Tessl • The package manager for agent skills

SkillPublic

ask-dora

Use when the teammate types /ask-dora, or asks any Dora question, a routine idea, a pocket job, dora harness new, or a connector catalog question.

Quality

74%

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 ./skills/ask-dora/SKILL.md

Quality

Content

85%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 router skill: a clear decision tree with concrete commands, explicit fallbacks, termination markers, and hard guardrails (MUST NOT list), with no padding. Its only notable gaps are the duplicated content between the Empty map and Route steps and the unspecified Hermes install steps.

Dimension	Reasoning	Score
Conciseness	The body is lean router text with zero concept explanations — every line is routing logic, commands, or guardrails. The 'Empty' map and the 'Route' steps overlap in content, but each serves a distinct function (literal printed output vs. routing decision tree), leaving only minor instances that could be tightened — anchor 4 rather than 5.	4 / 5
Actionability	Concrete executable commands appear throughout ("dora harness apply <slug> --yes", "dora wire --for claude --run", "npx skills add scalekit-inc/authstack", "dora --help --json") with explicit branch behavior and a verbatim install snippet for authstack. The one gap: Hermes 'official install steps' are referenced but never provided, unlike the authstack snippet — anchor 4, not 5.	4 / 5
Workflow Clarity	The Route section is a clearly sequenced 1-9 decision tree with explicit branch conditions (skill 'on disk' vs. 'missing'), termination markers ('Done: that skill is loaded'), and an error-recovery checkpoint ('If Hermes is missing... print official install steps. Do not fake a pass'). No destructive or batch operations are involved, so no further validation is required — anchor 5.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ are absent), and nothing in the body belongs in one: routing tables, the empty-invocation map, and the MUST NOT guardrails are all appropriately inline. Sibling-skill delegation (grilling-for-routine, review-with-dora, discover-connectors, setup-agentkit, integrate-agentkit) is clearly signaled one level deep, and sections are well organized for a short single-file skill.	5 / 5
	Total	18 / 20 Passed

Description

51%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 has excellent trigger guidance and near-zero conflict risk, but it is a pure 'when' clause with no statement of what the skill does. Adding a one-line capability summary (e.g., 'Routes Dora asks to the right primitive skill') would lift both specificity and completeness substantially.

Suggestions

Add a leading 'what' clause before the 'Use when' trigger list, e.g., 'Routes Dora-related asks to the right primitive skill or dora CLI verb.'

Include the other Dora trigger surfaces the body handles — review/fix/unused/scan jobs, dora session, and dora wire — so teammates asking those also match naturally.

Use third-person capability phrasing ('Routes...') rather than only trigger phrasing, so the description doubles as a summary in skill listings.

Dimension	Reasoning	Score
Specificity	The description names the Dora domain and concrete trigger phrases ("routine idea", "pocket job", "dora harness new", "connector catalog question") but states no capability or action at all — there is no 'what this does'. This matches anchor 2 ('Names the domain but actions are minimal or generic'); score 3 requires 1-2 concrete actions, which are absent.	2 / 5
Completeness	The 'when' is explicit and multi-trigger ('Use when the teammate types /ask-dora, or asks any Dora question...'), but the 'what' is entirely missing — the description never says what the skill does. This is exactly anchor 2 ('only when is present without what'); score 3 requires a clear 'what'.	2 / 5
Trigger Term Quality	"/ask-dora", "routine idea", "pocket job", and "connector catalog question" are natural phrases a teammate would say, giving good keyword coverage including the slash command. A few natural terms covered by the body are missing from the description (e.g., "dora wire", "review/fix/scan" jobs, "session"), so it falls short of anchor 5's comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	"Use when the teammate types /ask-dora, or asks any Dora question" carves a clear niche with distinct triggers; minimal conflict risk with any other skill, matching anchor 5.	5 / 5
	Total	13 / 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: saif-shines/doraval
Path: skills/ask-dora/SKILL.md
Revision: f1834a4

Reviewed: 6 days ago

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.

ask-dora

Table of Contents

Is this your skill?