CtrlK
BlogDocsLog inGet started
Tessl Logo

adding-a-feature

The four-area checklist every new feature must complete. Use when adding any feature, integration, or capability to ensure the agent and UI stay in parity.

64

Quality

80%

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 ./community-templates/account-expert/.agents/skills/adding-a-feature/SKILL.md

The canonical home for this skill is adding-a-feature in BuilderIO/agent-native

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 high-quality, highly actionable instruction skill: concrete APIs, one copy-paste code example, worked examples per app type, an anti-patterns section, and an explicit verification checklist. The main improvement opportunities are trimming the Area 2 digressions toward the already-referenced sibling skills and adding per-area or failure-path verification guidance.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with essentially no explanation of concepts Claude already knows, and every sentence carries a project-specific rule. The Area 2 section sprawls across provider integrations, credentials, attachments, and dependency weight — tangents that could be trimmed or fully delegated to the referenced skills.

4 / 5

Actionability

Guidance is fully concrete: exact APIs (useActionQuery, defineAction, http: { method: "GET" }, useChangeVersions(["dashboards", "action"])), a copy-paste-ready tsx snippet, explicit config keys (placeholderData: (prev) => prev), and runnable checks (pnpm action view-screen). Specific examples cover the common cases.

5 / 5

Workflow Clarity

"work through these four areas in order" gives a clear numbered sequence, and the Verification section provides an explicit 6-item checklist. It falls short of the top anchor because checkpoints come only at the end rather than per area, and there is no fix-and-recheck guidance when a verification question fails.

4 / 5

Progressive Disclosure

Good structure with well-labeled sections, worked example tables, anti-patterns, and clearly signaled one-level-deep references to sibling skills (real-time-sync, external-agents, sharing, performance §9, plus a Related Skills index). Some Area 2 digressions (provider API patterns, credential preflight) are inlined when the referenced skills could carry that detail.

4 / 5

Total

17

/

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.

A strong, concise description with an explicit 'Use when' trigger clause and a clear statement of purpose. Its one weakness is specificity: it describes the artifact ("four-area checklist") without naming any of the four areas or the concrete actions involved.

Suggestions

Name the four areas in the description (UI component, action, skills/AGENTS.md, app-state sync) so a reader can judge relevance at a glance, e.g. 'Every new feature must update four areas: UI component, agent-callable action, skills/AGENTS.md instructions, and app-state sync.'

Add a common trigger variation such as 'new feature' or 'building a feature' alongside 'adding any feature, integration, or capability' to broaden natural keyword coverage.

Briefly state the payoff term users may search on — e.g. 'agent/UI parity' already appears; consider also 'so the agent can do everything the UI can do' to sharpen the what.

DimensionReasoningScore

Specificity

"The four-area checklist every new feature must complete" names the domain but never lists a concrete action — not even the four areas themselves (UI, action, skills, app-state sync). This matches the anchor 'names the domain but actions are minimal or generic'; it is not a 3 because no 1-2 concrete actions are stated.

2 / 5

Completeness

The description explicitly answers both: what ("The four-area checklist every new feature must complete" to keep "the agent and UI ... in parity") and when ("Use when adding any feature, integration, or capability"). Both are concrete with explicit trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Use when adding any feature, integration, or capability" covers the natural phrases a user would say, with useful breadth across feature/integration/capability. It misses common variations like "new feature" or "build a feature", so it falls just below comprehensive.

4 / 5

Distinctiveness Conflict Risk

The trigger is anchored to a distinct niche (agent/UI parity for feature additions) with clear framing, but "adding any feature" broadly overlaps sibling skills the checklist itself points to (actions, storing-data, sharing). Mostly distinct with minor overlap risk.

4 / 5

Total

15

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository
BuilderIO/agent-native
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.