CtrlK
BlogDocsLog inGet started
Tessl Logo

project-development

This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.

40

Quality

38%

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 ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/project-development/SKILL.md

The canonical home for this skill is project-development in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

38%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-sectioned but overly long monolith that re-explains concepts Claude already knows and inlines material (case studies, pipeline patterns, examples) that should live in separate reference files. Batch operations lack explicit validation feedback loops, capping workflow clarity at 3.

Suggestions

Move Case Studies, Pipeline Patterns, and Examples into separate reference files under references/ and link to them one level deep, turning SKILL.md into a lean overview.

Trim conceptual exposition Claude already knows (LLM-suited/unsuited characteristic tables, basic pipeline-stage explanations) to improve token efficiency.

Add explicit validate->fix->retry feedback loops to the batch pipeline workflow (e.g. parse-failure logging and re-run gating) to lift workflow clarity above 3.

DimensionReasoningScore

Conciseness

At ~340 lines the body extensively explains concepts Claude already knows (e.g. 'Not every problem benefits from LLM processing', characteristics tables of LLM-suited/unsuited tasks, what pipeline stages are), with noticeable padding across 'Core Concepts', 'Detailed Topics', and 'Practical Guidance' that matches the 'noticeably verbose; several unnecessary explanations or padded sections' anchor below the mostly-efficient level 3.

2 / 5

Actionability

Concrete artifacts exist (the 'acquire -> prepare -> process -> parse -> render' pipeline, the data/{id}/ file layout, the cost formula, the example prompt structure, and the 5-part planning template), but as an instruction skill the guidance stays at the process/template level without the per-step specificity needed to reach level 4's 'mostly executable guidance'.

3 / 5

Workflow Clarity

The pipeline stages and planning template are clearly sequenced and the manual-prototype step acts as a pre-build gate, but the batch-processing pipeline (930 items, 15 workers) lacks explicit validate->fix->retry feedback loops, so per the batch-operation cap workflow_clarity cannot exceed 3 even though the sequence itself is clear.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) yet the body inlines everything — including Case Studies, Pipeline Patterns, and Examples that clearly belong in separate files — and the 'References' section points to 'Case Studies' and 'Pipeline Patterns' that are not real files, matching the 'content that clearly belongs in separate files is inlined' anchor below the well-organized level 3.

2 / 5

Total

10

/

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 clearly states what the skill covers but is abstract and lacks any 'Use when...' trigger guidance, capping completeness at 3. Trigger terms are technical rather than natural, and the broad scope creates real overlap risk with related skills in the same collection.

Suggestions

Add an explicit 'Use when...' clause with concrete trigger phrases users would naturally say (e.g. 'Use when starting an LLM-powered project, choosing between agents and traditional code, or planning a batch processing pipeline').

Replace abstract verbs ('identifying', 'designing', 'iterating') with more concrete capability statements to raise specificity.

Narrow the scope or foreground a distinguishing niche to reduce overlap with the tool-design and multi-agent-patterns skills it references.

DimensionReasoningScore

Specificity

Phrases like 'identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly' name the domain and several activities, but the actions are abstract ('identifying', 'designing', 'iterating') rather than concrete operations, fitting the 'names domain and 1-2 concrete actions but not comprehensive' anchor and falling below the multi-specific-action level 4.

3 / 5

Completeness

The description gives a clear 'what' ('covers the principles for identifying... designing... iterating') but provides no 'when'/Use-when clause, so per the missing-trigger-guidance cap it lands at level 3 ('clear what but when is missing or only weakly implied') and cannot reach level 4.

3 / 5

Trigger Term Quality

Terms such as 'LLM processing', 'project architectures', and 'agent-assisted development' are present but lean technical; the natural phrases a user would actually say (e.g. 'build an LLM project', 'agent development') are largely missing, matching the 'one or two generic keywords; missing the natural phrases users say' anchor rather than level 3's broader keyword coverage.

2 / 5

Distinctiveness Conflict Risk

The scope is broad and explicitly overlaps with sibling skills it later references (tool-design, multi-agent-patterns, evaluation), creating high overlap risk consistent with the 'very broad; high overlap risk with many similar skills' anchor rather than the more narrowly niched level 3.

2 / 5

Total

10

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.