docs(skills): tighten 11 skill descriptions + visibility priority on the two root entry points

skills/blob-reading/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: blob-reading
 version: 1.0.0
-description: Safe resolution of ci-blob:// URIs — extract specific fields without dumping full payloads
+description: Use when a graph result contains a ci-blob:// URI — resolve it by extracting only the fields you need, never the full payload.
 license: MIT
 ---
 

skills/context-intelligence-derived-metrics/SKILL.md

@@ -1,15 +1,12 @@
 ---
 name: context-intelligence-derived-metrics
 description: >
-  Use when a graph query returns structurally-identical rows that hide different
-  intent — many delegations all "none/conversation", many look-alike sessions,
-  many identical tool calls — and the raw shape refuses to tell you WHY. Teaches
-  how to derive an INTERPRETIVE metric by joining a second graph layer onto the
-  blanket shape, turning undifferentiated data into behavioral signatures.
-  Flagship pattern: the "flavour" of a sub-session = delegation transport × the
-  skill payload loaded inside the sub-session it spawned. Complements
-  context-intelligence-graph-query (which tells you how to READ the graph); this
-  skill tells you how to make blanket reads MEAN something.
+  Use when a graph query returns structurally-identical rows hiding different
+  intent — many delegations all "none/conversation", look-alike sessions,
+  identical tool calls. Derives an INTERPRETIVE metric by joining a second graph
+  layer onto the blanket shape (flagship: transport × sub-session skill payload =
+  "flavour"). Complements graph-query (READ the graph) by making blanket reads
+  MEAN something.
 license: MIT
 metadata:
   version: "1.0.0"

skills/context-intelligence-eval-design/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: context-intelligence-eval-design
 version: 1.0.0
-description: Use when designing evaluation scenarios for a context-intelligence tool signal — derives success criteria from domain-concepts.md and produces evaluation-scenarios.md entries and DTU profile templates.
+description: Use when designing evaluation scenarios for a context-intelligence tool signal. Derives success criteria from domain-concepts.md and produces evaluation-scenarios.md entries plus DTU profile templates.
 user-invocable: false
 allowed-tools: read_file, glob, grep, delegate, load_skill, todo
 model_role: reasoning

skills/context-intelligence-evaluation-methodology/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: context-intelligence-evaluation-methodology
 version: 1.0.0
-description: Use when deciding how to measure a context-intelligence tool signal — metric design across quality/efficiency/efficacy axes, artifact-metric avoidance via precursor measurement, A/B and statistical-N discipline, and test-data fidelity.
+description: Use when deciding how to measure a context-intelligence tool signal. Covers metric design across quality/efficiency/efficacy axes, artifact-metric avoidance via precursor measurement, A/B and statistical-N discipline, and test-data fidelity.
 user-invocable: false
 allowed-tools: read_file, glob, grep, delegate, load_skill, todo
 model_role: reasoning

skills/context-intelligence-gds/SKILL.md

@@ -1,15 +1,11 @@
 ---
 name: context-intelligence-gds
 description: >
-  Use when an analysis over the context-intelligence graph is about to be written as
-  naive Cypher — reach for Neo4j GDS (Graph Data Science) or APOC instead when the
-  question is really a complex topology search: pathfinding, reachability,
-  centrality/influence, community/clustering, topological/structural similarity, or
-  finding similar event PATHS / trajectories (with or without a time dimension). Names the
-  advantages of the graph-data-science package and the best-fit scenarios for it, so
-  you stop hand-rolling traversals and re-deriving structure one hop at a time. This
-  is the WHEN/WHY layer; the graph-query skill's "Push Work to the Database" section
-  is the HOW.
+  Use when about to write naive Cypher for a graph-topology question — pathfinding,
+  reachability, centrality/influence, community/clustering, structural similarity,
+  or similar event paths/trajectories (with/without time) — reach for Neo4j GDS or
+  APOC instead of hand-rolling traversals one hop at a time. WHEN/WHY layer;
+  graph-query's "Push Work to the Database" section is the HOW.
 license: MIT
 metadata:
   version: "1.2.0"

skills/context-intelligence-graph-query/SKILL.md

@@ -7,6 +7,9 @@ description: >
   layers, cross-layer SOURCED_FROM joins, SST navigation, blob handling, and
   verified Cypher patterns.
 license: MIT
+visibility:
+  priority: 5
+  summary: Query the context-intelligence property graph for session history, tool traces, delegation trees, skills, and recipe orchestration via verified Cypher patterns.
 metadata:
   version: "2.5.0"
   changelog:

skills/context-intelligence-hill-climbing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: context-intelligence-hill-climbing
-description: 'Use when an investigation needs MORE THAN ONE step — track the exploration as a hill climb in the todo tool so progress, dead leads, and findings leave an auditable trail. Governs HOW you track the climb, NOT how you query or extract (those stay in the graph-query / session-navigation skills).'
+description: 'Use when an investigation needs more than one step — track it in todo as a hill climb so progress and dead leads leave an audit trail. Governs HOW you track the climb, not how you query or extract — that stays in graph-query / session-navigation.'
 version: 0.1.0
 license: MIT
 ---

skills/context-intelligence-session-navigation/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: context-intelligence-session-navigation
-description: 'Use when extracting session data directly from JSONL files — the baseline path when the graph server is unavailable or when operating outside graph-analyst'
+description: 'Use when extracting session data directly from JSONL files — the fallback when the graph server is unavailable or outside graph-analyst.'
 version: 0.2.0
 license: MIT
 ---

skills/context-intelligence-tool-design/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: context-intelligence-tool-design
 version: 1.0.0
-description: Use when selecting a detection strategy and implementation primitive for a context-intelligence signal — classifies signals as deterministic/probabilistic/llm-evaluated/hybrid and applies the cheapest-sufficient-capability principle.
+description: Use when selecting a detection strategy and implementation primitive for a context-intelligence signal. Classifies signals as deterministic, probabilistic, llm-evaluated, or hybrid, and applies the cheapest-sufficient-capability principle.
 user-invocable: false
 allowed-tools: read_file, glob, grep, delegate, load_skill, todo
 model_role: reasoning

skills/workflow-pattern-analysis/SKILL.md

@@ -2,13 +2,11 @@
 name: workflow-pattern-analysis
 version: 1.0.0
 description: >
-  Analyse failure and success patterns across many runs of a specific workflow using
-  context-intelligence session data. Use when you want to answer: "How is <workflow>
-  failing?", "What does a successful run look like vs a failing one?", "Which steps are
-  the most common failure points?", or "What patterns appear consistently across sessions?"
-  Triggers on: workflow failure patterns, session failure analysis, compare successful and
-  failing runs, what patterns appear across sessions, session behaviour investigation,
-  how is the workflow failing, success patterns, failure signals, identify session signals.
+  Analyse failure/success patterns across many runs of a workflow using context-intelligence
+  session data. Use when asked "How is <workflow> failing?", "What does a successful run
+  look like vs a failing one?", "Which steps are the most common failure points?", or "What
+  patterns appear consistently across sessions?" — also triggers on session failure analysis
+  and identifying failure/success signals.
 user-invocable: true
 allowed-tools:
   - bash
@@ -17,6 +15,9 @@ allowed-tools:
   - write_file
 model_role: reasoning
 license: MIT
+visibility:
+  priority: 5
+  summary: Investigate failure and success patterns across many runs of a workflow using context-intelligence session data.
 ---
 
 # Workflow Pattern Analysis