backend-development-feature-development

Orchestrate end-to-end backend feature development from requirements to deployment. Use when coordinating multi-phase feature delivery across teams and services.

2.22x

Quality

60%

Does it follow best practices?

Impact

89%

2.22x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/backend-development-feature-development/SKILL.md

The canonical home for this skill is backend-development-feature-development in rmyndharis/antigravity-skills

Quality

Content

57%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 delivers a clear, actionable multi-phase orchestration workflow with concrete subagent wiring, but it is monolithic, carries a padded philosophy paragraph, and lacks explicit validation gates between risky phases. Splitting detail into referenced files and adding phase-gate checkpoints would lift the weaker dimensions.

Suggestions

Remove or sharply trim the '[Extended thinking: ...]' paragraph; Claude does not need the workflow's philosophy explained.

Add explicit validation checkpoints between phases (e.g. 'Confirm requirements signed off before starting implementation', 'Only proceed to deployment after security and test gates pass') to satisfy the destructive-operation workflow cap.

Move per-phase prompt templates and the parameter/config reference into separate referenced files (e.g. phases.md, config.md) so SKILL.md stays a lean overview with one-level-deep navigation.

Dimension	Reasoning	Score
Conciseness	The body is mostly structured lists, but the long '[Extended thinking: ...]' paragraph re-explains the workflow's own philosophy (concepts Claude already knows) and the 12 templated agent prompts are repetitive, fitting the 'mostly efficient with some unnecessary explanation' anchor; not 4 because the philosophy paragraph is clearly removable padding.	3 / 5
Actionability	Each phase gives a concrete subagent_type, a prompt template, expected output, and context, which is mostly executable orchestration guidance; it stops short of 5 because prompts carry unresolved placeholders like '[include business analysis from step 1]' that are not copy-paste ready.	4 / 5
Workflow Clarity	A clear 4-phase / 12-step sequence exists, but the skill drives destructive/risky operations (production deployment, data migrations, feature rollouts) and lacks explicit per-phase validation checkpoints/gates between phases, so the destructive-operation cap holds workflow_clarity at 3; it is not below 3 because the sequence itself is well-ordered.	3 / 5
Progressive Disclosure	The skill is a single monolithic ~175-line file with all 12 phases inlined and no bundle files or references; headers provide some structure, but content that belongs in separate files (per-phase prompt detail, config reference) is inlined, matching the 'some structure but could be better organized' anchor.	3 / 5
	Total	13 / 20 Passed

Description

62%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 clearly states both what the skill does and when to use it, with a coherent orchestration niche. It is held back by limited concrete action enumeration and missing common trigger synonyms a user would naturally say.

Suggestions

Add concrete trigger phrases users would naturally say, e.g. 'Use when shipping a backend feature end-to-end, planning a rollout, or coordinating a multi-service change'.

List a few discrete capabilities (e.g. requirements, architecture, implementation, testing, rollout) in the description to lift specificity beyond the 1-2 action range.

Tighten the 'when' clause with specific triggers like cross-team backend delivery, deployment with rollback, or feature-flag rollouts to reduce overlap with generic project-management skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('backend feature development') and the concrete arc ('requirements to deployment', 'multi-phase delivery'), matching the anchor that lists 1-2 concrete actions without comprehensive coverage; it does not enumerate several discrete capabilities to reach 4.	3 / 5
Completeness	It gives a clear 'what' (orchestrate backend feature development from requirements to deployment) and an explicit 'when' clause ('Use when coordinating multi-phase feature delivery...'), satisfying both; the 'when' is explicit but broad rather than concrete triggers, so not 5.	4 / 5
Trigger Term Quality	Relevant natural phrases appear ('multi-phase feature delivery', 'across teams and services') but common synonyms a user would say (rollout, deployment, shipping a feature) are missing, fitting the anchor with some relevant keywords lacking common variations.	3 / 5
Distinctiveness Conflict Risk	The niche (multi-phase, cross-team/service backend delivery orchestration) is distinct from single-purpose skills with only minor overlap risk against general project-management skills; not a 5 because the 'when' is broad enough to invite some overlap.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/backend-development-feature-development/SKILL.md
Commit: 57c135b

Reviewed: 21 hours 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.