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

73%

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

78%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 lean, well-structured instruction-only skill: a numbered workflow with a concrete fallback path and a ready-to-use sub-agent prompt template, plus sensible constraints against context bloat. Its only weaknesses are minor — slight redundancy in the delegation rationale and no guidance on resolving the session file path from the lineage.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence ("Do NOT read large session files directly into your own context"), with only minor redundancy — the sub-agent rationale appears in both the description and the Instructions/Constraints sections. Not a 5 because the delegation rationale is repeated and Constraints partly restate earlier steps.	4 / 5
Actionability	Provides concrete, executable guidance: a specific subagent type (`session-searcher`), a named fallback skill (`aichat:session-search`), and a copy-paste sub-agent prompt template. Not a 5 because it never explains how to locate the session file path from the lineage, leaving a small execution gap.	4 / 5
Workflow Clarity	A clear numbered 5-step sequence with an explicit fallback branch (sub-agents vs. session-search skill) and a defined report-back step; the operation is read-only so no destructive/batch validation cap applies. Not a 5 because there are no checkpoints confirming the extracted context before reporting back.	4 / 5
Progressive Disclosure	A simple, single-purpose skill at roughly 50 lines with well-organized sections (Instructions, Example Sub-agent Prompt, Constraints) and no content inlined that belongs in a separate file; per the rubric's simple-skill note, this qualifies for a 5 without external references.	5 / 5
	Total	17 / 20 Passed

Description

53%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 states a concrete, distinctive capability but reads as a "what" without a "when" — there is no explicit "Use when..." trigger guidance, which caps completeness. Trigger-term coverage is serviceable but lacks the natural synonyms users would actually say when they need this skill.

Suggestions

Add an explicit trigger clause, e.g. "Use when a session lineage is present and the user asks to recover, resume, or pick up context from a previous session."

Include natural user phrasings as trigger terms: "previous session", "last task", "resume work", "what was I working on".

Slightly enumerate the concrete actions (e.g. extract last task, its state, pending next steps, and key decisions) to raise specificity from 1-2 actions to several.

Dimension	Reasoning	Score
Specificity	Names the domain ("parent session", "session lineage") and 1-2 concrete actions ("Extract full context of the last task", "uses sub-agents to avoid bloating your own context"), but does not list several specific actions, matching the anchor for domain plus 1-2 concrete actions. Not a 4 because there is no broader catalog of specific capabilities.	3 / 5
Completeness	Has a clear "what" ("Extract full context of the last task from the most recent parent session") but no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not a 2 because the "what" is concrete and specific.	3 / 5
Trigger Term Quality	Includes some relevant keywords ("context", "parent session", "session lineage", "task") but misses the natural phrases a user would say, such as "previous session", "resume work", or "what was I working on". Not a 4 because common variations and synonyms are absent.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (recovering task context from a parent session in a session lineage) with distinct triggers like "session lineage" and "parent session"; only minor overlap risk with generic session-search or context-recovery skills. Not a 5 because the term "context" alone is broad enough to collide with other context-management skills.	4 / 5
	Total	13 / 20 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: 0ca7320

Reviewed: 14 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.