BC knowledge-graph
Embedded knowledge graph for persistent structured knowledge. ALWAYS use proactively — do NOT wait for user to ask. Auto-triggers on: (1) any mention of people, projects, devices, services, organizations, or infrastructure — search KG first, add if new, (2) decisions or architectural choices worth remembering, (3) credentials or API keys (store in vault), (4) relationships between entities (who owns what, what runs where, what depends on what), (5) recurring concepts, principles, or lessons learned, (6) preferences and opinions (likes, dislikes, reviews), (7) places and locations (where someone lives, travels, frequents), (8) life events and milestones (birthdays, trips, meetings), (9) habits and routines (daily patterns, recurring behaviors), (10) knowledge artifacts — research papers, articles, insights, ideas, interesting facts shared by the user, (11) know-how and procedures — how to do something, debugging approaches, workflows, mental models, problem-solving frameworks. Also use when recalling facts, answering questions about known entities, or needing structured context. Run install script on first use. NOT for: ephemeral daily notes (use memory/), transient conversation, or rapidly changing data.
Embedded knowledge graph for persistent structured knowledge.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 27. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1223 chars, limit 1024
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 40Consistency. Frontmatter name (knowledge-graph) differs from the folder (knowledge-graph-skill)
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 6 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 1817 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +3Description length 1223: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -34 of 15 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 6 items
- +4Has examples (10 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 57.