggers on requests to plan releases, define deployment criteria, or when user asks "how do we deploy?", "release criteria", "deployment plan", "rollback strategy", "go-live checklist". Outputs DEP- entries with deployment steps and release criteria.

allowed-tools

Read, Write, Edit, Glob, Grep, Bash

context

fork

execution_modes.default

standard

execution_modes.supports

quick, standard, deep

DEP-001: Production Environment Configuration
Type: Environment
Stage: Pre-deploy

Description: AWS production environment setup for application
Name: production
Infrastructure: AWS us-east-1, ECS Fargate, RDS PostgreSQL
Configuration:
  - NODE_ENV=production
  - LOG_LEVEL=info
  - RATE_LIMIT=100/min
  - METRICS_COLLECTION=enabled
Secrets: AWS Secrets Manager, rotated monthly
Access: DevOps team (deploy), On-call (read-only access)

Linked IDs: ARC-001 (monolith structure), TECH-005 (AWS)

---

DEP-002: All Tests Pass in Staging
Type: Criteria
Stage: Pre-deploy

Description: Complete test suite must pass in staging environment before production release
Requirement: All TEST- entries pass with >95% success rate, including smoke tests and E2E tests
Verification: CI/CD pipeline reports green; test report generated and reviewed
Blocker: Yes — Release cannot proceed if this fails
Owner: QA Lead

Linked IDs: TEST-001 to TEST-050 (from EPIC-01 through EPIC-07)

---

DEP-003: Error Rate Rollback Trigger
Type: Rollback
Stage: Post-deploy

Description: Automatic rollback if error rate exceeds baseline post-deployment
Trigger: 5xx error rate exceeds pre-deployment baseline
Threshold: >2% of requests for 5 minutes (currently 0.5% baseline from MON-001)
Procedure:
  1. Alert on-call engineer (PagerDuty)
  2. Pause traffic to new version
  3. Revert to pre-deploy git tag
  4. Investigate root cause
Notification: #incidents Slack, PagerDuty, Engineering Lead

Linked IDs: MON-001 (error rate metric), RUN-002 (rollback procedure), API-001–020 (endpoints affected)

---

DEP-004: Post-Deployment Smoke Tests
Type: Validation
Stage: Post-deploy

Description: Automated smoke tests to verify critical user journeys work post-deployment
Check: All critical UJ- (UJ-000, UJ-001, UJ-005, UJ-010) complete successfully
Method: Automated (tests/e2e/smoke.spec.ts) + manual spot-check
Success Criteria: All journeys complete <2 seconds, no auth failures, data persists
Escalation: If smoke tests fail, execute DEP-003 rollback and investigate

Linked IDs: UJ-000/001/005/010 (critical journeys), TEST-050 (E2E suite)

DEP-XXX: [Deployment Item Title]
Type: [Environment | Criteria | Rollback | Validation | Step]
Stage: [Pre-deploy | Deploy | Post-deploy | Rollback]

Description: [What this deployment item covers]

For Environment Type:
  Name: [staging | production | preview]
  Infrastructure: [Cloud provider, region, resources]
  Configuration: [Environment-specific settings]
  Secrets: [How secrets are managed]
  Access: [Who can deploy, who can access]

For Criteria Type:
  Requirement: [What must be true]
  Verification: [How to check this]
  Blocker: [Yes | No] — Does failure block deploy?
  Owner: [Who verifies]

For Rollback Type:
  Trigger: [What condition initiates rollback]
  Threshold: [Specific metric or condition]
  Procedure: [How to execute rollback]
  Notification: [Who to alert]

For Validation Type:
  Check: [What to verify post-deploy]
  Method: [Manual | Automated | Both]
  Success Criteria: [Expected result]
  Escalation: [What if validation fails]

Linked IDs: [EPIC-XXX, API-XXX, TEST-XXX related]

DEP-001: Production Environment Configuration
Type: Environment
Stage: Pre-deploy

Description: AWS production environment setup for main application

Name: production
Infrastructure: AWS us-east-1, ECS Fargate, RDS PostgreSQL
Configuration:
  - NODE_ENV=production
  - LOG_LEVEL=info
  - RATE_LIMIT=100/min
Secrets: AWS Secrets Manager, rotated monthly
Access: DevOps team (deploy), On-call (read-only)

Linked IDs: ARC-001, TECH-005

DEP-002: All Tests Pass in Staging
Type: Criteria
Stage: Pre-deploy

Description: Complete test suite must pass in staging environment

Requirement: All TEST- entries pass with >95% success rate
Verification: CI/CD pipeline green status, test report review
Blocker: Yes
Owner: QA Lead

Linked IDs: TEST-001 to TEST-050

DEP-003: Error Rate Rollback Trigger
Type: Rollback
Stage: Post-deploy

Description: Automatic rollback if error rate exceeds threshold

Trigger: 5xx error rate exceeds baseline
Threshold: >2% of requests for 5 minutes
Procedure:
  1. Alert on-call engineer
  2. Pause traffic to new version (if canary)
  3. Revert to previous known-good version
  4. Investigate root cause
Notification: #incidents Slack, PagerDuty

Linked IDs: MON-001, RUN-005

© mattgierhart, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references, assets) in .claude/skills/prd-v08-release-planning of mattgierhart/PRD-driven-context-engineering.

• SKILL.md
• assets/dep-template.md
• references/deployment-strategies.md
• references/examples.md
• references/rollback-procedures.md

Open the folder on GitHubat commit 30ed1b0