context-recovery

Recover missing conversation context after explicit compaction or truncation, or when the user explicitly asks to recover prior work. Use for requests such as "where were we before compaction?" when the current thread is insufficient. Do not trigger on a generic "continue" when the current thread already provides an actionable next step.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

75%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-crafted, trust-boundary-aware instruction skill with concrete templates, bounded scopes, and a clear sequenced recovery ladder plus failure handling. Minor gains are available from tightening template/list redundancy and making in-flow validation checkpoints more explicit.

Suggestions

Consolidate the 'Another source' enumerated requirements with the suggested approval-prompt blockquote to remove overlapping guidance and tighten conciseness.

Add an explicit in-flow validation checkpoint (e.g., 'verify retrieved items cover the missing fact before producing the report') inside the scope ladder to push workflow clarity toward 5.

Consider externalizing the full response-format template into a reference file so the SKILL.md body stays a lean overview, improving progressive disclosure for this 100+ line skill.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining known concepts; it earns a 4 rather than 5 because the approval-prompt blockquote and the preceding enumerated list overlap somewhat and could be tightened.	4 / 5
Actionability	Provides copy-paste-ready templates (approval prompt, recovery report format) and concrete bounds (50 items or 24 hours), but the actual retrieval mechanism is deliberately abstract ('Inspect the live capability schema rather than assuming a connector name'), leaving a minor executable-spec gap.	4 / 5
Workflow Clarity	A clear sequenced scope ladder ('Use the first sufficient stage and stop') plus a numbered failure-handling feedback loop; validation is framed as cautions and counterevidence-seeking rather than explicit embedded verify-checkpoints in the main flow, so it sits just below 5.	4 / 5
Progressive Disclosure	The single-file body is well-organized into clearly headed sections with easy navigation; at over 50 lines with no external references it has good structure but no one-level-deep reference split to reach 5.	4 / 5
	Total	16 / 20 Passed

Description

87%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, well-scoped description that clearly states both the capability and its activation conditions with concrete trigger phrasing and explicit non-trigger guidance. Minor room to broaden synonym coverage and enumerate more distinct actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ('Recover missing conversation context after explicit compaction or truncation') with concrete triggering conditions and an example phrase, landing above the 3 anchor though it centers on a single action rather than multiple distinct ones.	4 / 5
Completeness	Explicitly answers both what ('Recover missing conversation context...') and when ('Use for requests such as... when the current thread is insufficient') with concrete trigger phrases and explicit negative-trigger guidance.	5 / 5
Trigger Term Quality	Includes natural user phrasing such as 'where were we before compaction?', 'recover', and 'continue', giving good keyword coverage, though it lacks the breadth of synonyms that would warrant a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (post-compaction/truncation context recovery) and reduces conflict risk with explicit 'Do not trigger on a generic continue' boundary guidance.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: jdrhyne/agent-skills
Path: skills/context-recovery/SKILL.md
Commit: 439cd3a

Reviewed: 13 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.