CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

creating-skills

Use when you need to create a new custom skill for a profile - guides through gathering requirements, creating directory structure, writing SKILL.md, and optionally adding bundled scripts

Quality

80%

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 ./.agency/plugins/nori/skills/creating-skills/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%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 compact, well-sectioned instruction skill with a concrete checklist template and useful good/bad examples that show rather than tell. Its weaknesses are the absence of any validation step in the creation workflow and the missing frontmatter example, leaving the agent to infer what "proper frontmatter" means.

Suggestions

Add a verification checkpoint to the workflow, e.g., after writing SKILL.md, confirm the file parses and the skill appears in the target profile before instructing the user to switch.

Include a minimal valid frontmatter example (name plus a one-line description with a 'Use when...' trigger) so "Write SKILL.md with proper frontmatter" is fully executable.

Move the two `.agency/plugins/nori/skills/...` example pointers into a clearly labeled 'Examples to reference' section with one line explaining what to look for in each.

DimensionReasoningScore

Conciseness

The body is lean and instructional, with a copy-paste checklist template and concrete good/bad examples, but includes minor trimmable explanations like "Scripts are simple code cli tools that do various things deterministically" and the generic Overview sentence about where skills are stored, matching anchor 4 (efficient, minor instances of over-explanation). It is not a 5 because a few sentences restate things Claude can infer from the examples.

4 / 5

Actionability

Mostly executable guidance: an exact <required> block template, a concrete mkdir example in the step-format illustration, specific script-handling rules ("callable from the Bash tool", "stored in the same place as the skill"), and good/bad examples with real paths like "/home/foobar/daily-analysis/<DD-MM-YYYY>/slack". It is not a 5 because "Write SKILL.md with proper frontmatter" never shows what proper frontmatter looks like — no YAML name/description example is given.

4 / 5

Workflow Clarity

The <required> block lays out a clear six-step sequence (gather requirements → select profile → create directory → write SKILL.md → scripts → instruct user to switch), but there are no validation or verification checkpoints (e.g., confirm the skill is recognized or loads correctly), matching anchor 3 (steps listed, checkpoints missing). It is not a 4 because anchor 4 requires most checkpoints present, and none are; it is not a 2 because the sequence itself is complete and each step is concrete.

3 / 5

Progressive Disclosure

With no bundle files present, all content appropriately lives inline under clear sections (Overview, Writing Skills, Writing scripts, Tools and Code), and the external pointers to `.agency/plugins/nori/skills/.../SKILL.md` are one level deep, matching anchor 4 (good structure, references mostly clear, minor organization gaps). It is not a 5 because those example references are embedded in <good-example> tags at the bottom without explicit navigation signaling, and the body runs ~80 lines where a small reference file could carry the examples.

4 / 5

Total

15

/

20

Passed

Description

82%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.

A strong description that explicitly covers both what the skill does and when to use it, with a distinctive niche and mostly concrete action list. Its main flaw is the second-person "you need" phrasing in the trigger clause, which both violates the third-person voice convention and costs it specificity points.

Suggestions

Rewrite the trigger clause in third person, e.g., "Use when the user asks to create a new custom skill for a profile", to satisfy the third-person voice requirement.

Consider adding the final workflow step (instructing the user to switch profiles) or a synonym like "skill creation" to round out action coverage and natural trigger terms.

DimensionReasoningScore

Specificity

The description lists four concrete actions ("gathering requirements, creating directory structure, writing SKILL.md, and optionally adding bundled scripts"), which matches anchor 4 (several specific actions, minor gaps such as the profile-switch step), but the trigger clause "Use when you need to create" uses second person, so the rubric's third-person voice penalty reduces the score by 1.

3 / 5

Completeness

Both parts are explicit: the 'what' is "guides through gathering requirements, creating directory structure, writing SKILL.md, and optionally adding bundled scripts" and the 'when' is the concrete trigger phrase "Use when you need to create a new custom skill for a profile", matching the anchor 5 example structure. It is not a 4 because the 'when' clause is already explicit and specific rather than improvable.

5 / 5

Trigger Term Quality

Good natural keyword coverage including "create a new custom skill", "profile", "SKILL.md", and "bundled scripts", but common variations users might say ("make a skill", "add a skill", "skill creation") are missing, matching anchor 4 rather than the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

"create a new custom skill for a profile" carves out a clear niche with a distinct trigger; no other plausible skill would claim this trigger, matching anchor 5 (clear niche, minimal conflict risk). It is not a 4 because the domain qualifier "for a profile" plus the creation-only scope leave no meaningful overlap with related skills.

5 / 5

Total

17

/

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

microsoft/FluidFramework

Path

.agency/plugins/nori/skills/creating-skills/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.