hjemmesidekongen/completion-gate
plugins/smedjen/skills/completion-gate/SKILL.md
10-point quality gate run by the code-reviewer agent after implementation. Verifies spec compliance, lint, tests, security, and visual output. The implementing agent never runs this gate on its own work.
development
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai completion-gateInstall 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: Apr 5, 2026, 5:27 PM35.4s2 files scanned
SKILL.md
- name:
- completion-gate
- description:
- >
- user_invocable:
- false
- interactive:
- false
- model_tier:
- senior
- type:
- code_quality_gate
- - name:
- results_recorded
- verify:
- Gate results written to .ai/tasks/gate-results/<task-id>.yml
- fail_action:
- Write gate results file
- on_fail:
- Gate failed — return failures to agent, retry up to 2 times
- on_pass:
- Gate passed — task may be marked done
- origin:
- smedjen
- inspired_by:
- agency/skills/dev/completion-gate/SKILL.md + D-020
- ported_date:
- 2026-03-09
- iteration:
- 1
- changes:
- Expanded from agency 3-check gate to full 10-point criteria per D-020
Completion Gate
10-point quality verification. Run by the code-reviewer agent, never by the implementing agent. A task is not done until all applicable criteria pass.
The 10 Criteria
| # | Check | When to skip | |---|-------|-------------| | 1 | Spec compliance — matches original task description | Never | | 2 | Lint passes | No linter configured | | 3 | Type check passes | No type checker | | 4 | Unit tests pass | No test runner | | 5 | Integration tests pass | No integration tests | | 6 | E2E tests pass | No E2E setup | | 7 | New tests cover new behavior | No testable behavior added | | 8 | Visual verification passes | Not a UI change | | 9 | Security check — no new vulnerabilities | N/A | | 10 | Code-reviewer sign-off | Never |
Gate Flow
- Receive completed subtask from agent-dispatcher.
- Run each applicable criterion, collecting pass/fail + evidence.
- If any critical criterion fails: return error to implementing agent.
- Agent fixes, gate re-runs (max 2 retries).
- If still failing after retries: mark failed, log, escalate.
- All pass: write results, mark task as gate-passed.
See references/process.md for detailed criteria, evidence formats, and retry flow.
Related Skills
hjemmesidekongen/brand-strategy
development
VerifiedTrustedCommunity
Creates a brand from scratch through market research and interactive sparring. Runs competitive research via Perplexity, then guides the user through positioning, audience, voice, values, and content pillars. Produces the full brand guideline set at .ai/brand/{name}/. Use when building a new brand, defining brand strategy for a product, or when /våbenskjold:create is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-loader
testing
VerifiedTrustedCommunity
Loads brand guidelines from .ai/brand/{name}/ and makes them available to the current context. Progressive disclosure: L1 confirms brand exists, L2 loads summary, L3 loads specific files on demand. Use when a downstream skill or user needs brand context, or when /våbenskjold:apply is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-evolve
documentation
VerifiedTrustedCommunity
Guided reinvention of an existing brand guideline. Loads current brand from .ai/brand/{name}/, identifies what to keep vs change, and walks the user through targeted evolution. Preserves brand equity while updating positioning, voice, or values. Use when refreshing a brand or when /våbenskjold:evolve is invoked.
SKILL.mdUpdated Apr 5, 2026
hjemmesidekongen/brand-audit
development
VerifiedTrustedCommunity
Codifies an existing brand from materials, samples, and references. Analyzes provided content to extract voice patterns, values, and positioning. Produces the same guideline format as brand-strategy. Use when a brand already exists but isn't documented, or when /våbenskjold:audit is invoked.
SKILL.mdUpdated Apr 5, 2026