CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

factory-build

Implement a Factory work item's approved plan on its work branch, prove it with the plan's gates, push it, open its change request, and hand it on to review (or to self-review on a board that has a self-review phase)

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 operational skill: fully concrete commands and tool names, a clearly phased workflow with validation and retry loops at every risky step, and no wasted tokens. Its only weakness is that the Hand-off section concentrates five long decision paths plus issue-labeling housekeeping into one monolithic block that a well-signaled reference file could offload.

Suggestions

Split the five Hand-off path bullets and the completed-phase labeling housekeeping into a reference file (e.g. references/handoff.md), keeping a short decision summary in SKILL.md.

Break the very long first Hand-off bullet into shorter sub-steps so the open-change-request path is scannable.

DimensionReasoningScore

Conciseness

The body is dense and operational with no explanations of concepts Claude already knows, and every section earns its tokens; only minor tightening is possible in a few run-on sentences ('Say plainly in your messages which of these are done and which remain, so the judge can tell') and the very long Hand-off bullets.

4 / 5

Actionability

Guidance is near copy-paste ready: concrete commands ('git rev-parse --show-toplevel', 'gh pr list --head <your branch> --state open', the full 'gh label create' invocation with flags), named tools with arguments ('factory_transition_work_item', 'source_control_create_change_request', 'ask_user'), and explicit retry policies ('sleep 20'... 'retry, up to three times') covering all the common paths.

5 / 5

Workflow Clarity

Phases are clearly sequenced (Find the plan → Implement → Verify and push → Hand-off) with explicit validation checkpoints (repository guard before edits and pushes, gates must pass before push, 'A regression test must fail without the fix') and feedback loops for error recovery (rejected transitions: 'read the reason, address it... and retry once'; plan proven wrong → move back to Planning).

5 / 5

Progressive Disclosure

A single-file skill (~60 lines) with well-organized sections and no external references needed, so no bundle is required; however, the five dense Hand-off path bullets push it past the under-50-line simple-skill guideline, and the branch-specific labeling/transition rules are plausible candidates for a reference file.

4 / 5

Total

18

/

20

Passed

Description

75%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.

A highly specific, action-oriented description that clearly states what the skill does across the full build-and-hand-off lifecycle. Its one structural weakness is the absence of any explicit 'when to use' trigger clause, which limits discoverability despite the strong 'what'.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a Factory work item's plan has been approved and the card enters its build phase'.

Include a few natural synonym terms users might say, such as 'pull request' or 'PR' alongside 'change request'.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Implement a Factory work item's approved plan', 'prove it with the plan's gates', 'push it', 'open its change request', 'hand it on to review' — giving comprehensive coverage of the skill's behavior.

5 / 5

Completeness

The 'what' is explicit and multi-part, but there is no 'Use when...' clause or equivalent trigger guidance, which caps completeness at 3.

3 / 5

Trigger Term Quality

Good keyword coverage of the domain's natural terms ('work item', 'approved plan', 'work branch', 'change request', 'self-review'), but a few natural variants users might say (pull request, PR, ticket) are missing.

4 / 5

Distinctiveness Conflict Risk

The description is narrowly scoped to the Factory workflow with its own tool vocabulary ('Factory work item', 'change request', 'self-review phase'), giving it a clear niche with minimal conflict risk against other skills.

5 / 5

Total

17

/

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/factory-build/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.