CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

configure-factory-rules

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

59

Quality

74%

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

81%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 unusually dense, well-structured set of domain-specific instructions: it names exact APIs, source files, and validation steps, and closes with an explicit verify checklist. Its main gaps are code/commands that stop just short of copy-paste ready and a length that could benefit from splitting deep-dive sections into reference files. Overall a strong, high-signal instruction skill.

Suggestions

Provide the literal test/typecheck/build commands in "Verify the change" (e.g., the actual package-manager invocations) so the final steps are copy-paste executable rather than descriptive.

Consider moving the deep-dive sections ("Configure board phase semantics", "Change a built-in handler" source-path inventory) into a reference file, keeping SKILL.md as a leaner overview with clearly signaled one-level-deep links.

Tighten a few stacked caveat sentences (e.g., the long paragraph on default arrival behavior and Platform credentials) by splitting or tabulating the constraints to cut re-read cost.

DimensionReasoningScore

Conciseness

The body is dense and imperative with almost no padding or explanation of concepts Claude already knows — every sentence carries non-inferable constraints like "`initialPhase` must be resting" and "a function replaces the default, `null` disables that event's handler". A few stacked caveat sentences could still be tightened, so it sits at anchor 4 rather than anchor 5's every-token-earns-its-place.

4 / 5

Actionability

Concrete pointers abound (specific source paths like `src/boards/work-tool-rules.ts`, exact APIs like `includeDefaultBoards: false` and `rules[event]`) and two real TypeScript snippets are included, but the snippets are not fully wired and the verify steps name commands ("Run the narrow Factory rule tests and package typecheck") without literal invocations — anchor 4 (mostly executable, minor gaps) rather than anchor 5's copy-paste-ready coverage.

4 / 5

Workflow Clarity

Sequences are explicit and validated: "Find the configuration" (search, read existing config and its tests before editing, then edit), a numbered 5-step "Change a built-in handler" procedure, and a "Verify the change" checklist with explicit validation steps (test undefined/accepted/rejected paths, run rule tests, typecheck, Web build) plus failure guidance ("Do not weaken tests or bypass the transition service to make a policy work"). This matches anchor 5's explicit validation, feedback loop, and checklist character.

5 / 5

Progressive Disclosure

No bundle files exist, and the ~120-line body is well organized with clear section headers and explicitly signaled pointers to deployment source files (e.g., "Read `src/boards/transition-policy.ts` for the public contract"). It exceeds the under-50-line guideline and some deep-dive sections (phase semantics, handler replacement) could plausibly be split into reference files, so anchor 4 (good structure, minor organization gaps) fits better than 5.

4 / 5

Total

17

/

20

Passed

Description

53%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 specific and distinctive within its niche, clearly naming the rule types the skill configures. Its weaknesses are the single-action framing, missing product nouns and synonyms for trigger matching, and a complete absence of any "when to use" guidance. Adding an explicit use-when clause with natural trigger phrases would lift the two heaviest-weighted dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants to change Factory rule behavior, customize board lifecycle or transition policy, or override GitHub/Linear integration event handlers" — this directly addresses the missing 'when' (completeness is the highest-weighted dimension).

Include natural product and entity names (Factory, Mastra, boards, GitHub, Linear) and their variations as trigger terms so users' real phrasing matches (trigger_term_quality).

Express more than one concrete action (e.g., "Configure ... , replace built-in handlers, and set transition policies") to move specificity from one enumerated verb toward several distinct actions.

DimensionReasoningScore

Specificity

The description names a specific domain and enumerates concrete rule objects ("board-owned lifecycle, policy, phase-semantics, and tool-result rules, plus integration event rules"), but offers only a single action verb ("Configure"), fitting anchor 3 (domain plus 1-2 concrete actions) rather than anchor 4's several distinct actions.

3 / 5

Completeness

The "what" is clear and specific (configure lifecycle, policy, phase-semantics, tool-result, and integration event rules), but there is no "Use when..." clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3 (anchor 3: clear what, when missing).

3 / 5

Trigger Term Quality

Terms like "Configure", "rules", "policy", and "lifecycle" are natural for users of this system, but common variations and product nouns (Factory, Mastra, GitHub, Linear) are absent and jargon like "phase-semantics" dominates, matching anchor 3 (some relevant keywords, missing variations/synonyms) rather than anchor 4.

3 / 5

Distinctiveness Conflict Risk

Phrases like "board-owned lifecycle", "phase-semantics", and "integration event rules" carve a distinct niche with low wrong-skill risk, but semi-generic terms ("lifecycle", "policy", "integration event rules") and the absent product name leave minor overlap risk with closely related configuration skills, matching anchor 4 rather than anchor 5.

4 / 5

Total

13

/

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

Path

mastracode/factory/factory-skills/configure-factory-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.