herdr-manager-query

Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed remote-only Review Manager records through the plugin's stable public CLI.

Quality

73%

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 ./.mastracode/skills/herdr-manager-query/SKILL.md

Quality

Content

88%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 a well-structured, highly actionable, and concisely written workflow with strong validation and error-handling discipline throughout. Its main limitation is that all detail lives inline in one file with no progressive disclosure to supporting reference files.

Suggestions

Extract the detailed review-metadata field reference (reviews.events, comments, unresolved_threads, diff fields) into a references/ file and link to it from SKILL.md to shorten the main body.

Consider moving the capability-negotiation and schema-validation Python snippets into a scripts/ helper so the main workflow shows intent rather than boilerplate.

Add a brief one-line 'When to use' pointer at the top of the body that mirrors the description's trigger guidance.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful — it explains only Herdr-specific concepts (protocol/schema versions, manager inventory fields) Claude would not know and avoids padding generic concepts — with only minor prose that could be trimmed, fitting the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	Provides fully executable, copy-paste-ready shell plus Python heredoc blocks for plugin discovery, capability negotiation, querying, and materialization, covering the common workflow cases as the level-5 anchor requires.	5 / 5
Workflow Clarity	Multi-step processes (discover → negotiate capabilities → query → filter → recommend → materialize) are clearly sequenced with explicit validation checkpoints (protocol_version, schema_version, error summaries, stale-head rejection) and feedback loops for the destructive materialization operation, matching the level-5 anchor.	5 / 5
Progressive Disclosure	Content is organized into clearly headed sections with no nested references and everything kept one level deep, but the ~150-line monolithic file keeps all inline code and field reference detail in SKILL.md rather than splitting detail into bundle files, which is good but sits just below the ideally-split level-5 anchor.	4 / 5
	Total	18 / 20 Passed

Description

58%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 conveys concrete, distinct capabilities tied to a niche Herdr tooling domain, but it lacks an explicit 'Use when...' trigger clause and leans heavily on product jargon, which limits trigger quality and completeness.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when the user asks what to review or work on next, or wants to materialize a Review Manager PR').

Soften product jargon with common user-facing synonyms (e.g., 'pull request review recommendations', 'work queue') so the description reads as something a user would naturally say.

Tighten the single long sentence into a crisp capability statement plus a trigger sentence to improve scannability.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Query the authoritative global Herdr... inventory", "recommend actionable PR work", and "explicitly materialize confirmed remote-only Review Manager records" — with only minor coverage gaps, fitting the 'several specific actions' anchor rather than the fully comprehensive level 5.	4 / 5
Completeness	The 'what' is clear (query, recommend, materialize) but there is no "Use when..." clause or equivalent explicit trigger guidance; per the rubric a missing 'when' caps completeness at 3.	3 / 5
Trigger Term Quality	Contains some relevant domain keywords ("PR work", "Review Manager", "Work Manager", "materialize") but leans on product-specific jargon and omits common user-facing variations a requester might naturally say, matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The Herdr-specific scope ("Herdr Review and Work Manager inventory", "Review Manager records", "the plugin's stable public CLI") gives it a clear niche with minimal conflict risk, though "recommend actionable PR work" leaves minor overlap with general PR-review skills, so it sits just below the level-5 anchor.	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: mastra-ai/mastra
Path: .mastracode/skills/herdr-manager-query/SKILL.md
Commit: 748d4ed

Reviewed: 2 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.