CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

drifted-skill

A skill without activation trigger phrases.

Quality

28%

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/skills/drifted/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

22%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 two-line placeholder that documents its own shortcomings instead of teaching anything. While token-efficient by volume, it contains no actionable guidance, no workflow, and no structure beyond a single heading. The skill needs actual instructional content, not trimming.

Suggestions

Replace "This skill body lacks ordered steps, imperative verbs, code examples, and guardrails" with imperative, numbered steps that sequence the actual task, including explicit validation checkpoints for any risky or batch operations (which currently cap workflow clarity at 1).

Add concrete, executable guidance — working code examples or exact commands — for the common cases so Claude knows exactly what to do.

If the task warrants it, split detailed material into one-level-deep reference files linked from a clear overview section, giving the skill real structure to navigate.

DimensionReasoningScore

Conciseness

The body is only "# Drifted Skill" plus one sentence, so there is no verbosity or explanation of concepts Claude already knows. However, the single sentence "This skill body lacks ordered steps, imperative verbs, code examples, and guardrails" is itself an unnecessary explanation — it describes the skill's own deficiencies rather than earning its place as instruction, matching anchor 3 ("Mostly efficient but includes some unnecessary explanation"). Not level 4/5 because the one piece of content present adds no value to executing any task, and not level 2 because nothing is padded or over-explained.

3 / 5

Actionability

The body offers zero concrete guidance — no code, commands, or specific steps; it "only describes rather than instructs", which is the exact level-1 anchor. Level 2 would require at least high-level hints toward a task, but no task is even named.

1 / 5

Workflow Clarity

The body states it "lacks ordered steps" and indeed presents no sequence of any kind, matching level 1 ("Steps missing or incoherent; no sequence; no validation for risky operations"). Level 2 would require at least a rough sequence, which is entirely absent.

1 / 5

Progressive Disclosure

There are no bundle files (references/, scripts/, assets/ absent) and nothing is inlined that belongs in a separate file, so there are no buried or nested references. But the simple-skill exception cannot lift it to 5: the heading plus one non-instructional sentence is a stub, not a clear overview of organized content, and no section provides navigational value. Anchor 3 ("Some structure but could be better organized") is the best fit — above level 2 (no monolithic bulk to relocate) but below level 4 (no appropriately placed content to speak of).

3 / 5

Total

8

/

20

Passed

Description

0%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 is a placeholder that describes its own deficiencies rather than the skill's capabilities. It provides no domain, no concrete actions, no trigger guidance, and no way to distinguish it from any other skill. A complete rewrite stating what the skill does and when to use it is required.

Suggestions

State the concrete actions the skill performs in third person (e.g., 'Validates and rewrites SKILL.md descriptions'), replacing the meta-comment 'A skill without activation trigger phrases'.

Add an explicit 'Use when...' clause with natural trigger phrases, common synonyms, and file extensions users would actually say, which currently cap completeness at 1.

Include distinguishing domain terms so the description does not overlap with every other skill in the library.

DimensionReasoningScore

Specificity

The entire description is "A skill without activation trigger phrases" — it names no domain and no concrete action, only a meta-comment about the description itself. This matches the level-1 anchor ("Entirely vague; no concrete actions; pure abstract language"); it cannot be level 2 because not even a domain is named.

1 / 5

Completeness

Neither "what" nor "when" is present: the phrase "A skill without activation trigger phrases" says nothing about what the skill does or when to use it. Level 1 ("Missing both what and when") is the exact match; level 2 would require at least a vague 'what' or a 'when'.

1 / 5

Trigger Term Quality

There are no natural keywords whatsoever — no terms a user would say when needing this skill, not even generic ones like "files". Level 1 fits ("No natural keywords; only technical jargon or entirely generic language"); level 2 would require at least one or two generic keywords, which are absent.

1 / 5

Distinctiveness Conflict Risk

With no domain, actions, or triggers, the description is entirely generic and would conflict with virtually any other skill. Anti-drift check against level 2 ("Very broad; high overlap risk") confirms level 1 is the better fit since even a broad domain is never named.

1 / 5

Total

4

/

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

saif-shines/doraval

Path

test/fixtures/skills/drifted/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.