plano-filter-guardrails

Harden Plano filter chains and guardrails. Use for MCP filter setup, prompt guard responses, and safe filter ordering.

Quality

75%

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-filter-guardrails/SKILL.md

Quality

Content

71%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, token-efficient skill body with a clear sequenced checklist and a verification step. Its weaknesses are dangling rule references that resolve to no actual files and incomplete configuration specifics that leave execution details implicit.

Suggestions

Turn the 'Apply These Rules' tokens into explicit, resolvable references (e.g., 'See references/filter-mcp.md') and ship those files under references/, or inline the one-line rule definitions so they are self-contained.

Add concrete values or a minimal example for the MCP filter configuration in step 1 (e.g., type/transport/tool values or a short config snippet) so the guidance is executable rather than directional.

Add an error-recovery loop after the verification step ('If a blocked prompt is allowed, tighten the matching guard and re-verify') to turn the checklist into a full feedback workflow.

Dimension	Reasoning	Score
Conciseness	The body is lean and functional with no concept over-explanation; every line (When-To-Use triggers, rule list, checklist) earns its place and assumes Claude's competence, matching the score-5 anchor.	5 / 5
Actionability	Some guidance is concrete ("Order chain as guards -> rewriters -> enrichment -> output checks", "Configure filter type, transport, and tool"), but the "Apply These Rules" tokens are unexplained, no configuration values are given, and there is no code or command, leaving key execution details missing.	3 / 5
Workflow Clarity	A clear five-step numbered sequence includes an explicit verification step (#5, blocked and allowed test prompts), but it lacks an error-recovery feedback loop (what to do when verification fails), so it stops short of a 5.	4 / 5
Progressive Disclosure	Sections are reasonably organized, but the referenced rules (filter-mcp, filter-guardrails, filter-ordering) are presented as bare backtick tokens with no links or 'See X.md' signaling, and no references/ bundle directory exists to resolve them, so navigation is unclear.	3 / 5
	Total	15 / 20 Passed

Description

78%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 concise, third-person description that clearly answers both what the skill does and when to use it, with strong trigger terms and a distinct niche. Its only real gap is capability specificity, which rests on a single verb rather than a list of concrete actions.

Suggestions

Expand the 'what' with one or two more concrete actions (e.g., 'Harden Plano filter chains and guardrails, configure MCP transport filters, and audit guardrail rejection paths') to lift specificity.

Add a common synonym or file/transport token (e.g., 'MCP server filters' or 'tool allowlists') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Plano filter chains and guardrails") but offers essentially one action verb ("Harden"); the three "Use for" clauses are use-cases rather than additional capabilities, so coverage is not comprehensive enough for a 4.	3 / 5
Completeness	It explicitly states both what ("Harden Plano filter chains and guardrails") and when ("Use for MCP filter setup, prompt guard responses, and safe filter ordering") with concrete trigger phrases, matching the score-5 anchor.	5 / 5
Trigger Term Quality	Natural, niche-appropriate terms like "MCP filter setup", "prompt guard responses", and "safe filter ordering" give good keyword coverage a user would actually say, though a few synonyms/variations are absent.	4 / 5
Distinctiveness Conflict Risk	The "Plano" + "MCP" scope carves a clear niche with distinct triggers, but broader filter/guardrail skills could still cause minor overlap, fitting the score-4 anchor better than 5.	4 / 5
	Total	16 / 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-filter-guardrails/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.