CtrlK
BlogDocsLog inGet started
Tessl Logo

multi-deliverable-tracking-1e842b

Track completion status of all required deliverables and ensure ALL outputs are completed before stopping

49

Quality

62%

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-1e842b/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 a well-structured, actionable process skill with concrete templates, a clear multi-step sequence, and an explicit verification checkpoint before stopping. Its main weakness is conciseness — the example and anti-pattern sections restate the instructions — rather than gaps in guidance.

Suggestions

Collapse the 'Example Workflow' into a condensed walkthrough or remove it, since it restates Steps 1-3; alternatively, use it to show an edge case (e.g. a blocked deliverable) instead of the happy path.

Merge 'Anti-Patterns to Avoid' and 'Prioritize Completion Over Speed' into the relevant steps to remove redundancy and recover token budget.

Strengthen the error-recovery feedback loop in Step 4 with a concrete validate-fix-retry sequence rather than the vague 'switch tools, methods, etc.'

DimensionReasoningScore

Conciseness

The body is mostly efficient and assumes Claude's competence, but the 'Example Workflow' largely restates the four instruction steps and the 'Anti-Patterns'/'Prioritize Completion Over Speed' sections repeat prior guidance, so it could be tightened. Not a 4 because the redundancy is noticeable rather than minor.

3 / 5

Actionability

Provides concrete, copy-paste-ready templates (Required Deliverables Checklist, Progress Tracker with real placeholder rows) and a fully worked example workflow with explicit update/verify actions. Not a 5 because the templates remain generic placeholders rather than covering specific common cases end-to-end.

4 / 5

Workflow Clarity

Four steps are clearly sequenced with an explicit 'Verify Before Stopping' checkpoint and a feedback loop in Step 4 (attempt alternative approaches), plus a final verification in the example. Not a 5 because the error-recovery guidance is thin ('switch tools, methods') rather than a concrete validate-fix-retry loop.

4 / 5

Progressive Disclosure

Single file with well-organized sections (Purpose, Problem Pattern, Instructions, Example Workflow, Anti-Patterns, When to Apply) and no external references needed; content is appropriately inline. Not a 5 because the skill exceeds the 50-line simple-skill threshold, so the well-organized-sections exception does not strictly apply, though no splitting is genuinely warranted.

4 / 5

Total

15

/

20

Passed

Description

38%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 conveys a clear 'what' but lacks an explicit 'when/Use when' trigger and relies on generic process vocabulary, leaving it non-distinct and weakly triggered. It reads as a behavioral mandate rather than a discoverable, capability-scoped skill description.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggering situations, e.g. 'Use when a task requires multiple distinct deliverables and risks stopping after partial completion.'

Replace generic terms ('outputs', 'completed') with natural user phrasings and synonyms a person would actually say ('finish everything I asked', 'don't stop until all parts are done', 'multiple files to produce').

Tie the capability to a concrete niche to reduce overlap, e.g. name the multi-deliverable tracking behavior as distinct from general planning skills.

DimensionReasoningScore

Specificity

Names the domain ('required deliverables', 'outputs') and 1-2 concrete actions ('Track completion status', 'ensure ALL outputs are completed'), but coverage is not comprehensive. Not a 4 because only two actions are listed and both are fairly abstract.

3 / 5

Completeness

The 'what' is clear (track deliverable completion and ensure all outputs finish), but the 'when' is entirely absent with no explicit trigger guidance, capping completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Keywords are generic process terms ('completion status', 'deliverables', 'outputs', 'completed') that a user would rarely say verbatim when they need this skill, and there is no 'Use when...' trigger phrase. Not a 3 because natural user phrasings and synonyms are missing.

2 / 5

Distinctiveness Conflict Risk

The description is a very broad process-level statement that would overlap with virtually any task-completion or planning skill, with no niche-specific triggers to disambiguate. Not a 3 because nothing distinguishes it from sibling skills.

2 / 5

Total

10

/

20

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.

Validation — 16 / 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.