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.

1.98x

Quality

65%

Does it follow best practices?

Impact

99%

1.98x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/context-recovery/SKILL.md

The canonical home for this skill is context-recovery in jdrhyne/agent-skills

Quality

Content

67%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 well-structured, actionable recovery protocol with concrete code and a clear step sequence. Its main weaknesses are minor redundancy (repeated description, pseudocode duplicating triggers) and implicit rather than explicit validation checkpoints.

Suggestions

Remove the duplicated description paragraph at the top of the body and the 'Auto-Trigger Detection' pseudocode block, since both restate content already present in the Triggers section.

Add explicit validation/feedback checkpoints (e.g., verify the message:read fetch returned messages before parsing; if a fetch fails, retry or note the unavailable source) to strengthen workflow clarity.

Replace the pseudocode trigger block with a concrete checklist or fold it into the existing Triggers section to improve actionability.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code blocks, but the opening description is repeated from the frontmatter and the 'Auto-Trigger Detection' python pseudocode duplicates the already-listed Triggers section, so it could be tightened.	3 / 5
Actionability	Provides concrete message:read calls, executable bash/jq/grep snippets, and a ready-to-fill synthesis template; minor gaps come from placeholders and the pseudocode trigger block that is not directly executable.	4 / 5
Workflow Clarity	A clear 7-step protocol with well-defined sub-steps and stated bounds (50→100 messages, 2-hour goal, last 3 sessions); validation checkpoints are mostly implicit, but the operation is read-and-append rather than destructive, so gaps are minor.	4 / 5
Progressive Disclosure	Single-file skill with no bundle files, organized under clear section headers (Triggers, Execution Protocol, Channel-Specific Notes, Constraints, Example); good navigation, though the file is long and channel-specific notes could theoretically split out.	4 / 5
	Total	15 / 20 Passed

Description

62%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 clearly states what the skill does and gives an explicit trigger condition, with platform specificity aiding distinctiveness. It is held back by a single core action and trigger phrases that are more technical than the natural language users actually say.

Suggestions

Add a 'Use when...' clause with concrete user phrases such as 'continue', 'where were we?', or 'did this happen?' to raise trigger-term quality and completeness.

List 2-3 specific recovery actions (e.g., fetch channel history, extract session logs, synthesize a context summary) to broaden capability coverage.

Include synonyms or the literal word 'compacted'/'truncated' so the description matches the natural terms users and summaries emit.

Dimension	Reasoning	Score
Specificity	Names the domain ('recover working context after session compaction') and one concrete action plus the trigger condition and platforms, but offers only a single core action rather than a comprehensive list.	3 / 5
Completeness	Both 'what' (recover working context) and 'when' (after compaction or when continuation is implied but context is missing) are present; the 'when' is explicit but lacks concrete trigger phrases, so it is not a 5.	4 / 5
Trigger Term Quality	Relevant terms like 'session compaction', 'continuation is implied', and 'context is missing' appear, but the natural user phrases ('continue', 'where were we?', 'did this happen?') live in the body rather than the description, leaving common variations uncovered.	3 / 5
Distinctiveness Conflict Risk	The compaction/context-recovery niche with named platforms is mostly distinct from other skills, with only minor overlap risk against general memory or channel-history skills.	4 / 5
	Total	14 / 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: bap-jorkim/agent-skills-fork-feb-25
Path: skills/context-recovery/SKILL.md
Commit: f4ed46f

Reviewed: 4 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.