CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

rules

Maintains project .codex/rules and the AGENTS.md rule index. Explicit user invocation only.

Quality

81%

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

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.

The body is an exemplary lean, imperative instruction skill: specific commands, exact table structure, and an explicit post-change validation gate with failure conditions. Weaknesses are the missing error-recovery loop after validation failure and the orphaned `scripts/rules.sh` bundle file that the skill never tells Claude how or when to use.

Suggestions

Reference the bundled helper in the workflow, e.g. a step or note like "Use `scripts/rules.sh <read|check|create|list|validate>` for inventory and validation" so the 340-line bundle script is discoverable.

Add a feedback loop after the step-6 validation: state what to do when validation fails (fix the index/rule, re-run the inventory, re-validate) to close the recovery gap.

Show one example index row (Rule | Load when | Purpose) and reconcile the "synchronize" mode in step 2 with the Modes section list.

DimensionReasoningScore

Conciseness

The ~30-line body is dense and padded nowhere: it explains no concepts Claude already knows and states only non-obvious facts (e.g., "The index makes rules discoverable; it does not auto-load their bodies"). Every token earns its place, matching the lean anchor.

5 / 5

Actionability

Concrete, executable guidance is present: `rg --files .codex/rules | sort`, `$brewtools:text-optimize -l`, exact index columns (`Rule`, `Load when`, `Purpose`), and precise paths. It falls short of fully copy-paste-ready because no example rule file or index table row is shown, and step 2 names a "synchronize" mode that the Modes section does not list.

4 / 5

Workflow Clarity

The 7-step sequence is clear with an explicit validation checkpoint ("Fail validation when any rule path is missing from the root index, any indexed path is stale, or a rule body was duplicated") and a semantic-comparison gate before applying optimized patches. Not 5 because no error-recovery loop is described after "fail validation" — what to do on failure is left implicit.

4 / 5

Progressive Disclosure

The body is well-sectioned and appropriately short, but the bundle contains `scripts/rules.sh`, a 340-line helper script, that the body never mentions — scored against the actual bundle structure, this orphaned reference leaves navigation incomplete. Not 4 because an entirely unreferenced bundle script is more than a minor organization gap; not 2 because nothing that belongs in a separate file is inlined.

3 / 5

Total

16

/

20

Passed

Description

73%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 concise, honest, and clearly niche-scoped, with a correct third-person voice and an explicit invocation gate. Its main weakness is thin capability coverage — one generic verb ("Maintains") where the modes list (create, improve, review, sync) would be more specific — and the absence of positive trigger phrases.

Suggestions

Enumerate the concrete operations in the description, e.g. "Creates, improves, reviews, and syncs project .codex/rules files and the AGENTS.md rule index" instead of the single generic verb "Maintains".

Add a positive trigger clause alongside the invocation gate, e.g. "Use when the user explicitly asks to add, update, review, or inventory project rules or the AGENTS.md index."

DimensionReasoningScore

Specificity

"Maintains" is a single generic verb applied to two concrete artifacts ("project .codex/rules", "the AGENTS.md rule index"), matching the anchor for 1-2 concrete actions without comprehensive coverage; the body's create/improve/review/sync capabilities are not enumerated, so it does not reach anchor 4.

3 / 5

Completeness

Both parts are present: a clear what ("Maintains project .codex/rules and the AGENTS.md rule index") and an explicit when ("Explicit user invocation only"). Not 5 because the when-clause is a restriction rather than concrete positive trigger phrases; not 3 because the when is explicitly stated, not merely implied.

4 / 5

Trigger Term Quality

"rules", "AGENTS.md", ".codex/rules", and "rule index" are natural terms users of this tooling would say, including concrete file paths — good coverage. It falls short of anchor 5 because no synonyms or variations (e.g., conventions, instructions, rule creation/sync) appear.

4 / 5

Distinctiveness Conflict Risk

"project .codex/rules", "the AGENTS.md rule index", and Codex-specific terminology carve out a clear niche with distinct triggers and minimal conflict risk with any generic skill.

5 / 5

Total

16

/

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

kochetkov-ma/claude-brewcode

Path

.codex/plugins/brewcode/skills/rules/SKILL.md

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.