CtrlK
BlogDocsLog inGet started
Tessl Logo

keyword-stuffed

automation, automation, automation, automation, automation, automation, automation, automation, automation, automation, automation, automation. Use for CI, CD, build, deploy, release, pipeline, workflow, orchestration.

32

Quality

26%

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 ./crates/skill-validator-rs/tests/golden-corpus/fixtures/boundary/keyword-stuffed/SKILL.md

The canonical home for this skill is desc-1024 in pantheon-org/tekhne

SKILL.md
Quality
Evals
Security

Quality

Content

26%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 an empty stub: one ambiguous instruction ('Use the tool.') under a placeholder header, with no concrete guidance, no steps, no examples, and no supporting files. While it wastes no tokens, it delivers zero actionable content — the skill body fails at everything except brevity.

Suggestions

Replace 'Use the tool.' with concrete, executable guidance: name the specific tool/command and show at least one runnable example.

If the skill involves a multi-step process, list the steps in order and add validation checkpoints where operations are risky.

Add short, purposeful section headers (e.g., '## Quick start') so the body is organized, and split any detailed reference material into one-level-deep files in references/.

DimensionReasoningScore

Conciseness

The body is two lines ('# Body' / 'Use the tool.') with zero padding or explanations of known concepts, which is genuinely efficient. It falls short of the 5 anchor ('every token earns its place') because 'Use the tool.' earns nothing — the entire token budget is spent on a phrase that conveys no usable information.

4 / 5

Actionability

The only guidance is 'Use the tool.', which names no tool, command, or step — matching 'Entirely vague or abstract; no concrete code or commands; only describes rather than instructs'. It is not 2 because even a high-level hint of a specific step is absent.

1 / 5

Workflow Clarity

There is no sequence of steps at all — the body contains a single incoherent instruction with no defined process, matching 'Steps missing or incoherent; no sequence'. Even the simple-skill exception cannot apply because the one action is completely ambiguous ('the tool' is undefined).

1 / 5

Progressive Disclosure

The body has a bare '# Body' header and one line with no organized sections, and no bundle files exist (references/, scripts/, and assets/ are absent), so nothing is disclosed or navigable — matching 'Minimal structure'. It is not 3 because there is not even 'some structure': no sections organize the content, and the single line gives no overview of anything.

2 / 5

Total

8

/

20

Passed

Description

27%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 keyword-stuffed anti-pattern: a repeated buzzword in place of any capability statement, paired with a broad trigger list that spans an entire domain. It communicates when the skill might fire but gives no signal of what it actually does, and the stuffing behavior should be penalized as gaming the trigger-matching rather than informing the user.

Suggestions

Replace the repeated 'automation' keyword block with 1-3 concrete capability statements in third person (e.g., 'Runs build pipelines and manages deployment stages').

State a specific 'what' before the 'Use for...' clause so the description answers both what the skill does and when to use it.

Narrow the trigger list to a specific niche (e.g., a particular CI system or task) to reduce conflict risk with other DevOps-related skills.

DimensionReasoningScore

Specificity

The description is the word "automation" repeated twelve times, followed by a keyword list ("CI, CD, build, deploy, release, pipeline, workflow, orchestration") — no concrete capability or action is stated anywhere, matching the 'Entirely vague; no concrete actions; pure abstract language' anchor. It sits at 1, not 2, because it doesn't even name a domain plus generic action like 'Processes PDF files'; it names no verb-directed action at all.

1 / 5

Completeness

The 'when' is present ("Use for CI, CD, build, deploy, release, pipeline, workflow, orchestration") but the 'what' is entirely absent — the description never states what the skill does, exactly matching anchor 2's 'only when is present without what'. It is not 3 because that anchor requires a clear 'what', which the repeated 'automation' does not provide.

2 / 5

Trigger Term Quality

The trigger clause does include natural terms users would say ("CI, CD, build, deploy, release, pipeline, workflow, orchestration"), but the twelve-fold repetition of "automation" is keyword stuffing rather than natural phrasing, and no synonyms or variations are offered — fitting 'Some relevant keywords but missing common variations or synonyms'. It is not 4 because the stuffing pattern and absence of any variation (per the guideline penalizing buzzwords) undercut genuinely good keyword coverage.

3 / 5

Distinctiveness Conflict Risk

Triggers span the entire CI/CD and DevOps domain ("CI, CD, build, deploy, release, pipeline, workflow, orchestration") with no niche focus, creating high overlap risk with any deployment, build, or pipeline skill — matching 'Very broad; high overlap risk with many similar skills'. It is not 1 because the terms are at least confined to the delivery-automation domain rather than being fully generic like 'code and documents'.

2 / 5

Total

8

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
pantheon-org/tekhne
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.