CtrlK
BlogDocsLog inGet started
Tessl Logo

subagent-driven-development

当在当前会话中执行包含独立任务的实现计划时使用

48

Quality

55%

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

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, well-sequenced process with explicit validation loops and concrete bundled scripts. Its main weaknesses are a degree of verbosity (example transcript, advantages restatement) and two referenced prompt-template files that are absent from the bundle.

Suggestions

Add the missing implementer-prompt.md and task-reviewer-prompt.md to the bundle so the signaled one-level-deep references resolve, lifting progressive disclosure.

Trim the full '示例工作流' transcript to a shorter illustrative excerpt and condense the '优势' section, which restates benefits already implied by the process, to improve conciseness.

Consider moving the model-selection guidance and red-lines detail into a referenced file so SKILL.md stays a lean overview pointing one level deep.

DimensionReasoningScore

Conciseness

The body is mostly tight operational guidance, but the lengthy '示例工作流' transcript and the '优势' section restate points already conveyed by the process, and the rationale prose ('为什么用子智能体') could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation'.

2 / 3

Actionability

It gives concrete executable commands and paths throughout — 'scripts/review-package BASE HEAD', 'scripts/task-brief PLAN_FILE N', the progress ledger path and line format, and real bundled scripts — making the guidance copy-paste ready, matching 'fully executable code/commands; specific examples'.

3 / 3

Workflow Clarity

Two DOT flow diagrams lay out the per-task loop and overall sequence, with explicit validation checkpoints (task review for spec + quality, fix→re-review loop, final branch review) and red-line gating, matching 'clear sequence with explicit validation steps; feedback loops for error recovery'.

3 / 3

Progressive Disclosure

Content is sectioned and defers prompt detail to one-level-deep template files in a dedicated '提示词模板' section, but the referenced implementer-prompt.md and task-reviewer-prompt.md are missing from the bundle, breaking the signaled navigation; this fits 'references present but not clearly signaled' in practice and structure that could be better split.

2 / 3

Total

10

/

12

Passed

Description

32%

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 functions as a clear trigger clause but omits any statement of what the skill actually does, leaving completeness weak. It distinguishes itself moderately from sibling plan-execution skills via the current-session and independent-task qualifiers.

Suggestions

Add a 'what' clause stating the skill's concrete actions, e.g. '分派独立子智能体执行计划任务,每任务后做规格+质量审查,结尾做整分支审查' before the 'Use when' trigger.

Expand trigger coverage with natural phrasings users actually say, such as '实现计划', '执行计划', '并行子智能体', '任务拆分', so the skill surfaces for varied prompts.

Name concrete capabilities (dispatch implementer/reviewer subagents, task briefs, review packages, progress ledger) to lift specificity from domain-naming to action-listing.

DimensionReasoningScore

Specificity

The description names the domain concretely ('执行...实现计划', '独立任务', '当前会话') but lists no concrete actions the skill performs (e.g. dispatching subagents, reviewing), so it sits at 'names domain and some attributes' rather than 'lists multiple specific concrete actions'.

2 / 3

Completeness

The description is essentially only a 'when' clause ('当...时使用') and never states what the skill does; missing the 'what' maps to 'Missing what OR when, or both very weak'.

1 / 3

Trigger Term Quality

It uses relevant natural terms ('实现计划', '独立任务', '当前会话') a user might say, but offers only a single trigger phrasing with no common variations or synonyms, matching 'some relevant keywords but missing common variations'.

2 / 3

Distinctiveness Conflict Risk

The '当前会话' (current session) and '独立任务' qualifiers carve out a niche distinct from the sibling executing-plans skill, but the terse phrasing still overlaps the plan-execution space, fitting 'somewhat specific but could still overlap with similar skills'.

2 / 3

Total

7

/

12

Passed

Validation

75%

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

Validation12 / 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

relative_links

Relative link issues: 2 missing, 1 suspicious

Warning

Total

12

/

16

Passed

Repository
jnMetaCode/superpowers-zh
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.