Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/AI & Agent Building
hoangnguyen0403 avatar

Publish Notes

hoangnguyen0403/agent-skills-standard

This takes your merged commits, PRs, and deployment reports and turns them into structured release notes for different audiences. It triages what's user-facing versus internal, drafts public-safe summaries that skip implementation details, and separates out security notes that need careful wording. The template splits public, internal, and security notes cleanly, which is helpful if you're shipping to an app store with character limits or need to keep exploit details vague while still documenting the fix. It's built to prevent the common problem of claiming features in release notes that didn't actually ship, and it routes lessons learned to a separate retro workflow instead of cluttering your changelog.

GitHub stars
504
last updated
Jun 11, 2026
View on GitHubSave

Install

$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill publish-notes --agent claude-code

Installs into .claude/skills of the current project.

Files

Publish Notes Skill

[!IMPORTANT] Draft user-facing release notes, store changelogs, and internal publish summaries.

Optional args: slug=, ticket=<id/url>, mode=interactive|autonomous|channel, channel=, auto_continue=true|false, profile=business|hybrid|technical.

Instructions

When the user asks to perform this workflow, execute the following steps:

Publish Notes Workflow

Goal: Convert verified changes into accurate user-facing and internal release notes.

Steps

  1. Gather inputs:
    • Merged commits/diff, verification report, UAT signoff, deployment report, and STLC Stage 6 closure evidence (skills/quality-engineering/quality-engineering-test-plan-authoring/references/lifecycle-and-roles.md).
    • Product/store constraints, mobile platform/OS versions, and artifact build digest.
    • Product evidence contracts (docs/product/<slug>/evidence.json: measurement owner, MET baseline, instrumentation, guardrails).
    • Load common-operator-profile; carry inherited operator_profile without re-inferring.
    • User-facing change
    • Bug fix
    • Security or privacy note
    • Operational change
    • No-user-impact internal change
  2. Draft notes:
    • Use plain language and business outcomes for every tier; operator_profile=business gets Public Notes as the primary artifact, Internal Notes as an appendix.
    • Keep sensitive security details high-level.
    • Respect platform character limits.
  3. Verify and persist:
    • Cross-check notes against verified shipped scope and closure evidence; remove unshipped, blocked, or deferred claims.
    • Separate delivery proof from customer ROI. Feature feature_status=released preserved when product value observations are pending.
    • Write run record to artifacts/runs/[slug]/[compactISO]-publish-notes.json when allowed.
    • Route process lessons, defect escapes, and release gaps to retro-learn.
  • Use after deploy-release or uat-signoff to draft user-facing and internal release communication.
  • Required inputs: shipped diff/commits plus verification or deployment report to cross-check against.
  • Return BLOCKED only when no verified shipped scope exists to draft notes from. Feature released status is retained when product value is pending or inconclusive.

Handoff Payload

  • slug, operator_profile, public notes, internal notes, security/privacy notes, measurement contract refs when present, verification source, next workflow.

Blocking Questions

  • Ask max 3 at a time with a recommended default and 2-3 options.

Output Template

# Release Notes: [Version]

## Public Notes

## Internal Notes

## Security Or Privacy Notes

## Verification Source

## Outcome Report
{schema_version: 1, run_id: "[run-id]", slug: "[slug]", workflow: publish-notes, feature_status: released, started_at: "[timestamp]", completed_at: "[timestamp]", requirement_trace: {brd_objectives: [], requirements: [], acceptance_criteria: [], srs: []}, completed_evidence: [], missing_evidence: [], decision_needed: [], recommended_next_workflow: retro-learn, cost: {source: unavailable}, agent: {identity: "[agent-identity]", model: "[model]"}}

## Next Workflow

retro-learn

## Cost Report
Call `get_session_cost(workflow="publish-notes")` before final handoff.
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/hoangnguyen0403/agent-skills-standard
Categories
AI & Agent Building, Release Management
License
Apache-2.0
First seen
Jun 11, 2026

More from hoangnguyen0403/agent-skills-standard

All 28
  • Retro Learn
  • Review Ticket
  • Sdlc
  • Security Test
  • Session Report
  • Skill Benchmark
  • Skill Creator
  • Traceability Audit
  • Update Docs
  • Verify Bug
  • Verify Work
  • Zephyr Coverage Analysis
  • Battle Test
  • Brainstorm Feature
  • Caveman
  • Caveman Commit
  • Caveman Compress
  • Caveman Review
  • Code Review
  • Codebase Review
  • Deploy Release
  • Design Solution
  • Dev Fix
  • Implement Feature

Recommended

More AI & Agent Building
1hoangnguyen0403 avatarretro-learnhoangnguyen0403/agent-skills-standardConvert delivery findings into skill, eval, workflow, and documentation improvements.0installs
2hoangnguyen0403 avatarreview-tickethoangnguyen0403/agent-skills-standardReview a ticket or PR through focused specialist lenses: scope, architecture, security, tests, AC coverage, and PR metadata.0installs
3hoangnguyen0403 avatarsdlchoangnguyen0403/agent-skills-standardRoute a task to the next synced SDLC workflow based on current artifacts and repo state.0installs
4hoangnguyen0403 avatarsecurity-testhoangnguyen0403/agent-skills-standardFast, continuous DevSecOps pipeline for Pull Requests and active branches. Runs SAST, SCA, and secrets detection to catch vulnerabilities before they merge.0installs
5hoangnguyen0403 avatarsession-reporthoangnguyen0403/agent-skills-standardCapture delivery evidence, commands, changed files, tool usage, token/cost notes, blockers, and skill-feedback candidates after a work session.0installs
6hoangnguyen0403 avatarskill-benchmarkhoangnguyen0403/agent-skills-standardBenchmark AI skill effectiveness by measuring implementation quality against legacy constraints.0installs