New Feature
End-to-end feature workflow wrapper. Chains feature-research → feature-work → feature-test → feature-review and emits the final outline-form report. Usage: /new-feature <feature description>
Install
$ agentstack add skill-tianea2160-claude-skills-new-feature ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-tianea2160-claude-skills-new-feature) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
new-feature
Wrapper skill that runs the full feature workflow end-to-end by chaining four independent skills:
/feature-research— produces an approved Plan at.claude/plans/.md./feature-work— implements the Plan./feature-test— writes and runs tests./feature-review— verifies goal alignment and code quality.
Each stage is a self-contained skill that can also be invoked directly. This wrapper adds orchestration and a final outline-form report that stitches the four mini-reports together.
$ARGUMENTS is the feature description.
> Language note: This skill is authored in English per .claude/rules/skill-authoring.md. User-facing output follows the project's CLAUDE.md language preference.
References
- [references/report-template.md](references/report-template.md) — Final outline-form report template for Step 5.
Workflow
1. Run research
Invoke Skill: feature-research with $ARGUMENTS. On completion, capture the returned Plan path.
If the user declines the Plan during ExitPlanMode inside feature-research, the wrapper stops and surfaces the decline.
2. Run implementation
Invoke Skill: feature-work with the Plan path.
3. Run tests
Invoke Skill: feature-test with the Plan path.
4. Run review
Invoke Skill: feature-review with the Plan path.
5. Emit the final outline-form report
Render the combined outline-form report following references/report-template.md, as model text in the project's preferred language. Never emit via Bash.
The report stitches each stage's mini-report ▸ Summary/▸ Artifacts/▸ Metrics into a single view, adds a ▸ Stage results block, and surfaces any ▸ Next steps that require user action.
Invariants
- Do not re-implement the stage logic inline; always delegate to the dedicated skills.
- Do not embed Plan body text into the wrapper's prompts or report — reference by path.
- Preserve each stage's mini-report as-is; the final report composes them, does not replace them.
- If any stage stops with
status: blockedor an unresolved AskUserQuestion, halt the chain and surface the condition.
Constraints
- SKILL.md body length ≤ 80 lines.
- Allowed tools are intentionally narrow: orchestration only.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: Tianea2160
- Source: Tianea2160/claude-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.