plano-agent-skills

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

Quality

56%

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

62%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.

The body is well-structured, lean, and offers a clear workflow with explicit defaults and risky-pattern callouts, but it lacks executable worked examples and its reference structure is only nominal — the referenced files are not present as a bundle, so detail stays inlined rather than genuinely offloaded.

Suggestions

Add at least one copy-paste-ready worked example (a minimal `config.yaml` snippet showing `default: true`, `$ENV_VAR`, guardrails-before-enrichment ordering) to lift actionability.

Turn the closing 'validation checklist' into an explicit validate->fix->retry feedback loop with a gating step to reach workflow_clarity 5.

Actually offload the detailed rulebook to the referenced `skills/AGENTS.md` and surface it as a clearly signaled one-level reference, or create the `references/` bundle so progressive disclosure is real rather than nominal.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — concrete defaults like `version: v0.3.0`, exactly one `default: true`, `$ENV_VAR`, `host.docker.internal`, and commands `planoai up --with-tracing` / `planoai trace` earn their tokens with minimal padding. Not a 5 because 'How To Use' and 'Operating Workflow' partially restate the same classification/routing steps, and 'Response Style' is somewhat advisory.	4 / 5
Actionability	It gives concrete defaults and named CLI commands, but the guidance is high-level instruction ('Apply the smallest correct change', 'Classify the request by scope') rather than copy-paste executable code or a worked config snippet; the only concrete tokens are flag names and one env-var pattern. Not a 2 because specific commands/defaults are present; not a 4 because there are no complete runnable examples or before/after diffs.	3 / 5
Workflow Clarity	The 'Operating Workflow' is a clearly numbered sequence (identify area -> smallest change -> preserve defaults -> debug with traces -> return diffs+checklist) with an explicit validation checkpoint ('Return concrete diffs and a short validation checklist') and risky-pattern callouts. Not a 5 because the validation step is a single mention rather than a validate->fix->retry feedback loop with gating, and 'When To Use' / 'How To Use' overlap with it.	4 / 5
Progressive Disclosure	There is clear section structure (When To Use, How To Use, Operating Workflow, Response Style, References) and two one-level references (`skills/AGENTS.md`, a GitHub repo URL), but a `references/` / `scripts/` / `assets/` bundle does not exist, so the inlined rule-like content (security defaults, filter ordering) that plausibly belongs in AGENTS.md is inlined here rather than split out. Not a 4 because the navigation/signaling is thin and detail is not actually offloaded to the referenced files in the bundle.	3 / 5
	Total	14 / 20 Passed

Description

51%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.

The description clearly conveys scope and area coverage tied to a named product (Plano), but it lacks an explicit 'Use when...' trigger clause and leans on domain enumeration rather than natural user phrasing, which caps trigger quality and completeness at 3.

Suggestions

Add an explicit 'Use when...' trigger clause listing concrete user phrasings (e.g., 'Use when validating Plano config.yaml, debugging routing traces, or hardening guardrails').

Reframe the verb from generic 'best practices for building' toward concrete actions the skill performs ('Validates Plano config, designs listener routing, hardens guardrails').

Include natural synonyms users say ('fix my config', 'routing is broken', 'deploy Plano') to raise trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes 'building agents and agentic applications' plus a concrete enumeration ('configuration, routing, orchestration, guardrails, observability, and deployment') naming 6 domains, but the actions ('building', 'best practices') are generic rather than discrete operations; it names the domain and 1-2 actions but is not comprehensive on concrete actions.	3 / 5
Completeness	It clearly states the 'what' (best practices for building Plano agents across named areas) but the 'when' is only weakly implied — there is no explicit 'Use when...' clause or trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	The description surfaces domain nouns a user might invoke ('config', 'routing', 'guardrails', 'deployment') but omits the natural phrasings and synonyms a user would actually say ('fix my Plano config', 'routing failing', 'deploy Plano'), and there is no 'Use when...' trigger clause. Not a 2 because the listed terms are plausibly user-spoken; not a 4 because common variations and an explicit trigger are missing.	3 / 5
Distinctiveness Conflict Risk	The 'Plano' product qualifier plus the enumerated areas give it a clear niche and low conflict risk with unrelated skills; minor overlap risk exists with potential section-specific Plano sub-skills (e.g. plano-routing-model-selection). Mostly distinct; not a 5 because the broad 'building agents and agentic applications' framing could still overlap with adjacent Plano skills.	4 / 5
	Total	13 / 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: 003c36a

Reviewed: 3 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.