CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

artifact-completion

Create requested artifacts early, iterate from concrete output, and verify final deliverables

Quality

71%

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 ./resources/skills/agent/artifact-completion/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

92%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 exemplary compact instruction skill: lean, well-sectioned, with a clearly sequenced procedure, explicit validation checkpoints, a repair feedback loop, and pointed pitfalls. The only minor gap is the absence of illustrative examples for the verification step, which keeps actionability at 4 rather than 5.

DimensionReasoningScore

Conciseness

The body is lean and every line instructs ('Create a minimal complete version at the required location', 'Do not use a filename extension as proof that the file is valid in that format'); it assumes Claude's competence and contains no padding or explanation of known concepts. This clearly matches anchor 5, and nothing could be trimmed.

5 / 5

Actionability

Concrete directives throughout ('Extract the required deliverable path, format, content constraints, and acceptance criteria', 'Use the format's native parser, renderer, compiler, or test tool to inspect the artifact') — mostly executable guidance. It falls short of anchor 5 only in lacking illustrative examples (e.g., what a render check or validator invocation looks like), leaving minor gaps.

4 / 5

Workflow Clarity

The six-step procedure is clearly sequenced with explicit validation checkpoints (step 4 inspect via native tool, step 6 confirm) and an explicit repair feedback loop (step 5 'Repair specific validation, content, or presentation failures while preserving correct portions'), reinforced by a dedicated Verification checklist — a direct match for anchor 5. No destructive/batch cap applies since validation is present.

5 / 5

Progressive Disclosure

The skill is under 50 lines, needs no external references (none exist in the bundle), and is organized into well-signaled sections (When to Use, Procedure, Pitfalls, Verification). Per the rubric's simple-skill exception, this matches anchor 5.

5 / 5

Total

19

/

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 clear three-part workflow (create early, iterate, verify) but is entirely domain-generic and lacks any 'Use when...' trigger guidance. It would rarely be selected by matching natural user phrasing and risks conflicts with any deliverable-producing skill.

Suggestions

Add an explicit trigger clause, e.g., 'Use when the task asks for a file, report, patch, document, image, archive, or other persistent deliverable rather than only a text answer.'

Include natural keywords and concrete artifact types users actually name (report, document, config, archive, .pdf, .patch) instead of the generic 'artifacts'/'deliverables'.

Sharpen distinctiveness by scoping to the workflow that differentiates it — creating the output early and iterating from concrete output — so it does not compete with every file-producing skill.

DimensionReasoningScore

Specificity

Lists three actions ('Create requested artifacts early', 'iterate from concrete output', 'verify final deliverables') but the objects are generic nouns ('artifacts', 'deliverables') with no domain or file types, matching anchor 3 rather than the domain-specific action lists of anchor 4.

3 / 5

Completeness

The description answers 'what' (create early, iterate, verify) but contains no 'Use when...' clause or equivalent trigger guidance; the judging guideline explicitly caps completeness at 3 in that case. It is above anchor 2 because the 'what' is stated as three concrete actions rather than vague.

3 / 5

Trigger Term Quality

The only keywords are 'artifacts' and 'deliverables' — generic jargon rather than natural phrases users say (e.g., 'write a report', 'make a patch', '.pdf'). This matches anchor 2 ('one or two generic keywords; missing the natural phrases users say') and not anchor 3, which requires a relevant domain keyword like 'Works with PDF files'.

2 / 5

Distinctiveness Conflict Risk

Nearly any task that produces a file or answer could trigger this description, creating high overlap risk with many skills — anchor 2. It sits above anchor 1 only because the early-creation/iterate/verify workflow angle provides a slight distinguishing niche.

2 / 5

Total

10

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

odysseus-dev/odysseus

Path

resources/skills/agent/artifact-completion/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.