CtrlK
BlogDocsLog inGet started
Tessl Logo

team-planex

Unified team skill for plan-and-execute pipeline. Pure router — coordinator always. Beat model is coordinator-only in monitor.md. Triggers on "team planex".

48

Quality

51%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/team-planex/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.

This is a well-structured orchestration skill with strong actionability — concrete templates, explicit tool-call governance, and clear multi-phase workflows with timeout cascades and error handling. Its main weakness is moderate verbosity: some sections repeat information already conveyed elsewhere (architecture diagram vs. two-phase pattern description), and a few tables contain low-value entries (e.g., 'not used in this skill'). The progressive disclosure is reasonable but the document is long enough that some sections could be extracted to referenced files.

Suggestions

Remove the 'Not used in this skill' row from the Message Semantics table and trim the Two-Phase Pipeline Pattern section to avoid repeating what the architecture diagram already shows.

Consider extracting the v4 Agent Coordination section and Worker Spawn Template into a referenced file (e.g., specs/agent-coordination.md) to keep SKILL.md as a leaner router overview.

DimensionReasoningScore

Conciseness

The content is moderately efficient — the architecture diagram, role registry, delegation lock table, and spawn template all earn their place. However, some sections are verbose (e.g., the model selection guide with default/default values, the message semantics table explaining 'not used in this skill', and the two-phase pipeline pattern repeating concepts already shown in the architecture diagram). Some tightening is possible.

2 / 3

Actionability

Highly actionable: provides concrete spawn_agent templates with exact parameter structures, specific tool-call allow/block lists, exact file paths, timeout values (1800000ms), CLI commands, and a complete session directory structure. The delegation lock table is immediately executable as a decision matrix.

3 / 3

Workflow Clarity

The workflow is clearly sequenced: role routing → coordinator entry → analyze → dispatch → spawn workers → wait → timeout cascade (STATUS_CHECK → FINALIZE → close). The delegation lock provides explicit validation checkpoints before every tool call. Error handling table covers failure modes with specific resolutions. The two-phase pipeline pattern has clear sequencing with timeout cascades.

3 / 3

Progressive Disclosure

References to role files (roles/coordinator/role.md, roles/planner/role.md, etc.) and specs (specs/pipelines.md) are well-signaled and one level deep. However, no bundle files were provided to verify these references exist, and the SKILL.md itself is quite long (~180 lines) with some content (like the full agent coordination section and named agent targeting) that could potentially be split into referenced files for better organization.

2 / 3

Total

10

/

12

Passed

Description

25%

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 is heavily laden with internal jargon and lacks concrete, user-facing language about what the skill actually does. While it includes a trigger phrase ('team planex'), the phrase is technical and narrow, and the description fails to explain the skill's purpose or capabilities in accessible terms. It reads more like internal developer notes than a functional skill description.

Suggestions

Replace jargon like 'pure router', 'coordinator-only', and 'beat model' with concrete descriptions of what the skill does, e.g., 'Coordinates multi-step task execution by breaking complex requests into subtasks and delegating them.'

Add natural trigger terms that users might actually say, such as 'plan and execute', 'break down task', 'multi-step workflow', 'coordinate tasks', in addition to the internal 'team planex' trigger.

Add an explicit 'Use when...' clause describing the scenarios in which this skill should be selected, e.g., 'Use when the user needs a complex task broken into steps and executed sequentially by multiple agents.'

DimensionReasoningScore

Specificity

The description uses vague, jargon-heavy language like 'plan-and-execute pipeline', 'pure router', and 'coordinator always' without describing any concrete actions or capabilities that a user would understand.

1 / 3

Completeness

It has a minimal 'when' clause ('Triggers on "team planex"'), but the 'what' is extremely vague — 'plan-and-execute pipeline' and 'pure router' don't clearly explain what the skill actually does. The trigger guidance is present but very narrow.

2 / 3

Trigger Term Quality

The only explicit trigger is 'team planex', which is an internal/technical term unlikely to be naturally used by users. Terms like 'pure router', 'coordinator-only', and 'beat model' are internal jargon, not natural user language.

1 / 3

Distinctiveness Conflict Risk

The specific trigger phrase 'team planex' provides some distinctiveness, but the vague description of being a 'coordinator' and 'router' for a 'plan-and-execute pipeline' could overlap with other orchestration or planning skills without clearer boundaries.

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.