CtrlK
BlogDocsLog inGet started
Tessl Logo

configure-factory-rules

Configure board-owned lifecycle, policy, phase-semantics, and tool-result rules, plus integration event rules

58

Quality

66%

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 ./mastracode/factory/factory-skills/configure-factory-rules/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 strong, information-dense skill body: concrete code examples, exact source-file locations for every rule type, and explicit verification steps with sibling-safety checks. The main weaknesses are mild redundancy across sections, verification commands that are named rather than given verbatim, and a monolithic 120-line document where some sections could be split into reference files.

Suggestions

Give the verification steps as exact commands (e.g. the actual test-filter invocation and build command) so 'Run the narrow Factory rule tests' is copy-paste ready.

Deduplicate cross-section constraints (inheritance rules, 'do not invent replacement APIs') into a single 'Limits' section to trim tokens.

Move the built-in handler location map and the custom-board execution journey detail into a reference file, keeping SKILL.md as the overview.

DimensionReasoningScore

Conciseness

The body is dense, constraint-driven prose with no explanation of concepts Claude already knows, and every section carries deployment-specific information. Not 5 because some constraints are repeated across sections ("custom boards inherit nothing" appears twice; "Do not invent built-in replacement APIs" recurs) and the stacked 'do not' sentences could be consolidated.

4 / 5

Actionability

Provides executable TypeScript snippets (PlatformGithubIntegration/LinearIntegration rules, a complete BoardTransitionPolicy example), concrete source-file paths for every handler location, and specific verification commands. Not 5 because the test/build steps ('Run the narrow Factory rule tests and package typecheck', 'Run the Web build') are not exact copy-paste invocations, and a substantial share of guidance is prohibitive rather than executable.

4 / 5

Workflow Clarity

Clear numbered sequences for finding the configuration (read existing rules and tests before editing), changing built-in handlers (find/read, decide on preserved behavior, use typed fields, return shape, idempotency key), and an explicit 'Verify the change' section with validation steps including testing unaffected siblings. Not 5 because there is no explicit fix-and-re-run feedback loop after validation; not 3 because checkpoints are present and explicit throughout.

4 / 5

Progressive Disclosure

Well-organized into focused sections with clear headers, and repo source references (src/boards/transition-policy.ts, src/boards/work-tool-rules.ts) are clearly signaled and one level deep. Not 5 because at ~120 lines spanning six topics, sections like 'Execute a custom board' and the built-in handler location map would fit better in separate reference files; not 3 because structure and navigation are good and nothing is buried.

4 / 5

Total

16

/

20

Passed

Description

58%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 states a specific, multi-category 'what' in third person without fluff, but it has no 'when to use' trigger guidance and leans on internal jargon ('phase-semantics', 'tool-result rules') rather than phrases a user would naturally say. It is a solid but incomplete description whose main gaps are the missing trigger clause and natural keyword coverage.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to change Factory board rules, transition policy, phase kinds, tool-result rules, or GitHub/Linear integration event handlers.'

Replace or supplement internal jargon with natural user phrasings: 'board lifecycle handlers', 'phase kinds', 'GitHub/Linear event handlers' instead of 'phase-semantics' and 'tool-result rules'.

Include natural variations users might say, such as 'Factory policy', 'change board rules', 'disable a Linear event handler', so the skill triggers on real requests.

DimensionReasoningScore

Specificity

Names five concrete rule categories ("board-owned lifecycle, policy, phase-semantics, and tool-result rules, plus integration event rules") with a clear domain, but only a single action verb ("Configure"), so it falls short of the comprehensive multi-action anchor at 5.

4 / 5

Completeness

The 'what' is clear (configure these rule categories), but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines. It is not 4 because the 'when' is entirely absent rather than merely implicit.

3 / 5

Trigger Term Quality

Some relevant natural terms are present ("rules", "policy", "lifecycle", "integration event"), but "phase-semantics" and "tool-result rules" are internal jargon users would not naturally say, and common variations or synonyms are missing. Not 2 because the keywords are domain-relevant rather than generic; not 4 because few genuinely natural user phrasings appear.

3 / 5

Distinctiveness Conflict Risk

"Board-owned", "phase-semantics", and "integration event rules" carve a distinct niche with minimal conflict risk against other skills. Not 5 because standalone words like "rules" and "policy" remain generic and could overlap with other configuration skills.

4 / 5

Total

14

/

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
mastra-ai/mastra
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.