CtrlK
BlogDocsLog inGet started
Tessl Logo

200-agents-md

Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions; Generate contributor instructions for Java agents; Document repository conventions in AGENTS.md. Part of Plinth Toolkit

69

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured overview with a clean sequenced workflow and a real, single-level reference, but it carries redundancy with the frontmatter and pushes the actionable detail into the referenced file. Tightening the body and surfacing a few concrete generation patterns would lift the weaker dimensions.

Suggestions

Remove the redundant restatement: the intro paragraph, 'What is covered' bullets, and 'When to use this skill' overlap the frontmatter description — keep only what adds new information.

Surface one or two concrete AGENTS.md generation patterns inline (e.g., a minimal section template or a sample ✅/⚠/🚫 boundary block) instead of deferring all actionable detail to the reference.

Merge the duplicate 'Reference' and 'Workflow Step 2' pointers into a single clearly signaled link to references/200-agents-md.md to avoid repeating the same guidance.

DimensionReasoningScore

Conciseness

The intro paragraph, "What is covered in this Skill?" bullets, and "When to use this skill" list largely restate the frontmatter description and each other, so the body could be tightened even though it avoids explaining concepts Claude already knows.

2 / 3

Actionability

Concrete elements exist (read references/200-agents-md.md, gather role/tech-stack/commands/boundaries, emit ✅/⚠/🚫 boundaries) but the actual generation patterns are deferred to the reference, leaving the body's own guidance high-level rather than copy-paste ready.

2 / 3

Workflow Clarity

Four clearly sequenced steps with explicit checkpoints ("BEFORE STARTING", "BEFORE APPLYING") and edge-case stops (ask on ambiguity, report missing context, confirm conflicts) provide a clear, recoverable flow for this non-destructive task.

3 / 3

Progressive Disclosure

The body is a concise overview with a well-signaled, one-level-deep reference link to references/200-agents-md.md (a real file in the bundle), matching the clear-overview-with-single-level-reference anchor.

3 / 3

Total

10

/

12

Passed

Description

100%

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 strong, well-scoped description that clearly states capability, gives an explicit Use-when trigger, and enumerates natural request phrasings without over-claiming. No changes needed.

DimensionReasoningScore

Specificity

Lists multiple concrete coverage areas — "project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries" plus "a modular, step-based interactive process" — matching the multiple-specific-actions anchor.

3 / 3

Completeness

Explicitly answers what (generate an AGENTS.md file for a Java repository covering the listed areas) and when ("Use when you need to generate..." plus "This should trigger for requests such as..."), satisfying both halves.

3 / 3

Trigger Term Quality

Supplies natural user-style triggers ("Create AGENTS.md; Update AGENTS.md file; Add agent instructions; Generate contributor instructions for Java agents; Document repository conventions in AGENTS.md") giving good coverage of phrases users would actually say.

3 / 3

Distinctiveness Conflict Risk

Scoped to AGENTS.md generation for Java repositories with distinct triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
jabrena/plinth
Reviewed

Table of Contents

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.