CtrlK
BlogDocsLog inGet started
Tessl Logo

using-kit

Enforces skill discovery and invocation governance for every task. Use at the start of any conversation, before responding to any user message, when deciding whether a skill applies, when building or modifying features (triggers the brainstorming chain), or when operating within a team context. Defines the default workflow chain (brainstorming -> writing-plans -> team-dev -> finish-branch) and prevents rationalizing away skill usage.

48

Quality

49%

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 ./skills/using-kit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

47%

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

This skill provides a clear governance framework with a well-defined decision flowchart and workflow chain, but suffers significantly from verbosity and repetition. The core message ('always check for and invoke applicable skills before responding') is restated in at least 5 different ways across the document. The 12-row red flags table, while creative, is essentially 12 variations of the same instruction and consumes substantial tokens without proportional value.

Suggestions

Consolidate the repeated 'always invoke skills' message into a single clear statement and remove the EXTREMELY-IMPORTANT block, redundant rule restatements, and reduce the Red Flags table to 3-4 genuinely distinct scenarios.

Add a concrete example of skill invocation syntax (e.g., showing what 'Invoke Skill tool' looks like in practice with actual tool call format).

Move the Red Flags table and Team Context Awareness section to a separate reference file to keep the main SKILL.md lean and focused on the core workflow.

DimensionReasoningScore

Conciseness

Extremely verbose and repetitive. The core rule ('invoke skills before responding') is stated multiple times in different ways. The 12-row 'Red Flags' table is padded with variations of the same message ('check for skills'). The EXTREMELY-IMPORTANT block, the rule section, and the red flags table all say the same thing. Much of this content is meta-governance that Claude could infer from a much shorter instruction.

1 / 3

Actionability

The workflow chain (brainstorming → writing-plans → team-dev → finish-branch) is concrete and the dot graph provides a clear decision flow. However, there are no executable code examples or specific commands—it's all procedural instruction. The 'How to Access Skills' section gives a concrete tool name (Skill tool) but lacks examples of actual invocation syntax.

2 / 3

Workflow Clarity

The decision flowchart (dot graph) clearly sequences the process from receiving a user message through skill invocation. The default workflow chain is explicitly ordered with clear handoffs ('each skill invokes the next'). The team context section adds appropriate conditional logic. Validation is implicit but appropriate for this type of governance skill (it's not a destructive/batch operation).

3 / 3

Progressive Disclosure

The content is structured with clear sections (How to Access, The Rule, Default Workflow Chain, Team Context, Red Flags, Skill Priority, Skill Types, User Instructions), which is good. However, the red flags table and repetitive emphasis could be collapsed or moved to a reference file. No bundle files are provided, and no external references are made despite the content being long enough to benefit from splitting.

2 / 3

Total

8

/

12

Passed

Description

52%

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 a meta-governance skill that clearly articulates both what it does and when to use it, earning high completeness marks. However, its trigger conditions are so broad ('every task', 'any conversation') that it would conflict with virtually every other skill, and its language is entirely internal jargon that no user would naturally use. The description reads more like an internal system prompt directive than a skill description meant to be selected from a pool of alternatives.

Suggestions

Replace internal jargon ('invocation governance', 'rationalizing away skill usage') with natural language that describes the user-facing benefit or observable behavior.

Narrow the trigger conditions significantly — 'every task' and 'any conversation' make this indistinguishable from a system prompt; specify the concrete scenarios where this skill adds value over others.

Consider whether this is truly a 'skill' or a system-level directive; if it must be a skill, add distinct trigger terms that differentiate it from task-specific skills (e.g., 'workflow orchestration', 'multi-step project setup').

DimensionReasoningScore

Specificity

The description names a domain (skill discovery and invocation governance) and some actions (enforces governance, defines workflow chain, prevents rationalizing away skill usage), but the actions are more procedural/meta than concrete user-facing capabilities. It lists a specific workflow chain which adds some concreteness.

2 / 3

Completeness

The description explicitly answers both 'what' (enforces skill discovery and invocation governance, defines default workflow chain, prevents rationalizing away skill usage) and 'when' (at the start of any conversation, before responding to any user message, when deciding whether a skill applies, when building or modifying features, when operating within a team context).

3 / 3

Trigger Term Quality

The keywords used are highly internal/meta-process jargon ('skill discovery', 'invocation governance', 'brainstorming chain', 'rationalizing away skill usage') that no user would naturally say. Users would never ask for 'skill invocation governance' — these are system-level concepts, not natural user language.

1 / 3

Distinctiveness Conflict Risk

The meta-governance nature makes it somewhat distinct from typical task-oriented skills, but the extremely broad trigger conditions ('every task', 'any conversation', 'any user message') mean it would fire for virtually everything, creating high conflict risk with all other skills.

2 / 3

Total

8

/

12

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.

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
shousper/claude-kit
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.