beekeeper-lab/ai-team-library/claude/skills/release-notes
ai-team-library/claude/skills/release-notes/SKILL.md
# Skill: Release Notes ## Description Collects completed work items, merged changes, and resolved issues from a release cycle and produces structured release notes, a changelog entry, and a known issues list. The skill reads task completion records, PR summaries, and the generation manifest to build a comprehensive picture of what changed, then formats it for both technical and non-technical audiences. This supports the DevOps/Release Engineer and Technical Writer personas. ## Trigger - Invo
development
Updated Apr 3, 2026
$ install --global
skillsauthnpx skillsauth add beekeeper-lab/foundry ai-team-library/claude/skills/release-notesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 10:03 PM156.9s1 file scanned
SKILL.md
Skill: Release Notes
Description
Collects completed work items, merged changes, and resolved issues from a release cycle and produces structured release notes, a changelog entry, and a known issues list. The skill reads task completion records, PR summaries, and the generation manifest to build a comprehensive picture of what changed, then formats it for both technical and non-technical audiences. This supports the DevOps/Release Engineer and Technical Writer personas.
Trigger
- Invoked by the
/release-notesslash command. - Called by the DevOps/Release Engineer persona during release packaging.
- Called by the Technical Writer persona for external-facing communication.
Inputs
| Input | Type | Required | Description |
|-------|------|----------|-------------|
| version | String | Yes | Version identifier for this release (e.g., "1.2.0", "2025-Q1-sprint-3") |
| tasks_dir | Directory path | No | Directory of completed tasks; defaults to ai/tasks/ |
| previous_version | String | No | Previous version for comparison; used to scope what's "new" |
| changelog_file | File path | No | Existing changelog to append to; defaults to CHANGELOG.md |
| audience | Enum: internal, external, both | No | Who the notes are for; defaults to both |
Process
- Collect completed work -- Scan task files for items marked complete since the previous version. Group by category: features, fixes, improvements, documentation, infrastructure.
- Gather PR/change summaries -- If git history is available, collect merge commit messages and PR descriptions for the version range. Cross-reference with task IDs.
- Identify breaking changes -- Flag any changes that alter APIs, data formats, configuration, or behavior in ways that require consumer action.
- Compile known issues -- Collect open tasks, deferred items, and known limitations that ship with this version.
- Draft release notes -- Produce a structured document with sections: highlights (top 3 changes), features, fixes, improvements, breaking changes, known issues, and upgrade instructions.
- Draft changelog entry -- Produce a concise changelog entry following Keep a Changelog format: Added, Changed, Deprecated, Removed, Fixed, Security.
- Tailor for audience -- If
external, focus on user-facing changes and omit internal refactoring. Ifinternal, include technical details and infrastructure changes. Ifboth, produce both variants.
Outputs
| Output | Type | Description | |--------|------|-------------| | release_notes | Markdown file | Full release notes document for the version | | changelog_entry | Text (appended) | Entry appended to the existing changelog file | | known_issues | Section in notes | List of open issues and limitations shipping with this version |
Quality Criteria
- Every completed task is accounted for in either the release notes or changelog -- nothing is silently dropped.
- Breaking changes are prominently flagged and include migration/upgrade instructions.
- The highlights section contains no more than three items and captures the most impactful changes.
- The changelog entry follows Keep a Changelog conventions (Added/Changed/Fixed/etc.).
- Known issues are honest: they describe the limitation, its impact, and any workaround.
- External-facing notes use user-understandable language; internal notes can use technical shorthand.
- Version identifiers are consistent between the release notes, changelog, and any tagged artifacts.
Error Conditions
| Error | Cause | Resolution |
|-------|-------|------------|
| NoVersionProvided | Version identifier not supplied | Provide a version string |
| NoCompletedTasks | No tasks marked complete in the specified range | Verify task status or broaden the version range |
| ChangelogNotFound | Changelog file path does not exist | Create a CHANGELOG.md or specify the correct path |
| GitHistoryUnavailable | Not a git repo or git not installed | Release notes will be built from tasks only, without PR data |
Dependencies
- Completed tasks from the Seed Tasks / task management workflow
- Git history (optional) for PR and merge data
- Existing CHANGELOG.md for appending
- DevOps/Release Engineer persona's template if available
Related Skills
beekeeper-lab/ai-team-library/claude/skills/vdd
development
VerifiedTrustedCommunity
# Skill: VDD (Verification-Driven Development) Gate ## Description Runs the programmatic VDD gate for a bean: parses the bean's `## Acceptance Criteria` section, dispatches each criterion's evidence type to the matching runner (test, lint, file, file-contains, or manual), aggregates the results into a pass/fail verdict, and writes a structured markdown report at `ai/outputs/tech-qa/vdd-<NNN>.md` (zero-padded NNN). This is the machine-checkable counterpart to the prose VDD policy in `ai/contex
SKILL.mdUpdated May 2, 2026
beekeeper-lab/ai-team-library/claude/skills/spawn-task
tools
VerifiedTrustedCommunity
# Skill: Spawn Task ## Description Dispatches a single specialist persona to execute a single task with only that task's context. Auto-detects the runtime environment and chooses one of two execution paths: - **In tmux** (`$TMUX` set): spawn a worker in a git worktree using a child tmux window. Process-isolated, parallelizable, durable across the calling session's lifetime. Same pattern as `/spawn-bean` but at task granularity. - **Not in tmux**: invoke the `Agent` tool with `subagent_typ
SKILL.mdUpdated May 2, 2026
beekeeper-lab/ai-team-library/claude/skills/orchestration-report
development
VerifiedTrustedCommunity
# Skill: Orchestration Report ## Description Aggregates the per-bean **Orchestration Telemetry** blocks (BEAN-278) across recent Done beans and produces a markdown report that answers the architecture-aware-evaluation question: **is the orchestration paying for itself?** Distinct from `/telemetry-report` (which aggregates raw cost, duration, and tokens); this skill aggregates the orchestration-quality metrics layered on top — bounces, persona activations, contract violations, escape-hatch usag
SKILL.mdUpdated May 2, 2026
beekeeper-lab/.claude/local/skills/health-check
development
VerifiedTrustedCommunity
# Skill: Health Check ## Description Runs all health checks defined in `ai/context/health-checks.md` and produces a table-format report. Can be called standalone or by other skills (e.g., `/long-run`). ## Trigger - Invoked by the `/health-check` slash command. - Called programmatically by `/long-run` at the start of each cycle. ## Inputs | Input | Type | Required | Description | |-------|------|----------|-------------| | health_checks | Markdown file | Yes | `ai/context/health-checks.md`
SKILL.mdUpdated Apr 15, 2026