CtrlK
BlogDocsLog inGet started
Tessl Logo

multi-deliverable-tracking-2eb609

Systematic tracking and completion of all required deliverables before task termination

54

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./benchmarks/gdpval/skills/multi-deliverable-tracking-2eb609/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is actionable and well-structured with executable verification code, clear multi-step workflow, and recovery protocol. Minor redundancy in the checklist and anti-pattern examples is the only real weakness.

DimensionReasoningScore

Conciseness

The body is well-organized and mostly efficient, but the checklist format is shown twice with examples and the anti-pattern section repeats coverage already in the pitfalls table, matching the level-2 anchor; it avoids concept-explaining fluff so stays above level 1 but has minor padding that keeps it below level 3.

2 / 3

Actionability

Concrete checklist templates, an executable Python deliverable dict with a verify_all_complete function, and a runnable bash loop with `exit 1` provide copy-paste-ready guidance, matching the level-3 anchor; it is well above the pseudocode level.

3 / 3

Workflow Clarity

A clear sequence (identify -> track -> verify before stopping -> recovery) with explicit verification checkpoints and a feedback loop (acknowledge gap, complete, re-verify) matches the level-3 anchor for this batch/multi-output context.

3 / 3

Progressive Disclosure

As a single-file, simple skill with no bundle files and well-organized sections, it meets the scoring-note allowance for level 3; content is appropriately contained with clear section navigation.

3 / 3

Total

11

/

12

Passed

Description

35%

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 conveys the skill's purpose but is abstract and lacks explicit trigger guidance or natural user keywords. Adding a "Use when..." clause with concrete triggering phrases would materially improve it.

Suggestions

Add an explicit "Use when..." clause naming concrete triggering situations (e.g., tasks with multiple required files/outputs, conjunctions like "and"/"both"/"each").

Replace abstract phrasing with natural user-facing keywords (e.g., "multiple files", "checklist", "don't stop early") to improve trigger-term quality.

Name specific concrete actions (identify, checklist, verify, recover) rather than the single generic phrase "tracking and completion".

DimensionReasoningScore

Specificity

"Systematic tracking and completion of all required deliverables" names the domain and a couple of actions but offers no comprehensive list of concrete actions, matching the level-2 anchor; it is not level 3 (no multiple specific actions) and not level 1 (a domain and actions are present).

2 / 3

Completeness

It states what the skill does (track and complete deliverables) but provides no "Use when..." trigger clause, so per the guideline completeness is capped at 2; it is above level 1 because the "what" is present.

2 / 3

Trigger Term Quality

Terms like "deliverables" and "task termination" are abstract/technical rather than natural phrases a user would say, matching the level-1 anchor; no common user-facing variations appear, so it does not reach level 2.

1 / 3

Distinctiveness Conflict Risk

Generic deliverable-completion framing could overlap with general task-completion behaviors and lacks distinct triggers, matching level 2; it is somewhat specific (not level 1) but has no clear niche to reach level 3.

2 / 3

Total

7

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
HKUDS/OpenSpace
Reviewed

Table of Contents

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.