Install
$ agentstack add skill-compilet-dev-agent-skill-uselink-uselink-report ✓ 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.
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
Uselink Report Generator
> See report-templates.md for HTML templates and per-report-type data gathering commands.
Prerequisites
Before generating any report, verify:
- CLI installed --
which uselinkmust resolve. If not, tell the user to runnpm install -g uselink. - CLI configured --
~/.uselink/config.jsonmust exist withapi_key. If not, tell the user to runuselink loginin their terminal (interactive -- Claude cannot run it).
Stop here if either check fails. The user must fix these.
Report Types
| Type | Trigger phrases | Data sources | |------|----------------|--------------| | Code review | "review report", "code review summary" | git diff, file reads, grep | | Architecture | "architecture report", "system overview" | Directory scan, key config files | | Sprint/daily | "sprint report", "daily summary", "standup" | git log --since, gh pr list | | Custom | Anything else that asks for a "report" | Conversation context, user instructions |
If the type is ambiguous, ask. Do not guess.
Workflow
- Determine report type from the user's request.
- Gather data using the commands and file reads listed in
report-templates.mdfor that report type. - Generate HTML by filling the matching template from
report-templates.md. Write to/tmp/uselink-report--.html. - Publish with
uselink publish --title "" --format html. - Return the URL as the primary output.
Key Rules
- Always use
--format html. Reports are HTML, not markdown. - Title format:
Report -- --. Example:Code Review -- my-project -- 2026-05-25. - Infer project name from the git remote or directory name.
- Date in titles uses
YYYY-MM-DD. - Do not ask the user which template to use -- pick based on the report type.
- The temp file is not cleaned up so the user can re-publish after edits.
Content Rules
- Use real data from the repo. Never fabricate commits, file names, or findings.
- For code review reports, run the actual diff and analyze it. Do not summarize from memory.
- For sprint reports, use
git logoutput, not guesses about what was worked on. - Keep reports concise. A 200-line HTML report is better than a 2000-line one.
Gotchas
uselink loginis interactive. Claude cannot run it. If config is missing, tell the user to run it themselves and stop.- HTML must use inline CSS only. Uselink strips `
andtags that reference external files. All styles go instyleattributes or a singleblock in. See templates inreport-templates.md`. - Publishing always creates a new document. There is no upsert. If the user wants to update an existing report, they need to publish again and get a new URL.
- The CLI prints the URL to stdout. Capture full stdout from the publish command. The URL is typically the last line.
- Large diffs can exceed context. For code review reports on big PRs, summarize by file rather than including every line. Use
git diff --statfirst to scope the work, then read only the files with meaningful changes. git logdate formats matter. Use--format="%H|%an|%s|%ai"for parseable output. Do not rely on the default pretty format.- Sprint "since" needs a sane default. If the user does not specify a date range, default to 7 days for sprint reports and 1 day for daily summaries.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: compilet-dev
- Source: compilet-dev/agent-skill-uselink
- License: MIT
- Homepage: https://uselink.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.