CtrlK
BlogDocsLog inGet started
Tessl Logo

pantheon-ai/agents-md

Create and maintain AGENTS.md documentation for simple projects and complex monorepos with deterministic discovery, scoped instruction files, and low-token navigation patterns; use when generating AGENTS.md, updating agent docs, or standardizing AI-facing project guidance.

78

Quality

98%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Quality

Content

100%

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 lean, actionable overview with concrete commands, a sequenced workflow that includes validation, and well-organized references to scoped detail files. Its only weakness is bundle integrity rather than writing structure.

Suggestions

Add the referenced bundle files under references/ (discovery-commands.md, anti-patterns.md, api-template.md, design-system-template.md, database-template.md, testing-template.md, troubleshooting.md) — the References table links to files that do not currently exist in the bundle, so navigation is broken.

Consider replacing the broad detection regex ("workspaces|nx|turbo|pnpm|yarn|...") with a short note pointing to references/discovery-commands.md, keeping the root SKILL.md focused on the decision logic rather than a long alternation.

DimensionReasoningScore

Conciseness

The body is lean with no explanation of concepts Claude already knows, tight WHY/BAD/GOOD anti-patterns, and raw commands without padding. It is not a 2 because there is no unnecessary explanatory prose that could be tightened.

3 / 3

Actionability

It provides fully executable, copy-paste-ready commands ("rg --files", "find . -name AGENTS.md", "bunx markdownlint-cli2", "bun run lint") plus a concrete minimal template. It is not a 2 because the guidance is real and runnable rather than pseudocode or incomplete.

3 / 3

Workflow Clarity

The 5-step workflow pairs each step with an explicit "Output:" line, and a Verification section supplies a validate-then-fix feedback loop. It is not a 2 because validation checkpoints are present and explicit rather than implicit or missing.

3 / 3

Progressive Disclosure

The body is a clear overview with a well-signaled, one-level-deep References table linking to scoped template files. It is not a 2 because references are clearly signaled and content is appropriately split rather than dumped inline.

3 / 3

Total

12

/

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.

The description clearly states concrete capabilities and provides an explicit use-when trigger clause in third person. It is specific, complete, and unlikely to conflict with other skills.

DimensionReasoningScore

Specificity

Quotes multiple concrete actions ("Create and maintain AGENTS.md documentation", "deterministic discovery, scoped instruction files, low-token navigation"), matching the anchor for listing several specific actions. It is not a 2 because the action set is comprehensive rather than a partial naming of the domain.

3 / 3

Completeness

It states what the skill does ("Create and maintain AGENTS.md documentation...") and gives an explicit "use when..." clause answering when to use it. It is not a 2 because the when-trigger is explicit rather than missing or merely implied.

3 / 3

Trigger Term Quality

Natural phrasings a user would say appear ("use when generating AGENTS.md, updating agent docs"), giving good coverage of common variations. It is not a 2 because it supplies several natural trigger terms, not just one generic keyword.

3 / 3

Distinctiveness Conflict Risk

It targets a clear niche (AGENTS.md documentation) with distinct triggers unlikely to overlap other skills. It is not a 2 because the scope is specific to a named doc format rather than broadly overlapping similar skills.

3 / 3

Total

12

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 7 missing

Warning

referenced_paths_exist

Referenced path issues: 14 missing

Warning

Total

14

/

16

Passed

Reviewed

Table of Contents