Summarize Changes Headless
Summarizes uncommitted git changes in a concise machine-readable format. Use in CI pipelines, scripts, or headless invocations where the output will be piped or captured.
Install
$ agentstack add skill-davila7-claude-with-skills-02-headless ✓ 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-davila7-claude-with-skills-02-headless) 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
Current changes
!git diff HEAD
Instructions
If the diff above is empty, output exactly: No uncommitted changes.
Otherwise, output the summary in the following format with no surrounding prose:
SUMMARY
- [bullet point describing the first logical change]
- [bullet point describing the second logical change]
[continue as needed, two to five bullets maximum]
RISKS
- [risk] or NONERules for the SUMMARY section:
- Each bullet describes a logical change, not a file change. If three files were modified to implement one feature, that is one bullet.
- Use present tense: "Add validation for email field" not "Added" or "Adding".
- Maximum 80 characters per bullet.
Rules for the RISKS section:
- List only genuine risks: missing error handling, hardcoded credentials, removed tests, breaking API changes.
- If there are no risks, write NONE on a single line.
- Do not list stylistic observations as risks.
Output nothing else. No preamble, no "Here is the summary:", no closing remarks. The output must be parseable by a script that splits on the SUMMARY and RISKS headers.
Note: this skill is optimized for headless use with claude -p "/summarize-changes-headless". The concise, structured output can be captured with claude -p "/summarize-changes-headless" > summary.txt and processed by downstream tools. Compare this to the interactive summarize-changes skill, which produces more readable prose suited to an interactive session. In headless mode, conciseness and consistent structure matter more than readability, because there is no follow-up turn to ask for clarification or a reformatted response.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: davila7
- Source: davila7/claude-with-skills
- License: MIT
- Homepage: https://claude-with-skills.vercel.app
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.