hjemmesidekongen/confluence-lookup
plugins/herold/skills/confluence-lookup/SKILL.md
Search Confluence for pages related to the active task. Extracts keywords from task summary, description, and labels. Constructs CQL queries, scores results by relevance, and links matching docs to the task context for dev-engine consumption. Graceful fallback when Confluence MCP is not configured.
tools
Updated Apr 5, 2026
$ install --global
skillsauthnpx skillsauth add hjemmesidekongen/ai confluence-lookupInstall 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 24, 2026, 8:37 PM1.7s1 file scanned
SKILL.md
- name:
- confluence-lookup
- description:
- >
- user_invocable:
- true
- interactive:
- false
- model_tier:
- senior
- - "kronen:
- confluence-basics
- - ".ai/tasks/<KEY>.yml" # appends confluence_docs:
- array
- type:
- data_validation
- - name:
- docs_linked
- verify:
- confluence_docs key written to task YAML (empty array acceptable if no results)
- fail_action:
- Write empty array — do not leave key absent
- on_fail:
- Report which check failed and the task key that triggered it.
- on_pass:
- Report: found N Confluence pages for task <KEY>.
- origin:
- herold
- inspired_by:
- D-014 decisions
- ported_date:
- 2026-03-10
- iteration:
- 1
- changes:
- Orchestration skill for task-aware Confluence search
confluence-lookup
Searches Confluence for documentation relevant to the active task. Built on top of
kronen's confluence-basics MCP skill as the query layer. This skill adds
task keyword extraction, CQL construction, relevance scoring, and task context linking.
Steps
- Load task — read
.ai/tasks/<KEY>.yml. If no active task, abort and report. - Extract keywords — pull terms from summary, description, labels, and epic name (see
references/process.md§1) - Build CQL query — construct a Confluence Query Language string from keywords (see
references/process.md§2) - Execute search — call Atlassian MCP via
confluence-basics. If MCP unavailable, enter dry-run mode. - Score results — rank pages by relevance using keyword overlap and recency (see
references/process.md§3) - Link docs — append top results to task YAML under
confluence_docs:(seereferences/process.md§5) - Report — list matched pages with titles and URLs. State clearly if dry-run.
Foundation
Uses kronen/confluence-basics for raw MCP query execution. This skill owns
the task-awareness layer: keyword extraction, scoring, and context writing.
confluence-basics handles authentication, pagination, and response parsing.
Dry-run mode
When Confluence MCP is not connected, the skill writes confluence_docs: [] to the
task file and logs a warning. No stub data is fabricated — missing MCP is not an error,
just an empty result. The task remains processable by dev-engine.
Never
- Never fabricate Confluence results — empty array is the correct response when nothing matches
- Never return stale cached results without noting staleness
Output: Found N Confluence page(s) for <KEY>. Linked to task context.
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