CtrlK
BlogDocsLog inGet started
Tessl Logo

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

96

1.41x
Quality

63%

Does it follow best practices?

Impact

99%

1.41x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/subagent-driven-development/SKILL.md

The canonical home for this skill is subagent-driven-development in obra/superpowers

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 a well-sequenced, actionable guide with strong validation checkpoints and feedback loops, but it loses points on progressive disclosure because every referenced prompt-template file is missing from the bundle, leaving the detailed material unreachable.

Suggestions

Add the referenced prompt-template files (implementer-prompt.md, spec-reviewer-prompt.md, code-quality-reviewer-prompt.md) to the bundle, or inline their key contents so the references resolve.

Trim the Advantages and Red Flags lists to non-redundant items; the process graph already conveys most of the workflow guarantees.

Show at least one concrete subagent dispatch call (e.g. a sample Task tool invocation with the implementer prompt) so the example workflow is directly executable.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — dot-graph decision and process diagrams plus a compact example workflow carry the load with little concept explanation — but the Advantages/Red Flags bullet lists repeat ideas already implied by the diagrams, a minor trim opportunity.

4 / 5

Actionability

It gives concrete, executable guidance: a per-task process graph with named subagent prompts and a full worked example showing dispatch, Q&A, review output, and fix loops, though the actual prompt-template contents are referenced rather than shown.

4 / 5

Workflow Clarity

The multi-step process is clearly sequenced with explicit validation checkpoints (spec-then-quality review order) and feedback loops (reviewer finds issues → implementer fixes → re-review until approved), plus a final whole-implementation review — matching the explicit-validation-with-feedback-loops anchor.

5 / 5

Progressive Disclosure

Structure and sectioning are reasonable and references are signaled, but the body points to three prompt-template files (./implementer-prompt.md, ./spec-reviewer-prompt.md, ./code-quality-reviewer-prompt.md) that are not present in the bundle, so navigation to the actual detailed material is broken.

3 / 5

Total

16

/

20

Passed

Description

50%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 correctly answers both 'what' and 'when' and carves a distinct niche, but it is light on concrete capability actions and natural trigger terms, leaning on generic phrasing rather than specific verbs a user would voice.

Suggestions

Add concrete actions to the description, e.g. 'Dispatches a fresh subagent per task and runs two-stage spec and code-quality review after each.'

Include natural trigger phrases users would say, such as 'Use when implementing a plan, executing tasks from a plan, or running independent plan tasks in this session.'

Tighten the 'what' from the abstract 'executing implementation plans' to the specific mechanism (subagent-per-task dispatch plus staged review).

DimensionReasoningScore

Specificity

The description names the domain ("executing implementation plans") and a scenario but lists no concrete actions the skill performs — it never says it dispatches subagents, reviews, or tracks tasks, staying at the generic 'Processes PDF files' level.

2 / 5

Completeness

It has an explicit 'Use when' trigger ("Use when executing implementation plans with independent tasks in the current session") and a stated 'what' (executing plans with independent tasks), so both what and when are present, though the 'what' is abstract rather than concrete — fits the both-present-but-when-could-be-more-specific anchor.

4 / 5

Trigger Term Quality

Keywords like "implementation plans," "independent tasks," and "current session" are fairly technical/generic and omit the natural phrases a user would actually say (e.g. "implement a plan," "execute tasks"), matching the one-or-two-generic-keywords anchor.

2 / 5

Distinctiveness Conflict Risk

The trigger (same-session execution of plans with independent tasks) carves a clear niche distinct from parallel-session plan execution and manual coding, with only minor overlap risk against the closely related executing-plans skill.

4 / 5

Total

12

/

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
foryourhealth111-pixel/Vibe-Skills
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.