Tessl • The management layer for AI agent skills

SkillPublic

maintainer

Handle public Plate/Slate GitHub work, such as issue drafts, Slate issues, PRs, security and the queue scan, and hold the public truth gate. Triage of udecode/plate and udecode/plate-private issues runs the Triage playbook.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/maintainer/SKILL.md

Quality

Content

67%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.

This is a strong instruction-only coordinator skill: concrete gh/pnpm commands, a routing table, explicit validation and authority gates, and a clean mode structure with real one-level reference files. Its weaknesses are verbosity — dense multi-clause policy prose with some repeated authority rules — and policy detail (replay/retest rules) inlined in SKILL.md that belongs in a reference. Tightening the prose and moving the detailed proof rules out would raise both conciseness and progressive disclosure.

Suggestions

Rewrite the long multi-clause policy sentences (intro paragraph, replay requirements) as short imperatives or a checklist; e.g. split "It decides fit, priority, routing, authority and proof for what it keeps" into single-rule bullets.

Consolidate authority rules that appear in both the Intake and Authority sections into one place and cross-reference it.

Move the detailed replay/fingerprint and Reporter Retest Invalidation procedures into a reference file (e.g. references/proof.md) and keep only the one-line truth gate in SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept re-teaching, but many sentences pack multiple rules into heavy nominalized prose ("It decides fit, priority, routing, authority and proof for what it keeps") and authority rules recur across Intake, Authority, and the mode sections. It could be meaningfully tightened without losing content, matching the "mostly efficient but could be tightened" anchor.	3 / 5
Actionability	Provides concrete executable commands (gh api security-advisories with a --jq filter, gh pr list, pnpm triage queue, gh issue list), exact file paths (docs/triage/issues.tsv, CONTRIBUTING.md, SECURITY.md), and a per-item routing table. Minor gaps like "verify its live state and authority" stay high-level, keeping it below the fully copy-paste-ready bar.	4 / 5
Workflow Clarity	The queue mode is a numbered sequence with explicit stop and blocker handling ("If gh auth or network is blocked, record the blocker and stop"), and validation checkpoints are present throughout — re-reading live GitHub before any mutation, the pushed-ref replay truth gate, and the numbered reporter-retest recovery. Some modes (prs, issue-url routing) are prose decision rules rather than stepwise sequences, so it sits just below the checklist-complete anchor of 5.	4 / 5
Progressive Disclosure	The body is an overview coordinator with well-signaled, verified one-level-deep references (references/issue-draft.md, slate-issue.md, security-hotfix.md all exist) plus separated scripts/ and assets/. It stops short of 5 because long policy blocks (the replay requirements, Reporter Retest Invalidation) are inlined in SKILL.md rather than referenced out, and several links (../../playbooks/*.md) point outside the skill bundle.	4 / 5
	Total	15 / 20 Passed

Description

66%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 is specific and distinctive within its maintainer niche, naming concrete work items and target repositories. Its main weakness is the complete absence of "when to use" trigger guidance, which caps completeness, and a jargon phrase ("public truth gate") that obscures a capability. Adding an explicit "Use when..." clause with natural trigger phrases would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to maintain udecode/plate, review or merge PRs, draft issues, handle security advisories, or scan the issue/PR queue."

Replace jargon like "hold the public truth gate" with a plain capability statement such as "verifies fixes with a clean replay on the pushed ref before allowing 'fixed' or 'completed' claims".

Include common synonyms users would say — "pull requests", "bug reports", "repo maintenance", "triage" — to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names several concrete work items — "issue drafts, Slate issues, PRs, security and the queue scan" — anchored to specific repos. It falls short of 5 because the lead verb "Handle public... GitHub work" is generic and "hold the public truth gate" is internal jargon rather than a concrete action; it is above 3 because coverage goes beyond 1-2 actions.	4 / 5
Completeness	The "what" is clear (issue drafts, Slate issues, PRs, security, queue scan), but there is no "Use when..." clause or equivalent explicit trigger guidance; the Triage sentence is a delegation rule, not a usage trigger. Per the judging guidelines this caps completeness at 3.	3 / 5
Trigger Term Quality	Includes natural terms a maintainer would say — "PRs", "security", "triage", "Slate", "queue scan" — plus the udecode/plate repo names. A few common variations are missing ("pull request", "bug report", "repo maintenance"), keeping it below 5 but above the sparse keyword coverage of 3.	4 / 5
Distinctiveness Conflict Risk	The Plate/Slate and udecode/plate naming creates a clear niche and it explicitly distinguishes itself from the Triage playbook, but broad terms like "PRs" and "security" leave minor overlap risk with generic PR-review or security skills, so it is not the minimal-conflict case of 5.	4 / 5
	Total	15 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 4 suspicious	Warning

	Total	12 / 16 Passed

Repository: udecode/plate
Path: .agents/skills/maintainer/SKILL.md
Revision: f0c616a

Reviewed: 3 days ago

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.

maintainer

Table of Contents

Is this your skill?