dot-skill

Unified meta-skill engine for distilling colleague, relationship, or celebrity characters into reusable Skills. | 统一的 meta-skill 引擎，把 colleague、relationship、celebrity 三类对象蒸馏成可复用 Skill。

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with strong sequenced workflows and explicit validation feedback loops, but it is weakened by a full bilingual duplication and a monolithic structure that keeps large operational guides inline rather than offloading them to reference files.

Suggestions

Collapse the bilingual duplication: keep one canonical language and route the other to a separate reference file (e.g. references/zh.md), cutting roughly half the token load.

Move the lengthy Feishu OAuth/private-chat and DingTalk collection guides into a references/ file (e.g. references/feishu_collection.md) and keep only the command summary inline.

Verify or create the referenced prompts/ and tools/ paths so the progressive-disclosure navigation points to real bundle files rather than unresolved paths.

Dimension	Reasoning	Score
Conciseness	Each section is action-dense rather than explanatory, but the entire skill is duplicated verbatim in both Chinese and English (~730 lines each), and the Feishu OAuth/private-chat flows are lengthy, so it carries substantial unnecessary token weight that could be tightened.	2 / 3
Actionability	Provides fully executable, copy-paste-ready commands with concrete flags (e.g. 'python3 tools/feishu_auto_collector.py --name "{name}" --output-dir ./knowledge/{slug} --msg-limit 1000') and complete API call bodies, matching the 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Steps 0-5 are clearly sequenced with explicit validation checkpoints (Phase 1.5, Phase 2.5), PASS/FAIL gates, and fix-then-retry feedback loops ('If audit says FAIL, follow the Backfill Tasks before synthesis'; 'If validation says FAIL, revise the draft before continuing').	3 / 3
Progressive Disclosure	The two existing references/ files are correctly signaled one level deep, but the SKILL.md itself is a ~1465-line monolithic body with the entire Feishu collection guide and celebrity research protocol inline, and many referenced prompts/ and tools/ paths are not part of the bundle to verify, so content that should be split out remains inline.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 clearly names its three-object domain and core action but is abstract and lacks an explicit 'Use when...' trigger clause. It is solid but generic enough to cap most dimensions at the midpoint.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when the user wants to create a skill from a colleague, relationship, or celebrity figure').

Replace the jargon verb 'distilling' with concrete actions users would actually say, such as 'build, generate, or update a reusable Skill'.

List 2-3 specific concrete capabilities (e.g. 'collects Feishu/DingTalk material, analyzes persona, writes installable Skill files') to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	Names the domain ("colleague, relationship, or celebrity characters") and a concrete action ("distilling ... into reusable Skills"), but does not list multiple specific actions like the score-3 anchor; it is more abstract than 'Extract text and tables, fill forms, merge documents'.	2 / 3
Completeness	It states what the skill does (distill characters into reusable Skills) but provides no "Use when..." clause or equivalent explicit trigger guidance, so completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Includes relevant terms ("colleague", "relationship", "celebrity", "Skills") but leans on the jargon verb "distilling" and omits common natural phrasings a user would say (e.g. "create a skill", "make a skill"), matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The character-distillation niche is fairly specific, but "meta-skill engine" for creating skills overlaps the general skill-creation category, so it could still conflict with similar meta-skills rather than having a fully distinct trigger surface.	2 / 3
	Total	8 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1465 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: titanwings/colleague-skill
Path: SKILL.md
Commit: 47039d0

Reviewed: 4 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.