BB mysql-aiops
Use this skill whenever the user needs to operate or troubleshoot a MySQL 8.x or MariaDB 10.6+ server as a DBA — a one-shot server health overview (version + flavor, connection headroom, replica role); server reads (global variables, status counters, databases, storage engines); activity (sessions/processlist, long-running queries, open InnoDB transactions, lock waits); query stats (performance_schema statement-digest top-N, EXPLAIN FORMAT=JSON); index health (unused indexes, redundant/duplicate indexes, cardinality); table health (sizes, data_free fragmentation, engine/row-format status); replication (replica IO/SQL thread state and lag, binlog/GTID status); four flagship analyses — slow-query RCA (worst digest + EXPLAIN → cited cause/action incl. full-scan and lock-time-dominant classification), InnoDB lock-wait & deadlock chain RCA (wait-for tree, root blocker, last deadlock parsed from SHOW ENGINE INNODB STATUS), replication lag RCA (thread state/error fields → cause+action), and table fragmentation analysis (data_free → OPTIMIZE candidates); and guarded writes (kill a session or query, OPTIMIZE/ANALYZE TABLE, create/drop an index, SET GLOBAL a variable, reset digest stats). Always use this skill for "mysql health check", "why is this query slow", "top queries by time", "EXPLAIN this", "table fragmentation", "which indexes are unused", "redundant index", "who is blocking whom", "deadlock", "kill the session holding the lock", "replication lag", "replica stopped", "seconds behind master/source", "OPTIMIZE this table", "create/drop an index", or "SET GLOBAL max_connections" when the context is a MySQL or MariaDB database. Do NOT use for PostgreSQL — use postgres-aiops. Do NOT use when the target is OT / industrial equipment (use industrial-aiops), a hypervisor, a storage appliance, a backup product, or a container/cluster orchestrator (negative routing hints only). Common MySQL/MariaDB DBA operations with a built-in governance harness (audit, policy, token budget,
x or MariaDB 10.6+ server as a DBA — a one-shot server health overview (version + flavor, connection headroom, replica role); server reads (global variables…
As a process B 75/100 · Nearly there — weak spots: result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 2133 chars, limit 1024 - note
description-budgetdescription takes 2133 of the ~15000-char shared budget for all skills - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "displayName" - note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "installer"
Process rating: all ten parameters 75/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3193 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low The response is described with custom markup (5 tags): a typed call is more reliable
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
- +3Description length 2132: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 16 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 13 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.