CtrlK
BlogDocsLog inGet started
Tessl Logo

team-perf-opt

Unified team skill for performance optimization. Coordinator orchestrates pipeline, workers are team-worker agents. Supports single/fan-out/independent parallel modes. Triggers on "team perf-opt".

48

Quality

51%

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 ./.claude/skills/team-perf-opt/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%Scale 1-3

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

This is a well-structured orchestration skill with strong actionability and clear workflow definitions across three parallel execution modes. The main weakness is that it includes substantial inline content (directory trees, completion templates, architecture diagrams) that could be offloaded to the referenced spec files for better progressive disclosure. The error handling table with specific resolutions and the concrete spawn template are particular strengths.

Suggestions

Move the session directory tree and completion action template to specs/pipelines.md or a dedicated reference file, keeping only a brief summary inline

Consider condensing the ASCII architecture diagram to a simpler representation since the pipeline definitions and role registry table already convey the same information

DimensionReasoningScore

Conciseness

The content is reasonably efficient and avoids explaining basic concepts, but includes some verbose sections like the full ASCII architecture diagram, the completion action template, and the session directory tree that could be moved to referenced spec files. The role registry and error handling tables are well-structured but add bulk.

2 / 3

Actionability

The skill provides concrete, executable guidance: the Worker Spawn Template is copy-paste ready with clear variable placeholders, the role router logic is explicit, user commands are mapped to specific actions, and error handling has specific resolutions. The Agent() call template and team_msg references are directly usable.

3 / 3

Workflow Clarity

The pipeline modes (single, fan-out, independent) are clearly sequenced with explicit task ID prefixes showing ordering. Error handling includes feedback loops (review-fix cycle with 3-iteration escalation, benchmark regression auto-creating FIX tasks, branch failure isolation). The role router decision is unambiguous.

3 / 3

Progressive Disclosure

The skill references role files and spec files with correct relative paths, which is good. However, no bundle files were provided to verify these references exist, and the SKILL.md itself contains substantial inline content (session directory structure, completion action template, full spawn template) that could reasonably live in referenced files. The architecture diagram and session directory tree add significant length that could be in specs.

2 / 3

Total

10

/

12

Passed

Description

25%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads more like an internal architecture summary than a user-facing skill description. It focuses on implementation details (coordinator, workers, fan-out modes) rather than concrete user-facing capabilities, and relies on an artificial trigger command rather than natural language keywords. The domain of 'performance optimization' is too broad without specifying what kind of performance optimization is being done.

Suggestions

Replace the artificial trigger 'team perf-opt' with natural language triggers users would actually say, e.g., 'Use when the user asks to optimize performance, speed up code, reduce latency, or profile bottlenecks'.

Specify concrete actions the skill performs, e.g., 'Profiles code execution, identifies bottlenecks, parallelizes workloads, and recommends caching strategies' instead of describing internal architecture.

Narrow the domain scope to clarify what type of performance optimization this covers (e.g., backend API, frontend rendering, database queries) to reduce conflict risk with other potential optimization skills.

DimensionReasoningScore

Specificity

The description uses vague language like 'performance optimization' and 'orchestrates pipeline' without specifying concrete actions. It describes architecture (coordinator, workers, fan-out modes) rather than what the skill actually does for the user.

1 / 3

Completeness

It partially addresses 'what' (performance optimization with parallel modes) and includes a trigger clause ('Triggers on "team perf-opt"'), but the trigger is an artificial command rather than a natural usage scenario. The 'when' is technically present but not meaningful for real skill selection.

2 / 3

Trigger Term Quality

The trigger term 'team perf-opt' is artificial jargon that no user would naturally say. Terms like 'coordinator', 'fan-out', and 'pipeline' are internal implementation details, not natural user language. A user seeking performance optimization would say things like 'speed up', 'optimize performance', 'slow code', etc.

1 / 3

Distinctiveness Conflict Risk

'Performance optimization' is broad and could overlap with many skills (database optimization, frontend performance, build optimization, etc.). The artificial trigger 'team perf-opt' provides some distinctiveness but only because it's a custom command, not because the domain is well-scoped.

2 / 3

Total

6

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
catlog22/Claude-Code-Workflow
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.