CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-specification

Agent skill for specification - invoke with $agent-specification

43

1.54x
Quality

28%

Does it follow best practices?

Impact

51%

1.54x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-specification/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

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 well-structured, example-driven specification scaffold, but it is verbose, contains broken template syntax, and lacks interleaved validation and external reference files. It is moderately actionable but not copy-paste ready or token-lean.

Suggestions

Fix the corrupted delimiters (replace "$" with "/") in the OpenAPI paths, content types, "email$password", and "pass$fail" so templates are copy-paste ready.

Move the full deliverable templates (requirements document, data model, OpenAPI spec) into reference files under references/ and link to them from a concise overview, reducing SKILL.md to a lean scaffold.

Interleave validation checkpoints through the Specification Process with explicit fix-and-retry guidance rather than relying on a single end-of-document checklist.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but it is a ~250-line dump of full example templates (requirements doc, data model, OpenAPI) that could be tightened; verbosity is penalized even though accurate.

2 / 3

Actionability

Concrete YAML/Gherkin/OpenAPI scaffolds are provided, but corrupted syntax such as "$auth$login", "application$json", "email$password", and "pass$fail" breaks copy-paste readiness, leaving the guidance incomplete.

2 / 3

Workflow Clarity

The Specification Process is numbered (requirements, constraints, use cases, acceptance) and a Validation Checklist exists, but validation is a static tail checklist with no interleaved checkpoints or fix-and-retry feedback loops.

2 / 3

Progressive Disclosure

Sections are well organized, but the document is monolithic with all deliverable templates inline and no bundle files or one-level-deep references, so content that should be separate remains inline.

2 / 3

Total

8

/

12

Passed

Description

7%

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 frontmatter description is too sparse to function as effective trigger guidance: it names a domain but describes no concrete capabilities and gives no usage triggers. It relies on an invocation token instead of natural language.

Suggestions

Rewrite the description to list concrete actions, e.g. "Gathers requirements, analyzes constraints, and defines acceptance criteria for the SPARC Specification phase."

Add an explicit "Use when..." trigger clause naming natural terms users would say, such as "Use when defining requirements, writing specs, or producing acceptance criteria."

Drop the "$agent-specification" invocation token from the description; it is a technical artifact, not a natural trigger term.

DimensionReasoningScore

Specificity

The description states only "Agent skill for specification" with no concrete actions; it names a domain but lists nothing the skill actually does, matching the vague/abstract anchor.

1 / 3

Completeness

It weakly conveys "what" (just the topic "specification") and entirely omits "when" — there is no "Use when..." clause or equivalent trigger guidance, so both halves are weak per the cap guideline.

1 / 3

Trigger Term Quality

The only trigger-like phrase is the invocation token "$agent-specification", a technical artifact rather than natural language a user would say; no natural keywords such as "requirements", "specs", or "acceptance criteria" appear.

1 / 3

Distinctiveness Conflict Risk

"specification" points to a somewhat specific niche, but without the SPARC context (which lives only in the body) and with no distinct natural triggers, it could still overlap with other spec-related skills.

2 / 3

Total

5

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ruvnet/ruflo
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.