CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

with-trigger

Generates a thing and writes it to disk. Use when the user asks to scaffold a thing.

Quality

50%

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 ./tools/tests/fixtures/validate-skills/with-trigger/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

33%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 token-lean and structurally clean, but it contains no operational content whatsoever — it is meta-commentary about the skill rather than guidance for performing it. Actionability and workflow clarity are at the floor because there are no instructions, code, or steps for the task the description promises.

Suggestions

Add actual instructions for the core task: what "generate a thing" means, the expected output format, and where/how it is written to disk.

Include an executable example (command or code snippet) covering the common case so Claude can act without guessing.

Replace the meta-commentary sentence with task-relevant guidance, and if generation plus disk-write is multi-step, lay out a brief sequenced workflow (generate, validate, write).

DimensionReasoningScore

Conciseness

The body is only two lines with zero padding and no explanations of concepts Claude already knows. It falls just short of anchor 5 because the one content sentence — "An active skill whose description includes a \"Use when\" trigger phrase." — is meta-commentary that adds no operational value and could be trimmed.

4 / 5

Actionability

The body contains no concrete code, commands, or steps for generating or writing anything; it only describes the skill itself ("An active skill whose description includes...") rather than instructing. This is a direct match for anchor 1 ("only describes rather than instructs"), and no higher anchor is reachable without any executable guidance.

1 / 5

Workflow Clarity

No sequence of steps exists anywhere in the body — anchor 1 ("Steps missing or incoherent; no sequence"). The simple-skill exception cannot apply because no single action is unambiguously specified: the body never says what "generate a thing" involves or how the result is written to disk.

1 / 5

Progressive Disclosure

No bundle files (references/, scripts/, assets/) exist, nothing is inlined that belongs in separate files, and references are not nested or buried, which is cleaner than anchor 3's "some structure but could be better organized". It does not reach 5 even under the under-50-line simple-skill note, because a bare heading over one meta sentence does not constitute genuinely well-organized sections for a skill whose description promises artifact generation.

4 / 5

Total

10

/

20

Passed

Description

42%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 has the right structural shape — a what clause plus an explicit "Use when" trigger — which earns it full credit for completeness presence. However, the placeholder "thing" makes the capability, trigger terms, and niche all vague, capping every other dimension low.

Suggestions

Replace the placeholder "thing" with the concrete artifact(s) the skill actually produces (e.g., "project scaffolds", "config files") to sharpen specificity and distinctiveness.

Expand the trigger clause with natural synonyms and concrete nouns users would say (e.g., "scaffold a project", "generate boilerplate", "create a starter template").

Ground the 'what' in concrete actions and output details (format, destination) so the skill is distinguishable from other generator skills.

DimensionReasoningScore

Specificity

"Generates a thing and writes it to disk" names two actions (generate, write to disk) but the object is the placeholder "thing", so no real domain or concrete capability is described. This matches anchor 2 ("actions are minimal or generic") rather than anchor 1, since actions are stated rather than purely abstract, and falls short of anchor 3 because no concrete, real deliverable is ever named.

2 / 5

Completeness

Both parts are explicitly present: a what ("Generates a thing and writes it to disk") and an explicit when ("Use when the user asks to scaffold a thing"), matching anchor 4 (both present, could be more specific). It is not 5 because neither clause is concrete — the object is the placeholder "thing" — and not 3 because the "Use when" trigger clause is explicitly stated, and the rubric only caps at 3 when such a clause is missing.

4 / 5

Trigger Term Quality

The only trigger keyword is "scaffold" in "Use when the user asks to scaffold a thing" — no synonyms, variations, or concrete artifact names accompany it. It scores above 1 because "scaffold" is a term users naturally say, but below 3 because, unlike "Works with PDF files", the phrase never identifies concrete subject matter, leaving the natural phrases users would actually say missing.

2 / 5

Distinctiveness Conflict Risk

"a thing" is a maximally generic object, so this description would overlap with virtually any generator/scaffolding skill, matching anchor 2 ("Very broad; high overlap risk with many similar skills"). It is above anchor 1 only because the scaffold-and-write-to-disk operation gives a slight niche signal, and below anchor 3 because no concrete subject matter distinguishes it from related skills.

2 / 5

Total

10

/

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

bmad-code-org/BMAD-METHOD

Path

tools/tests/fixtures/validate-skills/with-trigger/SKILL.md

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.