skill-resume

Pick up where you left off from a previous session — use after context resets, compaction, or new conversations

Quality

66%

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 ./skills/skill-resume/SKILL.md

Quality

Content

63%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 thorough, well-structured restoration workflow with concrete commands and clear sequencing, but it is over-long for a SKILL.md, carries significant redundant illustration, and does not split detail into reference files.

Suggestions

Move the four full example-output blocks and the Best Practices/Red Flags/Integration sections into a separate references file (e.g. EXAMPLES.md) and link to it from SKILL.md.

Reconcile the state-reading mechanism: pick one canonical approach (octo-state.sh vs `octopus state-path` vs direct grep/sed) and use it consistently, or explicitly document when each applies.

Trim the Quick Reference and The Bottom Line sections, which restate the When-to-Use triggers and core principle already covered above.

Dimension	Reasoning	Score
Conciseness	The 510-line body is mostly actionable domain content rather than concept explanation, but it is noticeably redundant: four full example-output blocks, plus Best Practices, Red Flags, Quick Reference, and The Bottom Line sections restate earlier material.	3 / 5
Actionability	Concrete copy-paste bash commands, expected output formats, and routing tables are provided throughout, but the state-reading mechanism is inconsistent across sections (octo-state.sh vs `octopus state-path` vs direct grep/sed on STATE.md).	4 / 5
Workflow Clarity	Phases 0–6 are clearly sequenced with explicit checkpoints (e.g. "Stop here - do not proceed to Phase 2", existence checks, compaction-recovery validation), though error-recovery feedback loops are lighter outside the compaction section.	4 / 5
Progressive Disclosure	The skill is a single 510-line monolith with well-organized headers but no reference files; large blocks (examples, best practices, integration) that belong in separate files are inlined, and the one referenced path (skills/blocks/codex-host-adapter.md) is not present in the bundle.	3 / 5
	Total	14 / 20 Passed

Description

70%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 concise, uses an explicit "use after..." trigger clause, and names the domain clearly, but it stays idiomatic rather than describing the concrete technical actions the skill performs.

Suggestions

Add one concrete technical action to the description, e.g. "reads persisted workflow state, reloads adaptive context, and routes you to the right next step".

Include the common synonyms "resume" or "continue" as trigger terms to broaden natural-language matching.

Dimension	Reasoning	Score
Specificity	Names the domain (session restoration) and one concrete action ("Pick up where you left off"), but does not describe the technical mechanism (reading state, loading context, routing), so coverage is not comprehensive.	3 / 5
Completeness	Both "what" (pick up where you left off from a previous session) and "when" ("use after context resets, compaction, or new conversations") are present and explicit, but the "what" could be more specific about the restoration mechanism.	4 / 5
Trigger Term Quality	Good coverage of natural phrases users would say ("pick up where you left off", "previous session", "context resets", "compaction", "new conversations"), though common synonyms like "resume" and "continue" are absent.	4 / 5
Distinctiveness Conflict Risk	The session-restoration niche is clear with distinct triggers, with only minor overlap risk against status-checking skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (511 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: nyldn/claude-octopus
Path: skills/skill-resume/SKILL.md
Commit: 242e51d

Reviewed: 3 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.