Purpose: Take a project from "code is ready" to "tagged and ready to push."
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionreleaseExecute the skills CLI command in your project's root directory to begin installation:
Fetches release from boshu2/agentops and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate release. Access via /release in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
0
total installs
0
this week
260
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
260
stars
Purpose: Take a project from "code is ready" to "tagged and ready to push."
Pre-flight validation, changelog from git history, version bumps across package files, release commit, annotated tag, and curated release notes. Everything is local and reversible. Publishing (including the GitHub Release page) is CI's job.
/release 1.7.0 # full release: changelog + bump + commit + tag
/release 1.7.0 --dry-run # show what would happen, change nothing
/release --check # readiness validation only (GO/NO-GO)
/release # suggest version from commit analysis
| Argument | Required | Description |
|---|---|---|
version |
No | Semver string (e.g., 1.7.0). If omitted, suggest based on commit analysis |
--check |
No | Readiness validation only — don't generate or write anything |
--dry-run |
No | Show generated changelog + version bumps without writing |
--skip-checks |
No | Skip pre-flight validation (tests, lint) |
--changelog-only |
No | Only update CHANGELOG.md — no version bumps, no commit, no tag |
/release [version] — the complete local release workflow.
Steps: pre-flight → changelog → release notes → version bump → user review → write → release commit → tag → guidance.
/release --check — standalone readiness validation.
Runs all pre-flight checks and reports GO/NO-GO. Useful before starting the release, in CI as a gate, or composed with /vibe. Does not generate or write anything.
/release 1.7.0 --changelog-only — just update CHANGELOG.md.
Generates the changelog entry and writes it. No version bumps, no commit, no tag.
Run these checks before anything else:
./scripts/ci-local-release.sh # mandatory local CI parity gate (blocking)
git rev-parse --git-dir # must be in a git repo
git status --porcelain # warn if dirty
git branch --show-current # show current branch
/release MUST run the repo-root ci-local-release.sh gate first. If it fails, stop the release workflow and report the failing checks.
The local CI gate writes publishable artifacts to .agents/releases/local-ci/<timestamp>/, including SBOM files, a full security scan report, and release-artifacts.json.
Once the target version is known, rerun the gate as ./scripts/ci-local-release.sh --release-version <version> so the artifact manifest matches the final release version. Use ./scripts/resolve-release-artifacts.sh <version> when writing the audit trail.
Checks:
| Check | How | Severity |
|---|---|---|
| Git repo | git rev-parse --git-dir |
Block — cannot proceed |
| CHANGELOG.md exists | Glob for changelog (case-insensitive) | Offer to create if missing |
Has [Unreleased] section |
Read CHANGELOG.md | Warn |
| Working tree clean | git status --porcelain |
Warn (show dirty files) |
| On expected branch | git branch --show-current |
Warn if not main/master/release |
| Local CI parity gate | repo-root ci-local-release.sh |
Block — must pass before release |
| Publishable SBOM | Generated by local CI gate (CycloneDX + SPDX) |
Block — required artifact |
| Security scan report | Generated by local CI gate (full toolchain scan JSON) | Block — required artifact |
| Tests pass | Detect and run test command | Warn (show failures) |
| Lint clean | Detect and run lint command | Warn (show issues) |
| Dependency vulnerabilities | Run /deps vuln to confirm no critical vulnerabilities ship with this release |
Warn (show findings) |
| Version consistency | Compare versions across package files | Warn (show mismatches) |
| Manifest versions sync | Compare .claude-plugin/plugin.json and marketplace.json versions |
Warn (show mismatches) |
| Commits since last tag | git log --oneline <range> |
Block if empty — nothing to release |
| Unconsumed high-severity findings | Count items in .agents/rpi/next-work.jsonl where consumed=false and severity=high |
Warn — not a blocker (see check below) |
Unconsumed findings check (soft WARN, non-blocking):
if [ -f .agents/rpi/next-work.jsonl ] && command -v jq &>/dev/null; then
high_count=$(jq -s '[.[] | select(.consumed == false) | .items[] | select(.severity == "high")] | length' \
.agents/rpi/next-work.jsonl 2>/dev/null || echo 0)
if [ "$high_count" -gt 0 ]; then
echo "[WARN] $high_count unconsumed high-severity item(s) in .agents/rpi/next-work.jsonl"
echo " These carry-forward findings have not been addressed. Review before releasing."
echo " Run: jq -s '[.[] | select(.consumed==false) | .items[] | select(.severity==\"high\")]' .agents/rpi/next-work.jsonl"
fi
fi
This is a soft WARN — it does not block the release. It surfaces carry-forward findings from prior retro/post-mortem sessions so the release engineer can make an informed decision.
Test/lint detection:
| File | Test Command | Lint Command |
|---|---|---|
go.mod |
go test ./... |
golangci-lint run (if installed) |
package.json |
npm test |
npm run lint (if script exists) |
pyproject.toml |
pytest |
ruff check . (if installed) |
Cargo.toml |
cargo test |
cargo clippy (if installed) |
Makefile with test: |
make test |
make lint (if target exists) |
If --skip-checks is passed, skip ad-hoc test/lint detection only. It does not skip the repo-root ci-local-release.sh gate.
In --check mode, run all checks and output a summary table:
Release Readiness: NO-GO
[PASS] Git repo
[PASS] CHANGELOG.md exists
[PASS] Working tree clean
[WARN] Branch: feature/foo (expected main)
[FAIL] Tests: 2 failures in auth_test.go
[PASS] Lint clean
[PASS] Version consistency (1.6.0 in all 2 files)
[PASS] 14 commits since v1.6.0
[WARN] 2 unconsumed high-severity item(s) in .agents/rpi/next-work.jsonl
In --check mode, stop here. In default mode, continue (warnings don't block).
Find the last release tag:
git tag --sort=-version:refname -l 'v*' | head -1
v* tags exist, use the first commit: git rev-list --max-parents=0 HEAD<last-tag>..HEADGather commit data for classification:
git log --oneline --no-merges <range>
git log --format="%H %s" --no-merges <range>
git diff --stat <range>
Use --oneline for the summary view and full hashes for detail lookups when a commit message is ambiguous.
Classify each commit into one of four categories:
| Category | Signal |
|---|---|
| Added | New features, new files, "add", "create", "implement", "introduce", feat |
| Changed | Modifications, updates, refactors, "update", "refactor", "rename", "migrate" |
| Fixed | Bug fixes, corrections, "fix", "correct", "resolve", "patch" |
| Removed | Deletions, "remove", "delete", "drop", "deprecate" |
Grouping rules:
auth:, api:, feat(users))git show --stat <hash> to clarifyKey rules:
### Removed if nothing was removed--no-mergesIf no version was provided, suggest one based on the commit classification:
| Condition | Suggestion |
|---|---|
Any commit contains "BREAKING", "breaking change", or !: (conventional commits) |
Major bump |
| Any commits classified as Added (new features) | Minor bump |
| Only Fixed/Changed commits | Patch bump |
Show the suggestion with reasoning:
Suggested version: 1.7.0 (minor)
Reason: 3 new features added, no breaking changes
Current version: 1.6.0 (from package.json, go tags)
Use AskUserQuestion to confirm or let the user provide a different version.
Produce a markdown block in Keep a Changelog format:
## [X.Y.Z] - YYYY-MM-DD
### Added
- description of new feature
### Changed
- description of change
### Fixed
- description of fix
Use today's date in YYYY-MM-DD format.
Style adaptation: Read the existing CHANGELOG entries and match their conventions:
—, hyphen -, colon : )If no existing entries to reference (first release), use plain Keep a Changelog defaults.
Scan for files containing version strings:
| File | Pattern | Example |
|---|---|---|
package.json |
"version": "X.Y.Z" |
"version": "1.6.0" |
pyproject.toml |
version = "X.Y.Z" |
version = "1.6.0" |
Cargo.toml |
version = "X.Y.Z" |
version = "1.6.0" |
*.go |
const Version = "X.Y.Z" or var version = "X.Y.Z" |
const Version = "1.6.0" |
version.txt |
Plain version string | 1.6.0 |
VERSION |
Plain version string | 1.6.0 |
.goreleaser.yml |
Version from ldflags (show, don't modify — goreleaser reads from git tags) | — |
Show what was found:
Version strings detected:
package.json: "version": "1.6.0" → "1.7.0"
src/version.go: const Version = "1.6.0" → "1.7.0"
.goreleaser.yml: (reads from git tag — no change needed)
Use AskUserQuestion: "Update these version strings?" — "Yes, update all" / "Let me choose" / "Skip version bumps"
Present everything that will change:
If --dry-run was passed, stop here.
Use AskUserQuestion:
After user confirms:
## [Unreleased] line## [ line or EOF)## [Unreleased] + blank line + versioned entryRead references/release-notes.md for the full release notes format, quality bar, condensing rules, and examples. Key points:
docs/releases/YYYY-MM-DD-v<version>-notes.mdCRITICAL: Release notes MUST be written and staged BEFORE the release commit. GoReleaser checks out the tagged commit — if notes are committed after the tag, CI won't find them and falls back to raw changelog extraction.
Resolve the full local-CI artifact set that backs this release, then write the internal release audit record to docs/releases/YYYY-MM-DD-v<version>-audit.md (see Step 16 format). Stage it alongside the release notes.
ARTIFACT_JSON="$(./scripts/resolve-release-artifacts.sh <version>)"
ARTIFACT_DIR="$(echo "$ARTIFACT_JSON" | jq -r '.artifact_dir')"
Stage and commit all release changes together:
git add CHANGELOG.md <version-files...> docs/releases/YYYY-MM-DD-v<version>-notes.md docs/releases/YYYY-MM-DD-v<version>-audit.md
git commit -m "Release v<version>"
The commit message is intentionally simple. The changelog has the details. The release notes and audit trail are included in this commit so the tagged tree contains them.
Create an annotated tag:
git tag -a v<version> -m "Release v<version>"
Do NOT create a draft GitHub Release locally. GoReleaser in CI is the sole
Make data-driven prioritization decisions faster
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Prerequisites
Time Estimate
30-60 minutes to see productivity improvements
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid when
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
mattpocock/skills
parcadei/continuous-claude-v3
cursor/plugins
ailabs-393/ai-labs-claude-skills
ailabs-393/ai-labs-claude-skills
pproenca/dot-skills
We added release from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
release fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
release reduced setup friction for our internal harness; good balance of opinion and flexibility.
Registry listing for release matched our evaluation — installs cleanly and behaves as described in the markdown.
release has been reliable in day-to-day use. Documentation quality is above average for community skills.
Registry listing for release matched our evaluation — installs cleanly and behaves as described in the markdown.
Registry listing for release matched our evaluation — installs cleanly and behaves as described in the markdown.
release reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in release — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: release is focused, and the summary matches what you get after install.
showing 1-10 of 52