context-management-context-save

Use when working with context management context save

Quality

33%

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-management-context-save/SKILL.md

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 marketing-style knowledge dump about context engineering rather than an operational skill: pseudocode examples, validation-free workflows, generic instructions, and a broken reference to a nonexistent playbook. Its section headers give it some shape, but almost nothing in it is directly executable, and roughly a third of the content is boilerplate or aspirational filler.

Suggestions

Replace the pseudocode examples with executable code (define or import extract_project_metadata, semantic_compression, etc.) and add a runnable end-to-end capture-store-retrieve example.

Create the referenced resources/implementation-playbook.md (or fix the path) and move the vector DB integration, compression, and JSON schema details into it, keeping SKILL.md as a lean overview.

Add validation checkpoints to the workflows (e.g., verify the context artifact round-trips / deserializes losslessly before archiving) and delete the Future Roadmap, Role and Purpose, and circular use/don't-use sections.

Dimension	Reasoning	Score
Conciseness	Several sections are padded marketing fluff that adds nothing Claude doesn't know — 'An elite context engineering specialist', 'Compliance with enterprise knowledge management standards', the entire 'Future Roadmap' section, and circular 'Use this skill when / Do not use this skill when' boilerplate. This matches anchor 2 (noticeably verbose; several unnecessary explanations or padded sections) rather than 3, because the padding spans multiple full sections, not isolated sentences.	2 / 5
Actionability	There is some concrete material — the parameter list ($PROJECT_ROOT, $CONTEXT_TYPE, etc.), the JSON serialization schema, and two numbered workflows — but the Python examples are pseudocode calling undefined functions (extract_project_metadata, semantic_compression, advanced_vector_compression) and the Instructions section is generic ('Apply relevant best practices and validate outcomes'). This matches anchor 3 (some concrete guidance but incomplete; pseudocode instead of executable code) rather than 4, since nothing shown is executable end-to-end.	3 / 5
Workflow Clarity	The two Reference Workflows list ordered steps ('Analyze project structure -> Extract architectural decisions -> ... -> Create markdown summary') but contain no commands and no validation checkpoints for operations that capture and archive project state. This matches anchor 3 (steps listed but validation gaps, checkpoints missing); it does not reach 4 because there is no verification step anywhere, and the generic 'validate outcomes' instruction is not a concrete checkpoint.	3 / 5
Progressive Disclosure	The single reference in the body — 'open resources/implementation-playbook.md' — points to a file that does not exist (no references/, scripts/, assets/, or resources/ directories are present), so the promised detail layer is a dead link. Meanwhile ~180 lines of vector-database integrations, compression algorithms, and JSON schemas that belong in reference files are inlined in SKILL.md. This matches anchor 2 (minimal structure; content that belongs in separate files is inlined) rather than 3, because the only reference is broken rather than merely unclear.	2 / 5
	Total	10 / 20 Passed

Description

28%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 is essentially a circular restatement of the skill's name: it provides a 'when' with no 'what', no concrete capabilities, and no natural trigger phrases. It reads as auto-generated filler rather than a functional description, and would likely fail to fire for real users or misfire against sibling context-management skills.

Suggestions

State what the skill does first, in third person, with 2-3 concrete actions (e.g., 'Captures project context, serializes session state to structured artifacts, and supports semantic retrieval across sessions').

Add natural trigger phrases and synonyms users would actually say, such as 'save context', 'preserve session state', 'resume work later', or 'context snapshot', rather than repeating the skill name.

Combine 'what' and 'when' in one sentence following the pattern of the good examples: concrete actions, then 'Use when...' with explicit triggers.

Dimension	Reasoning	Score
Specificity	The description 'Use when working with context management context save' names a domain but contains zero concrete capability actions — there is no verb describing what the skill actually does (capture, serialize, retrieve context, etc.). It sits between anchor 1 (no concrete actions, pure abstraction) and anchor 3 (domain plus 1-2 concrete actions); since the domain is clearly named but no actions exist, anchor 2 is the closest fit.	2 / 5
Completeness	A 'when' clause is present ('Use when working with context management context save') but the 'what' is entirely absent — the description never states what the skill does. This is an exact match for anchor 2 ('only when is present without what'), and it cannot reach 3 because there is no clear 'what' to complement the 'when'.	2 / 5
Trigger Term Quality	The only keywords are the jargon-y, self-repeating phrases 'context management context save' — no natural user phrasings like 'save context', 'preserve session state', or 'context persistence'. This matches anchor 2 (one or two generic keywords, missing the natural phrases users say) rather than anchor 3, which requires genuinely relevant keywords users would employ.	2 / 5
Distinctiveness Conflict Risk	The trigger names a specific niche ('context save'), but that territory overlaps with general context-management, memory, and session-persistence skills, and the circular phrasing gives no signal to disambiguate. This matches anchor 3 (somewhat specific but could still overlap with similar skills) — not 4, since related skills would plausibly fire on the same phrase.	3 / 5
	Total	9 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: sickn33/agentic-awesome-skills
Path: skills/context-management-context-save/SKILL.md
Commit: 7b534bc

Reviewed: 5 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.