build-feature

Use whenever building or changing a feature in Skylark — the loop from first failing test to an open, mergeable PR. Covers red-green TDD, making `npm run check` pass, committing on a branch, pushing, and opening a PR. Once the PR is open, hand off to the **babysit-pr** skill (or a dedicated babysitter agent) to shepherd it through CI, reviews, and the merge — a feature isn't shipped until that's done too.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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, actionable workflow doc that sequences a five-step feature loop with concrete commands and explicit validation gates. It is nearly ideal, with only minor over-explanation of well-known TDD mechanics.

Dimension	Reasoning	Score
Conciseness	Largely lean and operational, but it briefly re-explains red-green TDD ('watch it fail, then write the smallest code that makes it pass') and restates gate mechanics Claude could be assumed to know.	4 / 5
Actionability	Provides concrete, copy-paste-ready commands throughout — `npm run check`, `npm run coverage:diff`, `npm run mutate:diff`, `git push -u origin <branch>`, and `gh pr create --fill` — covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced five-step loop with explicit validation checkpoints (commit-gate, landing-gate) and feedback loops ('fix them, don't work around the gate'; 'until it's clean') for error recovery.	5 / 5
Progressive Disclosure	A compact, single-file skill with no need for external references, organized into well-signaled numbered sections; cross-references are to peer skills rather than buried bundle files.	5 / 5
	Total	19 / 20 Passed

Description

88%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 strong, concrete description that pairs an explicit 'Use whenever...' trigger with a comprehensive list of feature-build actions and a clear handoff. It is well-scoped to Skylark with only minor trigger-synonym and sibling-skill overlap gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across the whole loop — red-green TDD, making `npm run check` pass, committing on a branch, pushing, opening a PR, and handing off to babysit-pr — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers 'when' ('Use whenever building or changing a feature in Skylark') and 'what' (the loop from failing test to a mergeable PR with its steps), both with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural phrases like 'building or changing a feature', 'failing test', and 'PR' are present, but a few common synonyms (e.g. 'implement', 'develop', 'merge request') are missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to Skylark with specific gates (commit-gate, landing-gate) and a distinct feature-build niche, with only minor overlap risk against the related babysit-pr skill at the handoff boundary.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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: drufball/skylark
Path: plugins/skylark-builder/skills/build-feature/SKILL.md
Commit: b5a3eaf

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.