my-tool

Fixture project-owned skill

Quality

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 ./.agents/skills/harness-engineering/tests/fixtures/good-project-owned-gittracked/.agents/skills/my-tool/SKILL.md

Quality

Content

18%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 effectively empty — a title with no guidance, examples, or workflow — so actionability and workflow clarity sit at the floor while conciseness and progressive disclosure land in the lower-middle because there is nothing to penalize structurally. It needs at least a minimal quick-start instruction to be usable.

Suggestions

Add a concise quick-start section with an executable command or code snippet covering the skill's primary task.

If the skill involves destructive or batch operations, include an explicit validate-then-proceed checkpoint so workflow clarity is not capped at 3.

If detailed material is needed, add one-level-deep reference links (e.g., See REFERENCE.md) instead of leaving the body empty.

Dimension	Reasoning	Score
Conciseness	The body is just the heading "# my-tool" with no padding or unnecessary explanation, so it is not verbose; however it carries no instructional content to be efficient with, leaving it between the lean (5) and vacuous anchors rather than clearly at either. A score of 3 reflects that it wastes no tokens yet provides nothing to act on.	3 / 5
Actionability	There is no code, command, or concrete instruction — only a title — matching the score-1 anchor ("Entirely vague or abstract; no concrete code or commands"). It cannot reach score 2 because even a high-level hint is missing.	1 / 5
Workflow Clarity	No steps or sequence are present at all, matching the score-1 anchor ("Steps missing or incoherent; no sequence"). The simple-skill exception cannot apply because there is no described action to clarify.	1 / 5
Progressive Disclosure	The body has only a single heading with no sections or references, giving minimal structure with nothing organized or navigable, which sits between the monolithic (1) and lightly-structured (3) anchors. It does not reach 3 because there are no organized sections to navigate.	2 / 5
	Total	7 / 20 Passed

Description

0%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 placeholder with no concrete capabilities, no natural trigger terms, and no usage guidance, placing it at the floor of every dimension. It needs to state specific actions and an explicit 'Use when...' clause to become functional.

Suggestions

Replace 'Fixture project-owned skill' with concrete actions the skill performs (e.g., 'Extract text from X, generate Y, validate Z').

Add an explicit trigger clause such as 'Use when the user mentions <keywords/file extensions>'.

Include natural synonyms and file extensions users would actually say to improve trigger-term quality and distinctiveness.

Dimension	Reasoning	Score
Specificity	The phrase "Fixture project-owned skill" names no concrete actions and uses purely abstract language, matching the score-1 anchor ("Entirely vague; no concrete actions"). It does not rise to score 2 because even a generic domain verb like "Processes PDF files" is absent.	1 / 5
Completeness	Neither a clear "what" nor any "when"/Use-when guidance is present; "Fixture project-owned skill" is extremely vague on both, matching the score-1 anchor and the guideline capping completeness at 3 when trigger guidance is missing (here it is fully absent, so 1).	1 / 5
Trigger Term Quality	No natural user keywords or synonyms appear; the description is generic fixture language rather than phrases a user would naturally say, matching the score-1 anchor. It cannot reach score 2 because not even one generic domain keyword is present.	1 / 5
Distinctiveness Conflict Risk	The description is entirely generic and would overlap with virtually any skill, matching the score-1 anchor; no niche or distinguishing trigger exists to lift it toward score 2.	1 / 5
	Total	4 / 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: TencentBlueKing/bk-bcs
Path: .agents/skills/harness-engineering/tests/fixtures/good-project-owned-gittracked/.agents/skills/my-tool/SKILL.md
Commit: 99ba07d

Reviewed: 13 hours 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.