CtrlK
BlogDocsLog inGet started
Tessl Logo

context-recovery

Post-compaction recovery runbook for reconstructing active lane state from Memory Core recency, semantic recall, session rollups, and A2A. Triggers: Use immediately after context compaction/compression, resuming a summarized session, or noticing the active lane was reconstructed from a lossy summary.

68

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 an exemplar of lean, pointer-style progressive disclosure that delegates detail to a well-structured reference. The main weakness is that almost all actionable and workflow content lives in the reference, so the body scores slightly below ceiling on actionability and workflow clarity.

DimensionReasoningScore

Conciseness

Two lean sentences with no padding; it assumes Claude's competence and does not explain what compaction is, so every token earns its place.

5 / 5

Actionability

Gives a concrete instruction with a named tool and exact file path ("use the `view_file` tool to read ... `references/context-recovery-workflow.md`"), but delegates the actual recovery procedure to the reference rather than embedding executable steps.

4 / 5

Workflow Clarity

The single directive is unambiguous and correctly ordered (read → adhere → before asserting state), and the referenced runbook carries the full validated sequence; the body itself only implies the checkpoints rather than stating them.

4 / 5

Progressive Disclosure

The body is a clean overview pointing to one real one-level-deep reference with a fully-qualified path, but the reference itself contains a nested citation to another audit doc, introducing a minor second-level hop.

4 / 5

Total

17

/

20

Passed

Description

83%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 is strong: it clearly states both the capability and the triggers, uses third person, and avoids fluff. Minor gains are available by adding a couple more natural trigger synonyms and sharpening the distinction from sibling recovery skills.

DimensionReasoningScore

Specificity

Names the domain and several concrete data sources ("Memory Core recency, semantic recall, session rollups, and A2A") but the single verb "reconstructing" covers the action set, leaving minor coverage gaps versus a fully comprehensive action list.

4 / 5

Completeness

Explicitly answers both what ("Post-compaction recovery runbook for reconstructing active lane state...") and when ("Triggers: Use immediately after...") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural domain terms users would say ("context compaction/compression", "summarized session", "reconstructed from a lossy summary") with a synonym pair, though a few common phrasings are absent.

4 / 5

Distinctiveness Conflict Risk

"Post-compaction recovery" carves a clear niche with specific triggers, but it overlaps slightly with sibling recovery skills (e.g. session-sunset, memory-mining) acknowledged in the skill's own out-of-scope guidance.

4 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
neomjs/neo
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.