BB ceph-aiops
Use this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTH_WARN/ERR state into cause + action (cluster_health), read the cluster status, inspect OSDs (tree/df/perf), placement groups (summary/stuck/scrub), pools (list/usable capacity), RBD images and snapshots, CephFS/MDS and RGW status, monitors/managers, slow ops and capacity forecast — plus governed writes (set cluster flags, reweight/mark-in/mark-out/purge OSDs, trigger scrubs, set pool quota/pg_num/autoscale/size, create/delete pools, create/delete RBD images and snapshots, throttle recovery/backfill). Always use this skill for "ceph health", "what does this HEALTH_WARN mean", "PG_DEGRADED / OSD_NEARFULL / SLOW_OPS / MON_DOWN", "ceph -s", "which OSD is most full", "drain an OSD", "purge an OSD", "stuck PGs", "overdue scrub", "pool usable capacity", "set pool size / quota", "rebalance is too slow / throttle backfill", "RBD image or snapshot", "MDS behind on trimming", "RGW large omap", "mon quorum", or "days to nearfull" when the context is a Ceph cluster (cephadm, hypervisor-bundled Ceph, or MicroCeph). Do NOT use when the target is not Ceph — a hypervisor, a different storage appliance, a backup product, a Kubernetes cluster, or a network device. Route those to the appropriate other AIops-tools skill (negative routing hint only). Common Ceph ops with a built-in governance harness (audit, policy, token budget, undo, risk-tiers).
Use this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTHWARN/ERR state into cause +…
As a process B 71/100 · 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 1479 chars, limit 1024 - 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 71/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 55Failures and branches. 1 branches
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 37 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2347 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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 1478: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 37 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: 67.