context-recovery
Automatically recover working context after session compaction or when continuation is implied but context is missing. Works across Discord, Slack, Telegram, Signal, and other supported channels.
Install with Tessl CLI
npx tessl i github:jdrhyne/agent-skills --skill context-recovery72
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
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 identifies a clear, distinct use case (context recovery after session compaction) and specifies supported platforms, which helps with distinctiveness. However, it lacks specific concrete actions explaining what 'recovery' entails and misses an explicit 'Use when...' clause with natural trigger terms users might actually say when they need this functionality.
Suggestions
Add an explicit 'Use when...' clause with natural trigger phrases like 'lost context', 'forgot what we were discussing', 'where were we', or 'resume our conversation'
Specify concrete actions performed during recovery, such as 'retrieves previous conversation state', 'restores file references', or 'reconstructs task progress'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (context recovery after session compaction) and mentions supported channels, but lacks specific concrete actions beyond 'recover working context' - doesn't explain what recovery entails or what specific operations are performed. | 2 / 3 |
Completeness | Describes what it does (recover working context after compaction) but lacks an explicit 'Use when...' clause. The 'when continuation is implied but context is missing' is somewhat implicit rather than providing clear trigger guidance. | 2 / 3 |
Trigger Term Quality | Includes some relevant terms like 'session compaction', 'continuation', 'context is missing', and channel names (Discord, Slack, etc.), but missing natural user phrases like 'lost context', 'forgot what we were doing', 'where were we', or 'resume conversation'. | 2 / 3 |
Distinctiveness Conflict Risk | Clear niche focused specifically on session compaction recovery and context restoration - this is a distinct technical scenario unlikely to conflict with other skills. The mention of specific messaging platforms adds further distinctiveness. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, actionable skill with clear workflow sequencing and concrete executable commands. The main weakness is moderate verbosity—some sections (channel-specific notes, pseudocode trigger detection) could be condensed or moved to reference files. The skill excels at providing a complete, step-by-step protocol with appropriate validation checkpoints.
Suggestions
Condense the channel-specific notes section into a brief table or move to a separate CHANNELS.md reference file
Remove the pseudocode trigger detection section—the trigger list above it is sufficient and the pseudocode adds little value
Consider moving the detailed output template (Recovered Context markdown) to a separate TEMPLATES.md file with just a brief inline example
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some unnecessary verbosity, such as the pseudocode trigger detection section and overly detailed channel-specific notes that could be condensed. The structured output templates are useful but add length. | 2 / 3 |
Actionability | Provides concrete, executable commands for message reading, session log extraction, and memory operations. The bash commands and message:read calls are copy-paste ready with clear parameter specifications. | 3 / 3 |
Workflow Clarity | Excellent 7-step workflow with clear sequencing, explicit validation logic (adaptive depth expansion), and a complete feedback loop. The protocol includes specific conditions for when to expand fetches and hard caps for token budget constraints. | 3 / 3 |
Progressive Disclosure | Content is well-organized with clear sections, but everything is inline in a single file. The channel-specific notes and detailed output templates could be split into reference files. No external file references are provided for advanced topics. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
68%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
license_field | 'license' field is missing | Warning |
body_output_format | No obvious output/return/format terms detected; consider specifying expected outputs | Warning |
Total | 11 / 16 Passed | |
- Reviewed
Table of Contents
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.