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

78%

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 ./.agents/skills/adding-a-feature/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

73%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 well-structured, highly actionable checklist skill with strong workflow sequencing and verification. Its main weakness is conciseness — the single monolithic file runs long and repeats some guidance that could be trimmed or split into referenced sub-files.

Suggestions

Tighten the Action and Skills/Instructions sections: several credential-preflight and layout rules are restated and could be consolidated into a single statement plus a cross-skill pointer.

Consider moving the per-area long-form detail (provider integrations, credential preflight, link/mcpApp metadata) into one referenced file so SKILL.md stays a lean overview, improving progressive_disclosure.

Add one short executable code snippet for an Action (defineAction) to match the depth of the useChangeVersions example and close the actionability gap.

DimensionReasoningScore

Conciseness

The body is information-dense and covers framework-specific contracts Claude would not know, but at ~219 lines several prose passages repeat guidance (e.g., credential and layout re-explanations) that could be tightened.

3 / 5

Actionability

Concrete named primitives (defineAction, useActionQuery, buildDeepLink, ownableColumns, defineAppRoles) and one complete copy-paste tsx block plus `pnpm action view-screen` give mostly executable guidance with minor gaps where only API names are given without full examples.

4 / 5

Workflow Clarity

A clearly ordered four-area checklist plus a dedicated 6-point Verification checklist and a Scope-check-first gate provide an explicit sequence with validation checkpoints and a feedback loop, satisfying the top anchor.

5 / 5

Progressive Disclosure

Clean section structure (Rule, Why, Checklist, Examples, Anti-Patterns, Verification, Related Skills) with well-signaled one-level-deep cross-skill references; not a 5 because all detail lives in one long monolithic file rather than being split into referenced files.

4 / 5

Total

16

/

20

Passed

Description

83%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 tight, third-person description that pairs a concrete mechanism with explicit "Use when" trigger guidance, cleanly answering both what and when. Its only weakness is that the broad trigger surface leaves minor overlap risk with sibling agent-native skills.

DimensionReasoningScore

Specificity

Names a concrete mechanism ("four-area checklist every new feature must complete") plus the parity outcome it guarantees, which lists several specific aspects with only minor gaps in enumerating the four areas.

4 / 5

Completeness

It explicitly answers both what ("four-area checklist every new feature must complete") and when ("Use when adding any feature, integration, or capability") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

"Use when adding any feature, integration, or capability" supplies natural phrases a user would say; coverage is good but a few common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The agent-native parity framing and four-area checklist give it a clear niche, but "adding any feature, integration, or capability" is broad enough to risk minor overlap with closely related agent-native skills.

4 / 5

Total

17

/

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.

Validation13 / 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.