recover-context

Extract full context of the last task from the most recent parent session shown in the session lineage. Strategically uses sub-agents to avoid bloating your own context.

Quality

71%

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 ./plugins/aichat/skills/recover-context/SKILL.md

Quality

Content

85%

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-sequenced, actionable read-only workflow with concrete tool names and a copy-ready prompt template, organized into clean sections with no need for external references. Its only weakness is mild redundancy between the example prompt and step 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept explanations Claude already knows, but the 'Example Sub-agent Prompt' repeats the extraction list already given in step 3 and the 'avoid bloating your own context' rationale is stated twice, so it could be tightened.	2 / 3
Actionability	Guidance is concrete and copy-paste ready: a specific subagent_type ('session-searcher'), a named fallback skill ('aichat:session-search'), and a ready-to-use prompt template with specific instructions ('final 20-30 messages').	3 / 3
Workflow Clarity	A clearly numbered 5-step sequence with an explicit fallback (subagent -> session-search skill if sub-agents unavailable); this is a benign read-only extraction that does not require validation checkpoints, so the absence of validation does not cap the score.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no need for external references, and content is organized into well-signaled sections (Instructions, Example Sub-agent Prompt, Constraints); no bundle files exist, so a single well-organized file scores 3 per the simple-skills guideline.	3 / 3
	Total	11 / 12 Passed

Description

57%

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 clearly conveys a distinct, specific purpose but lacks an explicit 'Use when...' trigger clause and leans on technical jargon ('session lineage') over natural user phrasings. It answers 'what' well while leaving 'when' only implied.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when a session lineage is shown in the first user message and you need to recover the previous task's context.'

Replace or supplement jargon like 'session lineage' with natural user phrasings (e.g. 'previous session', 'what I was working on before').

List a couple more concrete sub-actions (e.g. summarize task state, surface pending next steps) to push specificity toward a multi-action list.

Dimension	Reasoning	Score
Specificity	Names the domain ('parent session', 'session lineage') and concrete actions ('Extract full context', 'uses sub-agents'), but does not list multiple specific concrete actions like the anchor-3 examples; it is one main action plus its method.	2 / 3
Completeness	It clearly states what the skill does, but provides no 'Use when...' clause — the 'when' (when a session lineage is present) is only implied, so completeness is capped at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Some relevant natural terms appear ('context', 'last task', 'parent session'), but 'session lineage' is technical jargon and common user phrasings are missing, matching the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The niche (recovering context from a parent session shown in a session lineage) is distinct and specific, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	9 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pchalasani/claude-code-tools
Path: plugins/aichat/skills/recover-context/SKILL.md
Commit: 45ee0e2

Reviewed: 2 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.