ff-oce-dashboard

Generate the OCE shift status dashboard. Triggers on: 'generate shift dashboard', 'show dashboard', 'shift status', 'status dashboard', 'what's going on', or any request for a NON-SPECIFIC overview of current OCE status (incidents, pipelines, errors).

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-sequenced operational runbook with exact tool calls, parameters, and a recovery loop. Its main weakness is progressive disclosure: a large inline KQL query and six agent-prompt templates live entirely in SKILL.md with no bundle files to offload them.

Suggestions

Move the full KQL query (and the fallback) into a references/ file (e.g. references/error_rates.kql) and reference it from Agent 4, keeping only the query's intent and result format inline.

Extract the six self-contained agent prompt templates into a references/agents.md file linked from Step 1, reducing SKILL.md to the orchestration overview.

Consider moving the dashboard output template (Step 3) into a references/template.md so the core procedure stays lean.

Dimension	Reasoning	Score
Conciseness	The body is dense with operationally necessary specifics (team IDs, pipeline IDs, result codes, full KQL) and avoids explaining concepts Claude already knows, fitting 'efficient; minor instances that could be trimmed'; not 5 because the inline KQL block and repeated emphasis callouts add length that could be externalized or tightened.	4 / 5
Actionability	Every agent prompt gives exact tool names, parameters, IDs, a complete executable KQL query, result-code mappings, and output table formats — copy-paste ready and covering the common cases, matching the level-5 anchor.	5 / 5
Workflow Clarity	Steps are clearly sequenced (confirm → launch 6 agents → 90s hard-cutoff collect → present) with explicit checkpoints, failure handling ('FAILED: <reason>', timeout → 'unavailable'), and a Kusto fallback feedback loop; the batch-operation cap does not apply because validation/recovery steps are present, so this fits the level-5 anchor.	5 / 5
Progressive Disclosure	The ~140-line body is well-sectioned but entirely monolithic with no bundle files or references, and content that clearly belongs in separate files (the full KQL query, agent prompt templates) is inlined, matching 'content that should be separate is inline'; not 4 because there are no signaled one-level references at all and the skill exceeds the under-50-line simple-skill exception.	3 / 5
	Total	17 / 20 Passed

Description

86%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states its purpose and provides rich, natural trigger phrases with an explicit 'Triggers on' clause. Its only weak spot is a single-action capability list and a couple of generic trigger terms that slightly raise overlap risk.

Suggestions

Expand the 'what' beyond a single action, e.g. 'Gathers incidents, pipeline health, error rates, and alerts into a consolidated OCE shift status dashboard.'

Qualify the generic triggers ('show dashboard', 'what's going on') with the OCE context inline so they cannot fire for unrelated dashboard skills.

Dimension	Reasoning	Score
Specificity	It names the domain ('OCE shift status dashboard') and one concrete action ('Generate'), but lists no other specific capabilities, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action level 4.	3 / 5
Completeness	It explicitly states both what ('Generate the OCE shift status dashboard') and when ('Triggers on: ...') with concrete trigger phrases, matching the level-5 anchor exactly; not 4 because the 'when' is fully explicit rather than merely adequate.	5 / 5
Trigger Term Quality	It supplies several natural phrases users would actually say ('generate shift dashboard', 'show dashboard', 'shift status', 'what's going on') plus synonyms, matching the comprehensive-coverage anchor; not 4 because the synonym coverage is broad rather than 'a few missing'.	5 / 5
Distinctiveness Conflict Risk	The OCE shift-status niche is mostly distinct, but generic triggers like 'show dashboard' and 'what's going on' create minor overlap risk with other dashboard skills, fitting 'mostly distinct; minor overlap' rather than the minimal-risk level 5.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: microsoft/FluidFramework
Path: .agency/plugins/ff-oce/skills/ff-oce-dashboard/SKILL.md
Commit: ac7d1a3

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.