Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

aven

Use aven to find tasks, update status, and leave durable handoff context.

Quality

69%

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 ./.claude/skills/aven/SKILL.md

Quality

Content

71%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.

This is a generated delegation stub: maximally lean and unambiguous about its single instruction, but it delegates 100% of the skill's substance to an external file outside the bundle, which cannot be verified to exist and has no fallback. As a standalone SKILL.md it provides almost nothing actionable for the capabilities its description advertises.

Suggestions

Inline a brief overview (3-5 lines) of the shared skill's core commands or workflow so the file carries minimal standalone value if the external path is missing — this would raise actionability.

Make the delegation target verifiable: reference the shared skill via a path shipped with the bundle, or document the environment requirement that ~/.agents/skills/aven must be installed.

Add a fallback instruction for when the shared skill file is absent (e.g., report the missing dependency rather than proceeding blind), which would also add the missing validation checkpoint for workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is two lines — a generator comment and one delegation instruction — with zero padding and no explanation of concepts Claude already knows. Every token earns its place, matching the anchor-5 example of lean, competence-assuming content.	5 / 5
Actionability	The single directive ("Load and follow the shared skill at `~/.agents/skills/aven/SKILL.md`") is concrete with an exact path, but it is the only guidance present — no commands, examples, or steps for any of the three capabilities the description claims, and the target file lives outside the bundle and cannot be resolved. This matches anchor 3 (some concrete guidance but incomplete, missing key details) rather than 4, since the gap is the entire substance of the skill, not a minor detail.	3 / 5
Workflow Clarity	The single action — load and follow the shared skill — is unambiguous, and per the simple-skill note a single clear action can score highly. It falls to 4 rather than 5 because the delegation hop has no validation or fallback: if the referenced file is absent (as it is in this environment), the workflow dead-ends with no recovery step.	4 / 5
Progressive Disclosure	The reference is clearly signaled and exactly one level deep, which is good, but it points to an absolute home-directory path outside the skill bundle that does not exist in the review environment, and the SKILL.md contains no overview content of its own. Anchor 4 assumes only 'minor organization gaps'; a reference that cannot be verified to resolve, with zero in-file overview, is a larger structural gap, placing this at 3.	3 / 5
	Total	15 / 20 Passed

Description

53%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 serviceable but incomplete description: it clearly states what the skill does via three named actions anchored by the tool name aven, but it entirely omits when to use it and offers thin trigger vocabulary. Adding an explicit trigger clause and natural synonyms would raise completeness and trigger quality substantially.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases, e.g., 'Use when the user asks to find or claim tasks, update task status, or leave handoff notes for the next agent' — this would lift completeness from 3 to 4-5.

Make the actions more mechanically concrete: instead of 'find tasks, update status', name what is operated on and how (e.g., 'list and claim available tasks, move task status through todo/doing/done, attach handoff notes').

Broaden trigger vocabulary with natural synonyms users would actually say — todo, pick up work, task assignment, handoff notes — to improve trigger_term_quality.

Dimension	Reasoning	Score
Specificity	The description names the domain (aven, task management) and three actions — "find tasks", "update status", "leave durable handoff context" — but these are high-level CRUD-style verbs rather than mechanically concrete operations, and coverage is not comprehensive. It sits at anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4, whose examples list specific operations like "extracts text, fills forms, converts pages to images".	3 / 5
Completeness	The "what" is clear (find tasks, update status, leave durable handoff context) but there is no "Use when..." clause or equivalent trigger guidance anywhere. Per the judging guidelines a missing when-clause caps completeness at 3, which is exactly the anchor: clear what, when missing.	3 / 5
Trigger Term Quality	"tasks", "status", and "handoff" are relevant, fairly natural keywords, but common variations and synonyms are missing (e.g., todo, pick up work, claim a task, handoff notes). This matches anchor 3 (some relevant keywords, missing common variations) rather than 4, which requires good keyword coverage with only a few natural terms missing.	3 / 5
Distinctiveness Conflict Risk	Naming the specific tool "aven" plus a distinctive action trio ("leave durable handoff context") makes it mostly distinct with only minor overlap risk against other task-management skills. It is not 5 because "find tasks" and "update status" are generic verbs that could collide with todo/tracker skills absent any niche-defining trigger phrasing.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: phatblat/dotfiles
Path: .claude/skills/aven/SKILL.md
Revision: 4d65cab

Reviewed: 7 hours 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.

aven

Table of Contents

Is this your skill?