plano-agent-skills

Best practices for building agents and agentic applications with Plano, including configuration, routing, orchestration, guardrails, observability, and deployment.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/plano-agent-skills/SKILL.md

Quality

Content

75%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 well-structured, appropriately concise umbrella skill: concrete rules and CLI commands, clearly sequenced workflows with an explicit validation deliverable, and clean section organization. The main gap is that its single deep reference ('skills/AGENTS.md') does not exist in the bundle, so the promised detail is not actually reachable.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanations of concepts Claude already knows; concrete rules are stated as compact one-liners ('secrets via $ENV_VAR substitution only', 'guardrails before enrichment in filter chains'). Not a 5 because a few self-evident meta-instructions ('Prefer actionable edits over generic advice', 'Keep examples minimal and production-viable') could be trimmed without losing information.	4 / 5
Actionability	Contains concrete, executable guidance: exact values and commands ('version: v0.3.0', 'planoai up --with-tracing', 'planoai trace', 'host.docker.internal for host services', 'exactly one default: true model provider'). Not a 5 because there are no actual config snippets or example diffs — the common cases are described but not shown, leaving minor gaps for copy-paste execution.	4 / 5
Workflow Clarity	Both 'How To Use' and 'Operating Workflow' are clearly sequenced numbered lists, and validation appears as an explicit terminal step ('Return concrete diffs and a short validation checklist') plus trace-first debugging guidance. Not a 5 because checkpoints within steps are implicit rather than embedded validate-and-retry loops (e.g., no 'verify config passes planoai validation before delivering the diff').	4 / 5
Progressive Disclosure	Well-organized sections under 50 lines with a clearly signaled one-level-deep reference to the full rulebook ('Full rulebook: skills/AGENTS.md'), matching anchor 4. Not a 5 because the referenced 'skills/AGENTS.md' does not resolve within the skill bundle (no references/ directory exists), so navigation depends on an unverifiable external path, and the umbrella design pushes detail to sibling skills that are also absent here.	4 / 5
	Total	16 / 20 Passed

Description

61%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 middling description: it clearly scopes the domain and includes a solid set of domain keywords anchored by the distinctive product name 'Plano', but it describes topic areas rather than concrete actions and completely lacks a 'Use when...' trigger clause. Adding explicit trigger guidance and 1-2 concrete actions would lift the two 3-score dimensions.

Suggestions

Append an explicit trigger clause, e.g., 'Use when validating or fixing Plano config.yaml, designing model/provider routing, hardening guardrail filter chains, or debugging routing with planoai traces.'

Convert the topic-area list into concrete actions — e.g., 'Validate config.yaml, select model providers and fallbacks, order guardrail filters, debug routing with traces, and run production readiness checks.'

Include natural variations users would actually say ('config.yaml', 'planoai CLI', 'tracing', 'debug routing') to raise trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	The description names the domain ('building agents and agentic applications with Plano') and enumerates six scope areas ('configuration, routing, orchestration, guardrails, observability, and deployment'), but these are topic nouns rather than concrete actions — the opening phrase 'Best practices for building' is generic and no specific verbs/tasks (e.g., 'validate config.yaml', 'debug routing with traces') appear. It sits between anchor 3 and 4 but is not 'noticeably above the midpoint' since nothing listed is an actual action.	3 / 5
Completeness	The 'what' is clear (best practices for building Plano agents across six areas), but there is no 'Use when...' clause or equivalent explicit trigger guidance — 'when' is entirely absent, not even weakly implied. Per the judging guidelines, a missing 'Use when' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage: 'Plano', 'agents', 'configuration', 'routing', 'orchestration', 'guardrails', 'observability', 'deployment' are terms a user working in this domain would plausibly say. Falls short of anchor 5 because natural variations and concrete artifacts users would mention are missing (e.g., 'config.yaml', 'planoai CLI', 'tracing', 'debugging', 'model provider').	4 / 5
Distinctiveness Conflict Risk	The product name 'Plano' establishes a clear niche with minimal conflict risk against non-Plano skills. However, as an umbrella skill spanning six areas, it has real overlap risk with closely related section-specific Plano skills (the body itself references 'plano-routing-model-selection'), matching anchor 4 ('mostly distinct; minor overlap risk with closely related skills') rather than 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: katanemo/plano
Path: skills/plano-agent-skills/SKILL.md
Commit: 72002a6

Reviewed: 20 hours 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.