CtrlK
BlogDocsLog inGet started
Tessl Logo

team-roadmap-dev

Unified team skill for roadmap-driven development workflow. Coordinator discusses roadmap with user, then dispatches phased execution pipeline (plan -> execute -> verify). All roles invoke this skill with --role arg. Triggers on "team roadmap-dev".

53

Quality

60%

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-roadmap-dev/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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 that serves effectively as a router document. Its strengths are excellent actionability with concrete spawn templates, clear workflow sequencing with validation loops, and good progressive disclosure to role-specific files. Minor verbosity in some sections (model selection rationale, some table descriptions) prevents a perfect conciseness score, but overall the content is high quality and purpose-built for multi-agent coordination.

DimensionReasoningScore

Conciseness

The content is mostly efficient and avoids explaining basic concepts, but includes some redundancy (e.g., the Model Selection Guide rationale column restates obvious points, and some tables could be tighter). The ASCII architecture diagram and detailed session directory structure are useful but borderline verbose for a router file.

2 / 3

Actionability

Provides concrete spawn_agent templates with exact parameters, specific tool call allowlists/blocklists, exact file paths, timeout values (1800000ms), and executable patterns for agent health checks and completion actions. The delegation lock table is immediately actionable with clear verdicts.

3 / 3

Workflow Clarity

Multi-step processes are clearly sequenced: the pipeline flow (PLAN -> EXEC -> VERIFY) with gap closure loops (max 3 iterations) is explicit, timeout handling has a clear escalation sequence (STATUS_CHECK -> FINALIZE -> mark timed_out -> close), and error handling covers recovery paths. Validation checkpoints are embedded in the verification phase and gap closure loop.

3 / 3

Progressive Disclosure

SKILL.md serves as a clear router/overview with well-signaled one-level-deep references to role files (roles/coordinator/role.md, roles/planner/role.md, etc.) and specs (specs/pipelines.md). The Role Registry table provides a clean navigation index. Content is appropriately split between the overview here and detailed role instructions in referenced files.

3 / 3

Total

11

/

12

Passed

Description

35%

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 outlines a multi-role development workflow but relies on artificial trigger phrases rather than natural language cues, making it poorly suited for automatic skill selection. The capabilities described are process-oriented abstractions rather than concrete actions, and the description reads more like internal documentation than a skill selection guide.

Suggestions

Replace the artificial trigger 'team roadmap-dev' with natural language triggers like 'Use when the user asks to plan and execute a development roadmap, break down project phases, or coordinate multi-step feature implementation'.

Add specific concrete actions such as 'breaks down roadmap items into tasks, generates implementation plans, executes code changes, and verifies results against acceptance criteria'.

Include natural keywords users would say, such as 'project planning', 'feature development', 'milestone tracking', 'phased implementation', or 'development pipeline'.

DimensionReasoningScore

Specificity

Names the domain (roadmap-driven development) and describes a pipeline (plan -> execute -> verify), but the actual concrete actions are vague — 'discusses roadmap', 'dispatches phased execution pipeline' are abstract process descriptions rather than specific capabilities like 'creates task breakdowns' or 'generates implementation plans'.

2 / 3

Completeness

The 'what' is partially addressed (coordinator discusses roadmap, dispatches pipeline), and there is a 'Triggers on' clause, but the trigger is an artificial command ('team roadmap-dev') rather than natural user intent descriptions. The 'when' is technically present but not useful for natural language matching.

2 / 3

Trigger Term Quality

The only explicit trigger is the artificial phrase 'team roadmap-dev', which is not something a user would naturally say. Terms like 'roadmap', 'phased execution pipeline', and '--role arg' are technical jargon unlikely to match natural user requests. Missing natural terms like 'project planning', 'development workflow', 'build features', etc.

1 / 3

Distinctiveness Conflict Risk

The artificial trigger 'team roadmap-dev' makes it unlikely to accidentally conflict with other skills, but the underlying description of 'roadmap-driven development workflow' and 'plan -> execute -> verify' could overlap with general project management or development planning skills. The specificity of the invocation mechanism helps but the conceptual scope is broad.

2 / 3

Total

7

/

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.