CtrlK
BlogDocsLog inGet started
Tessl Logo

rules

Use when the user asks about Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/omo-codex/plugin/components/rules/skills/rules/SKILL.md

The canonical home for this skill is rules in code-yeongyu/lazycodex

SKILL.md
Quality
Evals
Security

Quality

Content

78%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 tight, well-organized reference that respects the token budget completely and needs no bundle files. Its main weakness is that it reads as a settings inventory: it lists what exists (sources, env vars) without explaining how they behave or how to use them, leaving the 'matching' behavior unexplained.

Suggestions

Add 1-2 lines explaining rule matching/selection order (which source wins, how file-specific rules are matched), since both the description and the body's "matching file-specific rules" line currently leave this undefined.

Briefly state what each CODEX_RULES_MODE value does (e.g., 'static = inject at SessionStart only') so the env-var list is directly usable rather than just a name inventory.

DimensionReasoningScore

Conciseness

The ~25-line body is lean: every line states plugin-specific facts (injection events, source globs, env var names and value formats) with zero padding and no explanation of concepts Claude already knows. Matches anchor 5 ('Lean and efficient... every token earns its place'); nothing to trim.

5 / 5

Actionability

Concrete details are present (exact env vars like "CODEX_RULES_MODE=both|static|dynamic|off" and exact file globs like ".omo/rules/**/*.md"), but the body is descriptive rather than instructive — it never shows how to configure a source, disable injection, or what the modes do, and rule "matching" (promised in the description) is never explained. Matches anchor 3 ('Some concrete guidance but incomplete; missing key details'); not 4 because no usage example or semantic explanation accompanies the raw settings list.

3 / 5

Workflow Clarity

As a simple single-purpose reference skill with no multi-step process or destructive operations, the content is organized into clearly labeled fact groups (injection behavior, sources, env knobs, legacy fallback). Scored 4 rather than 5 because the matching/selection behavior is named in the description but absent from the body, leaving one ambiguity about how rules are chosen.

4 / 5

Progressive Disclosure

The skill is under 50 lines with no need for external references, and the content is well organized into labeled lists ("Supported project sources", "Supported environment knobs") with no bundle files to reference. Per the simple-skill guideline this matches anchor 5; not 4 because there is no content that should be split out — everything belongs at this level.

5 / 5

Total

17

/

20

Passed

Description

47%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 has a clear, explicit trigger clause with decent natural keywords and a distinctive named domain, but it omits any statement of what the skill actually does. Adding a one-clause 'what' (e.g., explains/configures Codex Rules injection) would move it to the good-example pattern.

Suggestions

Add a 'what' clause stating the skill's capabilities, e.g. "Explains and configures Codex Rules rule injection: what gets injected, when, supported rule sources, and matching behavior."

Include the concrete terms users are likely to mention — file names like CONTEXT.md, .claude/rules, .cursor/rules, and the legacy pi-rules name — to broaden trigger coverage.

Tighten the generic tail ("matching, or environment configuration") into specific phrases such as "rule matching order" or "CODEX_RULES_* environment variables" to reduce overlap with general configuration skills.

DimensionReasoningScore

Specificity

The description names the domain ("Codex Rules behavior, injected project rules, supported rule file locations, matching, or environment configuration") but lists no concrete actions or capabilities — it is a topic list, not an action list. It matches anchor 2 ('Names the domain but actions are minimal or generic'), and not 3 because no 1-2 concrete actions (what the skill actually does) are stated; not 1 because the domain is named specifically rather than being entirely vague.

2 / 5

Completeness

The 'when' is explicit ("Use when the user asks about...") but the 'what' is entirely missing — the description never states what the skill does. This matches anchor 2 exactly ('only 'when' is present without 'what'); it is not 3 because there is no clear 'what' at all, and not 1 because a concrete, explicit trigger clause is present.

2 / 5

Trigger Term Quality

Phrases like "injected project rules", "rule file locations", and "environment configuration" are natural things a user would say when needing this skill. It falls just short of anchor 5 because common synonyms and concrete file names users might mention (e.g., CONTEXT.md, .claude/rules, pi-rules) are absent.

4 / 5

Distinctiveness Conflict Risk

"Codex Rules" is a clearly named niche, making it mostly distinct, but generic tail phrases like "matching, or environment configuration" create minor overlap risk with general config or rules-management skills. Not 5 because of that generic overlap; not 3 because the named plugin scope keeps it well above 'somewhat specific'.

4 / 5

Total

12

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
code-yeongyu/oh-my-openagent
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.