context-engineering-advisor

Diagnose context stuffing vs. context engineering. Use when an AI workflow feels bloated, brittle, or hard to steer reliably.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/context-engineering-advisor/SKILL.md

Quality

Content

77%

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

A thorough, well-structured interactive diagnostic with concrete templates and a clear multi-step workflow. Its weakness is conciseness (repetition and re-explanation of LLM basics) and the absence of progressive disclosure—everything lives in one large file with no supporting reference bundles.

Suggestions

Trim the Purpose section (it duplicates the frontmatter intent) and condense the Key Concepts LLM fundamentals to only what is non-obvious, since Claude already knows parametric vs. contextual knowledge, RAG, and vector databases.

Offload the three long worked Examples and the detailed Context Manifest/PLAN.md templates into separate reference files under references/, keeping SKILL.md a concise overview with one-level-deep, clearly signaled links.

Consolidate the duplicated stuffing-vs-engineering framing that appears in both the comparison table and the Application steps to reduce token cost without losing the diagnostic structure.

Dimension	Reasoning	Score
Conciseness	The body is substantive but verbose: the Purpose section restates the frontmatter intent verbatim, and Key Concepts re-explains LLM fundamentals Claude already knows (e.g., "LLMs have parametric knowledge (encoded during training) = static, outdated"), so it could be tightened considerably despite being accurate.	2 / 3
Actionability	Highly concrete for an instruction-only skill: fill-in-the-blank sentences (the Falsification Protocol), a copy-ready Context Manifest template, specific thresholds (persist at 80%+, retrieve below 20%), and worked examples with measured outcomes.	3 / 3
Workflow Clarity	A clearly sequenced Step 0–Step 9 diagnostic with explicit branching (symptom-count thresholds route to 0-1 / 2-3 / 4+ paths) and a synthesized action plan with a timeline; no validation feedback loops are needed for an advisory (non-fragile) workflow.	3 / 3
Progressive Disclosure	The skill is organized into clear sections, but it is essentially a monolithic ~750-line file with all detail inline and no bundle files in references/scripts/assets; content that could be split out (long Examples, the conceptual explainer) is not offloaded to one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 concise, third-person description that cleanly pairs a concrete diagnostic action with an explicit use-when trigger and a distinctive niche. Its main weakness is limited breadth—single action verb and a narrow symptom-cluster trigger—rather than vagueness.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Diagnose context stuffing vs. context engineering") and a specific domain, but lists only a single diagnostic action rather than multiple concrete capabilities, so it is not comprehensive enough for a 3.	2 / 3
Completeness	It explicitly answers both what ("Diagnose context stuffing vs. context engineering") and when ("Use when an AI workflow feels bloated, brittle, or hard to steer reliably") with an explicit trigger clause.	3 / 3
Trigger Term Quality	Natural trigger phrasing ("AI workflow feels bloated, brittle, or hard to steer reliably") would plausibly be said by a user, but coverage is narrow—focused on one symptom cluster with no common variations—so it falls short of the broad keyword coverage expected for a 3.	2 / 3
Distinctiveness Conflict Risk	The "context stuffing vs. context engineering" framing carves a clear, distinctive niche with trigger symptoms unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (776 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 5 suspicious	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/context-engineering-advisor/SKILL.md
Commit: 9971018

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.