CtrlK
BlogDocsLog inGet started
Tessl Logo

project-development

This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token and cost estimation, choosing between single-agent and multi-agent at the project level, structured output design for downstream parsing, and structuring agent-assisted iteration. Use this when the unit of work is a whole project or a multi-stage pipeline. Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/project-development/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.

A well-structured methodology skill with concrete pipeline guidance, a sequenced planning workflow, and clean progressive disclosure into real reference files. Its main weakness is redundancy: the Guidelines and Gotchas sections restate Core Concepts, inflating the token budget.

Suggestions

Collapse the Guidelines and Gotchas sections into Core Concepts (or drop them) to remove restated material and reduce the body's token footprint.

Add an explicit validate→fix→retry feedback loop to the planning template or process stage so batch-failure recovery is concrete rather than implied.

Inline one small executable snippet (e.g., the needs_processing file-existence check) in the body so the core idempotency pattern is copy-paste ready, not just described.

DimensionReasoningScore

Conciseness

Mostly efficient and does not explain basic concepts Claude already knows, but the Guidelines (10 items) and Gotchas (9 items) sections largely restate Core Concepts, adding redundant tokens that could be trimmed.

3 / 5

Actionability

Provides concrete guidance — the canonical acquire→prepare→process→parse→render pipeline, a file-system state layout, a cost formula with a 20-30% buffer, and a 5-step planning template — though most is methodological instruction rather than copy-paste code.

4 / 5

Workflow Clarity

The Project Planning Template is a clearly ordered 5-step sequence with validation embedded ('each step validates assumptions before the next step invests effort') and a manual-prototype gate, though the explicit fix→retry feedback loop is less spelled out than the anchor-5 example.

4 / 5

Progressive Disclosure

Well-organized into overview sections with two real one-level-deep references (case-studies.md, pipeline-patterns.md) and a script, each clearly signaled with 'Read when:' guidance; minor gap is the body's own length and section redundancy.

4 / 5

Total

15

/

20

Passed

Description

92%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 strong description: specific, complete with an explicit 'Use this when' trigger, and well-differentiated via explicit routing to sibling skills. The only minor gap is a few missing natural synonyms a user might utter.

DimensionReasoningScore

Specificity

Lists multiple concrete project-level actions — 'whether an LLM is the right primitive', 'the shape of a multi-stage batch or agent pipeline', 'token and cost estimation', 'choosing between single-agent and multi-agent', 'structured output design', 'structuring agent-assisted iteration' — with comprehensive coverage.

5 / 5

Completeness

Explicitly answers both what (enumerated project-level decisions about LLM-powered systems) and when ('Use this when the unit of work is a whole project or a multi-stage pipeline') with a concrete trigger clause.

5 / 5

Trigger Term Quality

Good natural-term coverage ('multi-stage pipeline', 'token and cost estimation', 'single-agent and multi-agent', 'structured output') that users would say, but a few common synonyms (e.g. 'batch processing', 'agent architecture') are implicit rather than named.

4 / 5

Distinctiveness Conflict Risk

Clear project/pipeline-shape niche with explicit routing of adjacent work ('Route individual tool design to tool-design and individual skill-loading or context-budget tactics to context-optimization'), minimizing wrong-skill activation.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
muratcankoylan/Agent-Skills-for-Context-Engineering
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.