context-management-context-restore

Use when working with context management context restore

Quality

42%

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-restore/SKILL.md

Quality

Content

61%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 compact, well-sectioned procedure with a genuinely instructive example and honest limitations, and it avoids padding elsewhere. Its weaknesses are the misplaced boilerplate preamble with a hard-coded date, implicit rather than explicit validation checkpoints, and abstract steps that lack concrete commands.

Suggestions

Replace abstract steps with executable ones, e.g. 'Run git status and git stash list to inventory dirty work' and 'Confirm the ledger's recorded SHA with git rev-parse HEAD' in the Procedure and Inputs sections.

Make the verify-then-proceed loop explicit: add a step such as 'Re-run the checks covering Y before treating any work as complete; if they fail, fix and re-run' instead of the implicit caution 'A past test run does not validate new edits'.

Move or trim the 'Compatibility and maintenance' preamble — relocate it below the H1 (or into a maintenance note) and drop the hard-coded 'Modified in AAS on 2026-09-05' date, which is time-sensitive detail that does not help execution.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no re-teaching of known concepts, but the 'Compatibility and maintenance' preamble is boilerplate and includes the time-sensitive date 'Modified in AAS on 2026-09-05' outside any deprecated/old-patterns section, which the guidelines penalize.	4 / 5
Actionability	Guidance is high-level ('Locate the latest task ledger', 'Read only the referenced files relevant to the pending action') with no concrete commands or search strategies; only the Example section approaches usable specificity ('Check X against the recorded result, inspect Y separately').	3 / 5
Workflow Clarity	A clear six-step procedure exists, but validation checkpoints are implicit rather than explicit — 'A past test run does not validate new edits' is a caution, not a checkpoint, and no verify-then-proceed or fix-and-retry loop is spelled out.	3 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files needed, and sections (When to Use, Inputs, Procedure, Example, Limitations) are well organized, but the compatibility preamble sits before the H1 title — a minor organization gap that keeps it from a clean top score.	4 / 5
	Total	14 / 20 Passed

Description

23%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 a bare, jargon-laden when-clause: it names no capabilities, gives no natural trigger phrases, and does not say what the skill actually does. A user or Claude selecting skills would have little basis to choose it over related context-management skills.

Suggestions

State what the skill does before the when-clause, e.g. 'Restores interrupted project work from a saved handoff or task ledger by validating past notes against the current checkout.'

Replace the redundant phrase 'context management context restore' with natural user vocabulary such as 'resume interrupted work', 'pick up where I left off', 'handoff notes', or 'restore context'.

Add concrete triggers to the when-clause, e.g. 'Use when resuming a stopped session, reconstructing a prior decision, or comparing a saved handoff with the current git checkout.'

Dimension	Reasoning	Score
Specificity	The description is only a when-clause ('Use when working with context management context restore') with no action verbs or concrete capabilities whatsoever, matching the 'no concrete actions; pure abstract language' anchor.	1 / 5
Completeness	Only 'when' is present with no 'what' — the description never states what the skill does, matching the anchor 'only when is present without what'.	2 / 5
Trigger Term Quality	'context management context restore' is redundant technical jargon; the natural phrases a user would actually say ('resume work', 'pick up where I left off', 'handoff', 'context window') are missing.	2 / 5
Distinctiveness Conflict Risk	It points at a specific niche (restoring project context/handoffs) but the broad phrase 'context management' overlaps with many memory- and context-handling skills, and no distinct trigger phrasing separates it.	3 / 5
	Total	8 / 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-restore/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.