CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creator

Create new OpenCode skills with the standard scaffold.

54

Quality

68%

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 ./.opencode/skills/skill-creator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 content is actionable and well-organized, with concrete commands, explicit scaffold rules, validation checkpoints, and copy-ready templates. Main weaknesses are redundancy between the scaffold checklist and the dedicated .env/template sections, and a workflow whose steps are presented out of order without error-recovery guidance.

Suggestions

Consolidate the .env/.gitignore guidance that currently appears in both the scaffold checklist and the dedicated sections, and merge the two overlapping frontmatter/skill templates into one.

Reorder the body to follow the actual execution sequence (mkdir → scaffold files → write SKILL.md from template → validate), and add a brief "if validation fails, fix and re-check" loop.

Replace bare placeholders in the minimal template ("Action 1", "command here") with a short worked example of a real generated skill.

DimensionReasoningScore

Conciseness

The body is mostly lean (checklists, commands, templates) but includes avoidable duplication: the .env/.gitignore rules appear both in the scaffold checklist and again in dedicated sections, and two overlapping templates ("Frontmatter template" and "Minimal skill template") repeat each other; awkward phrasing ("This should trigger this scaffold", "skills that are self-buildable") could also be tightened. It is not anchor 4 because several of these redundancies are noticeable, and not anchor 2 because there is no padding explaining concepts Claude already knows.

3 / 5

Actionability

Concrete, executable guidance dominates: the bash command "mkdir -p .opencode/skills/<skill-name>", an explicit minimum-scaffold file list, and copy-ready YAML/markdown templates with specific rules ("create a `.env.example` without credentials", "Always add a `.gitignore`... that ignores `.env`"). It falls short of anchor 5 only because the "Minimal skill template" contains bare placeholders ("command here", "Action 1") and there is no worked example of a finished generated skill.

4 / 5

Workflow Clarity

The sequence is discernible (create folder → add scaffold files → apply scaffold rules → validate description → verify .env not tracked) with real checkpoints ("Quick validation" checklist, "verify `.env` is not tracked"). It is not anchor 5 because there are no error-recovery feedback loops (what to do when validation fails), and the ordering scatters workflow steps between template sections rather than presenting one coherent ordered procedure.

4 / 5

Progressive Disclosure

No bundle files exist, and the ~97-line body is organized into clear, well-labeled sections (scaffold rules, trigger phrases, templates, .env, notes, reference) with a single external link clearly signaled ("Follow the official OpenCode skills docs"). It is below anchor 5 because the content exceeds simple-skill scale with some redundancy and interleaved template sections that could be consolidated, though no references are buried and nothing requires deep navigation.

4 / 5

Total

15

/

20

Passed

Description

53%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, distinct capability but omits any "Use when..." trigger guidance and natural trigger phrases. Adding explicit trigger conditions with quoted user phrases (as the skill's own body recommends) would raise completeness and trigger-term quality substantially.

Suggestions

Add a "Use when..." clause to the description, e.g. "Use when the user says 'create a skill', 'make a skill for this', or asks to scaffold a new OpenCode skill."

Include 2-3 quoted trigger phrases with common synonyms (create/make/scaffold a skill, new skill template) to improve trigger-term coverage.

Optionally enumerate the concrete actions (folder scaffold, SKILL.md, .env.example, .gitignore, scripts/) to strengthen specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

"Create new OpenCode skills with the standard scaffold" names the domain (OpenCode skills) and 1-2 concrete actions (create skills, apply a standard scaffold), but coverage is not comprehensive. It sits above anchor 2 ("Names the domain but actions are minimal or generic" like "Processes PDF files") because the deliverable (standard scaffold) adds a second concrete element, and below anchor 4 because it does not list several specific actions.

3 / 5

Completeness

The "what" is clearly stated (create OpenCode skills with the standard scaffold), but the "when" is entirely missing — there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the rubric guidelines. It is not anchor 4 or 5 because neither an explicit nor implicit usage condition appears in the description itself.

3 / 5

Trigger Term Quality

Relevant domain keywords are present ("Create", "OpenCode skills", "scaffold") which map to what a user would say ("create a skill"), but common variations and synonyms ("make a skill", "new skill", "skill template", "scaffold a skill") are absent. It matches anchor 3 ("Some relevant keywords but missing common variations or synonyms") rather than anchor 4, which requires broader natural-term coverage.

3 / 5

Distinctiveness Conflict Risk

"Create new OpenCode skills" occupies a clear, distinct niche (skill authoring/scaffolding) that would rarely conflict with ordinary task skills, though it could overlap with other meta/scaffolding skills. It falls below anchor 5 because the anchor example pairs the niche with distinct explicit trigger phrases, which this description lacks; it is above anchor 3 because the domain is specific rather than broadly overlapping.

4 / 5

Total

13

/

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
trackdubllc/Babel-Player-Alpha
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.