CtrlK
BlogDocsLog inGet started
Tessl Logo

ccb-fixture-skill

Proves that a managed Claude session can discover a seeded plugin.

60

Quality

69%

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 ./test/fixtures/claude-plugin-marketplace/plugins/ccb-fixture-plugin/skills/ccb-fixture-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-5

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 minimal, perfectly calibrated instruction: one unambiguous action with the exact reply string and trigger condition, and nothing else. It fully satisfies the simple-skill exceptions for workflow clarity and progressive disclosure.

DimensionReasoningScore

Conciseness

The body is two lines — "Reply with `ccb-fixture-plugin-loaded` when this fixture is invoked." — with zero padding and nothing that assumes Claude lacks knowledge, matching 'lean and efficient; every token earns its place'. It cannot be below 5 since no unnecessary token exists anywhere in the body.

5 / 5

Actionability

The instruction is fully concrete and executable for this instruction-only skill: it gives the exact response string (`ccb-fixture-plugin-loaded`) and the exact invocation condition ('when this fixture is invoked'). Per the scoring notes, instruction-only skills need concrete specific guidance rather than code, and this is maximally specific. Not a 4 because there are no gaps — the single common case is covered verbatim.

5 / 5

Workflow Clarity

This is a simple single-purpose skill whose single action (reply with the marker string when invoked) is unambiguous, which per the judging guidelines and scoring notes earns a 5 without a multi-step workflow. There are no destructive or batch operations, so the workflow-clarity cap does not apply.

5 / 5

Progressive Disclosure

The skill is well under 50 lines, needs no external references, and no bundle files (references/, scripts/, assets/) exist to organize — matching the guideline that such skills score 5 with a well-organized single section. The heading plus one instruction line is the appropriate structure for this content.

5 / 5

Total

20

/

20

Passed

Description

38%Weight 40%Scale 1-5

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 states a single clear, concrete purpose but is written as an internal test-fixture label rather than a user-facing skill description. It lacks any 'when to use' trigger guidance and uses only technical jargon no user would naturally say, leaving it undiscoverable in practice.

Suggestions

Add an explicit trigger clause, e.g. 'Use when testing whether a plugin has been successfully loaded into the session.'

Replace internal jargon ('managed Claude session', 'seeded plugin') with natural keywords a user would actually say, such as 'plugin loaded', 'verify plugin installation', or 'check plugin discovery'.

State the concrete actions the skill performs beyond the single 'proves' claim — for example, what the skill replies with and what that confirms — to round out the 'what' alongside the missing 'when'.

DimensionReasoningScore

Specificity

"Proves that a managed Claude session can discover a seeded plugin" names the domain (managed session plugin discovery) and exactly one concrete action ('proves ... can discover'), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because it lists no additional actions or coverage, and not a 2 because the single action stated is concrete rather than generic like 'Processes PDF files'.

3 / 5

Completeness

The 'what' is stated clearly (proves plugin discovery) but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It is not a 4 because the when-clause is entirely absent rather than merely imprecise, and not a 2 because the what is clear rather than vague.

3 / 5

Trigger Term Quality

The description contains only internal technical jargon — "managed Claude session", "discover a seeded plugin" — with no natural phrases a user would say when needing this skill, matching the 'no natural keywords; only technical jargon' anchor. It is not a 2 because it lacks even the one or two generic user-facing keywords that anchor requires.

1 / 5

Distinctiveness Conflict Risk

The niche (verifying plugin discovery in a managed Claude session) is very specific, so overlap risk with other skills is minor, matching 'mostly distinct; minor overlap risk'. It is not a 5 because the description offers no explicit distinct trigger phrases (the 5-anchor example includes them), and not a 3 because its subject matter is far more specific than the 'Works with document files' level of generality.

4 / 5

Total

11

/

20

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SeemSeam/claude_codex_bridge
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.