alienfast/next
skills/next/SKILL.md
Suggest the best next issue to work on. Considers current cycle, dependency graph, triage status, and what's unblocked. Use when the user says 'what's next', 'next issue', or invokes /next.
tools
Updated May 27, 2026
$ install --global
skillsauthnpx skillsauth add alienfast/claude nextInstall 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: May 27, 2026, 4:28 AM338.4s1 file scanned
SKILL.md
- name:
- next
- description:
- Suggest the best next issue to work on. Considers current cycle, dependency graph, triage status, and what's unblocked. Use when the user says 'what's next', 'next issue', or invokes /next.
Next Issue
Suggests the most logical next issue to work on by combining cycle planning, dependency analysis, and triage signals. All fetching, blocker verification, and tier ranking is delegated to scripts/next-candidates.sh — this skill is just the entry point and result narration.
When to Use
- Starting a fresh day/week and unsure where to begin
- After finishing an issue (invoked from
/finish) - Deciding between multiple candidate issues
Workflow
Step 1: Determine completed-issue context
Check whether there's a just-completed issue providing context. Two ways this can surface:
- Invoked from
/finishwith the issue ID already in scope — capture it as<COMPLETED-ID>. - Current branch name matches a Linear issue (e.g.
kross/pl-260-foo) AND that issue is in Done or Ready For Release — capture as<COMPLETED-ID>. Otherwise treat as standalone.
If neither applies, run in standalone mode.
Step 2: Run the ranking script
Run from inside the project directory so the script can read .linear.yaml for the team key. Use the appropriate form:
# Standalone
~/.claude/scripts/next-candidates.sh
# Post-finish (transitively unblock from <COMPLETED-ID>)
~/.claude/scripts/next-candidates.sh --completed <COMPLETED-ID>
# Show more than the default 3
~/.claude/scripts/next-candidates.sh --limit 5
The script emits a markdown-formatted ranked list with tier, parent chain, and reasoning per candidate. It exits 0 even when no workable candidates exist (it prints _No workable issues in team <KEY>._).
Step 3: Present the result
Read the script's stdout and narrate it naturally:
- Lead with the top candidate: identifier, title, why it's the recommendation (the tier reason already encodes this).
- If there's a runner-up that's qualitatively different from the top pick (different tier, different parent epic), mention it as "also consider."
- If the script reported no workable issues, say so plainly — do not invent a suggestion.
The script's tier reasons (e.g. "in current cycle + newly unblocked", "sibling under completed parent") already explain the why — surface them rather than rephrasing.
Error Handling
- Exit 1 — arg error. Read stderr and fix the invocation.
- Exit 2 — Linear/network failure. Surface the error message verbatim and stop.
- Exit 3 — missing dependency (
linear,jq). Tell the user to install it. - If
linear auth statusshows logged out, prompt:linear auth login.
Notes on the Algorithm
The script applies the same six-tier scheme the previous prose version of this skill described — see scripts/next-candidates.sh for the exact logic. The high-level priority order:
- Already assigned to you (finish what you started)
- In current cycle + newly unblocked by
<COMPLETED-ID> - In current cycle, ready
- Newly unblocked anywhere
- Sibling under the same parent as
<COMPLETED-ID> - Highest-priority workable fallback
Within each tier: parent-epic state (In Progress > Planned > Backlog > Triage) > priority > cycle membership > estimate.
Related Skills
alienfast/full
testing
VerifiedTrustedCommunity
End-to-end Linear issue macro — runs /start then /finish in sequence, gated on the /quality-review verdict. Worktree mode is opt-in via the `wt` token, mirroring /start. Pauses only for plan approval and the deferred-items filing decision; otherwise autonomous. Use when the user says 'full PL-XX', 'ship PL-XX end-to-end', or invokes /full.
SKILL.mdUpdated May 28, 2026
alienfast/quality-review
development
VerifiedTrustedCommunity
Adversarial implementation review with triage and fix loop. Hard-gates on `pnpm check`, delegates to the quality-reviewer agent for categorized findings (Critical/High/Medium/Nice-to-Have/Approved), then triages and fixes findings via the developer agent. Loops until a re-review surfaces no new Critical/High/Medium findings (convergence), with a soft ceiling of 5 cycles before asking the user how to proceed; option 3 of that prompt terminates with verdict `escalated-to-architect`. Use when the user says 'review my work', 'check this implementation', 'adversarial review', 'quality review', or invokes /quality-review.
SKILL.mdUpdated Apr 29, 2026
alienfast/triage
testing
VerifiedTrustedCommunity
Triage and prioritize Linear backlog. Analyzes issues for staleness, blockers, and suggests priorities based on dependencies and capacity.
SKILL.mdUpdated Apr 15, 2026
alienfast/start
testing
VerifiedTrustedCommunity
Start working on a Linear issue — check blockers, assign, move to In Progress, create branch, plan implementation, execute with checkpoint updates, review and triage findings. Use when the user says 'start issue', 'work on PL-XX', 'begin PL-XX', or invokes /start.
SKILL.mdUpdated Apr 15, 2026