context-engineering-collection

A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops.

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

42%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-organized conceptual map of 17 sub-skills with a clear reference list, but it functions as a knowledge article rather than actionable skill guidance: it re-explains familiar concepts, provides no executable code or steps, and its reference structure is undercut by referenced paths that do not exist in the bundle alongside orphaned unreferenced assets.

Suggestions

Replace the re-explanation of known concepts (what context is, lost-in-middle, tool basics) with concise pointers to the relevant sub-skill files, trimming the body to an overview that earns its tokens.

Add at least one concrete, executable example or template per major pattern (e.g., a launch-brief skeleton, a harness loop snippet) to move from description to instruction.

Fix the bundle/references mismatch: either ship the 17 skills/*/SKILL.md files that are referenced, or update the References list to point at files that actually exist, and either reference or remove the orphaned SVG assets.

Dimension	Reasoning	Score
Conciseness	The prose is information-dense rather than filler-padded, but it re-explains concepts Claude already knows (what context is, lost-in-middle/U-shaped attention, what tools are), fitting 'mostly efficient but includes some unnecessary explanation that could be tightened.'	3 / 5
Actionability	The body is almost entirely abstract description with no code, commands, or copy-paste examples; high-level principles like 'prefer single comprehensive tools' are actionable hints but lack the specific steps to execute, matching 'minimal concrete guidance; high-level hints but missing specific steps.'	2 / 5
Workflow Clarity	No real multi-step workflow exists; the closest is the 'Practical Guidance' rough order (fundamentals -> architectural -> operational), which gives a sequence with no validation checkpoints, matching 'steps listed but validation gaps; sequence present but checkpoints missing.'	3 / 5
Progressive Disclosure	The References section cleanly lists 17 one-level-deep sub-skill links and the body is well-sectioned, but the referenced skills/*/SKILL.md paths do not exist in the bundle while the actual bundle assets (4 SVGs under assets/release/v2.3.0/) are unreferenced, and per-skill conceptual content is inlined rather than deferred to sub-files, matching 'some structure but could be better organized; references present but not clearly signaled / content that should be separate is inline.'	3 / 5
	Total	11 / 20 Passed

Description

75%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 cleanly states both what the collection covers and when to use it with an explicit 'Use when' trigger, and uses good natural terminology. It is held back from the top tier by generic rather than concrete actions and by the inherently broad conflict surface of a multi-domain collection.

Suggestions

Add one or two concrete, distinctive verbs or artifacts (e.g., 'designs operating loops,' 'structures launch briefs') to raise specificity above generic build/optimize/evaluate/debug.

Tighten the domain list or add a scoping qualifier so the description is less likely to compete with single-purpose skills in each sub-domain.

Dimension	Reasoning	Score
Specificity	Names the domains ("context engineering, harness engineering, multi-agent architectures, and production agent systems") and verbs (building, optimizing, evaluating, debugging), but these are generic meta-actions rather than concrete operations like "extract text from PDFs," matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers both: the 'what' ("A comprehensive collection of Agent Skills for...") and the 'when' via a concrete "Use when building, optimizing, evaluating, or debugging agent systems that require effective context management and reliable operating loops" clause, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural-term coverage ("context engineering," "multi-agent architectures," "debugging agent systems," "context management") that users would plausibly say, missing only a few synonyms/variations to reach comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The niche (context engineering / production agent systems) is somewhat specific, but as a 17-skill collection spanning fundamentals, architecture, evaluation, and methodology it overlaps broadly with many individual skills in those domains, matching 'somewhat specific but could still overlap with similar skills.'	3 / 5
	Total	15 / 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
relative_links	Relative link issues: 17 missing, 17 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: muratcankoylan/Agent-Skills-for-Context-Engineering
Path: SKILL.md
Commit: 6dbe1a1

Reviewed: 3 days ago

Table of Contents

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.