CtrlK
BlogDocsLog inGet started
Tessl Logo

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates

62

Quality

73%

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 ./plugins/sadd/skills/subagent-driven-development/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 content is well-structured with actionable prompts and clear workflows including validation checkpoints. Its main weaknesses are redundancy that hurts token efficiency and a monolithic structure with no progressive disclosure into separate files.

Suggestions

Remove redundancies: drop the restated "Core principle" lines and consolidate the overlapping Sequential/Parallel guidance to tighten token use (improves conciseness).

Split the long Real Example and Agent Prompt Structure sections into reference files (e.g. examples.md, agent-prompts.md) and link to them from SKILL.md to improve progressive disclosure.

Add an explicit per-task verification step in the Parallel Execution batch process to match the rigor of the Sequential process's validation checkpoints.

DimensionReasoningScore

Conciseness

Mostly efficient but contains redundancy: the "Core principle" is restated, Sequential and Parallel sections overlap, and the Real Example rehashes Common Mistakes, so it could be tightened.

3 / 5

Actionability

Provides concrete Task-tool prompts, code-reviewer dispatch templates, and a specific agent-prompt example, with only minor gaps from placeholder fields like [task name].

4 / 5

Workflow Clarity

Clear numbered sequences with validation checkpoints (review between tasks, fix Critical/Important before proceeding, final review, "Stop when blocked"), though the parallel batch step is slightly less explicit about per-task validation.

4 / 5

Progressive Disclosure

No bundle files exist, and the body is a monolithic single file with several long inline sections (Real Example, Agent Prompt Structure) that could be split into referenced files for easier navigation.

3 / 5

Total

14

/

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.

The description is concrete and well-structured, clearly stating both what the skill does and when to use it in third-person voice. It is distinguishable from related skills and uses natural trigger phrasing.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ("dispatches fresh subagent for each task," "code review between tasks," "quality gates"), with only minor gaps in coverage rather than comprehensive listing.

4 / 5

Completeness

Explicitly answers both what (dispatch fresh subagent per task with code review) and when ("Use when executing implementation plans... or facing 3+ independent issues") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say ("executing implementation plans," "independent tasks," "independent issues") with good coverage, though a few synonyms (e.g. "parallelize," "code review") are missing.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (subagent dispatching for plan execution) with minimal conflict risk, though it overlaps slightly with generic plan-execution skills.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NeoLabHQ/context-engineering-kit
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.