demo-profile

Demo skill for the SkillToolProfile example.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./examples/skilltoolprofile/skills/demo-profile/SKILL.md

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 minimal skill document: terse, purposeful, and mode-aware, with a verified executable script and no filler or over-explanation. Its only weakness is the unspecified 'docs' referenced in the knowledge-only mode instruction.

Dimension	Reasoning	Score
Conciseness	The 12-line body is lean and efficient: it states its purpose in one sentence, gives one command, and one behavioral rule, with no explanation of concepts Claude already knows and every token earning its place — a clear anchor-5 match.	5 / 5
Actionability	The full-mode path is fully executable ('sh scripts/write_profile.sh out/profile.txt' is a verified, real script), but the knowledge-only instruction 'use the docs for reasoning' leaves 'the docs' unspecified, which is a minor gap matching 'Mostly executable guidance; concrete code or commands with minor gaps'.	4 / 5
Workflow Clarity	This is a simple, single-purpose skill whose one action is unambiguous, with a clearly stated mode-dependent branch (run in full mode, treat as reference in knowledge-only mode) and no destructive or batch operations, so the simple-skill exception applies and it merits 5.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and its single referenced path (scripts/write_profile.sh) is a real, one-level-deep bundle file clearly signaled by the command — matching the guideline that short skills with well-organized content and no reference needs can score 5.	5 / 5
	Total	19 / 20 Passed

Description

25%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 honest but non-functional as a skill trigger: it states only that this is a demo tied to a code example, with no capabilities, no use-when guidance, and no natural keywords. It would rarely be selected by a user or model through description matching alone.

Suggestions

Add a concrete 'Use when...' clause stating the situations in which this skill should be invoked (e.g., 'Use when testing or demonstrating skill tool profile behavior').

Replace the vague 'Demo skill' framing with 1-2 concrete capabilities so the 'what' is explicit (e.g., 'Writes a demo profile file and documents full vs knowledge-only tool profile modes').

Include natural trigger terms a user or model would actually say (e.g., 'skill tool profile', 'full mode', 'knowledge-only mode') rather than only the API symbol 'SkillToolProfile'.

Dimension	Reasoning	Score
Specificity	"Demo skill for the SkillToolProfile example" names a domain (the SkillToolProfile example) but lists zero concrete actions or capabilities, matching the anchor 'Names the domain but actions are minimal or generic'. It cannot reach 3 because no concrete action verb or capability is stated at all.	2 / 5
Completeness	It offers a vague 'what' (a demo for an example) and entirely omits any 'when to use' guidance, matching anchor 2 'Has a vague what and no when'. The judging guideline that a missing 'Use when...' clause caps completeness at 3 is not even needed here, as the 'what' itself is too vague for 3.	2 / 5
Trigger Term Quality	The only substantive term is the technical symbol 'SkillToolProfile', which no user would naturally say when needing this skill; there are no natural keywords or synonyms, matching 'No natural keywords; only technical jargon or entirely generic language'.	1 / 5
Distinctiveness Conflict Risk	The reference to a specific developer API example gives it a clear niche unlikely to collide with other skills, but it provides no distinct trigger phrases, so it fits 'Mostly distinct; minor overlap risk' rather than the anchor-5 requirement of distinct triggers.	4 / 5
	Total	9 / 20 Passed

Validation

100%

Warnings & errors only

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: trpc-group/trpc-agent-go
Path: examples/skilltoolprofile/skills/demo-profile/SKILL.md
Commit: 9bb1c42

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.