skill-resume

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

Quality

67%

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 ./.claude/skills/skill-resume/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete commands, expected outputs, and a clearly sequenced, checkpointed workflow. Its main weaknesses are verbosity from duplicated examples and a monolithic structure that would benefit from splitting detailed material into reference files.

Dimension	Reasoning	Score
Conciseness	The body is operationally focused with no basic-concept padding, but at ~526 lines it carries heavy redundancy — the restoration and failure summaries are duplicated in both the phases and the Examples section, and the Quick Reference and Bottom Line restate the process flow.	2 / 3
Actionability	Concrete executable commands (octo-state.sh read_state, get_context_tier auto) with exact grep/sed snippets, expected output formats, and specific slash-command routing make the guidance copy-paste ready.	3 / 3
Workflow Clarity	Six phases are explicitly sequenced with conditional checkpoints (e.g., Phase 1 'Stop here' when no .octo/ exists) and status-based routing; the read-only nature means the destructive/batch-operation validation cap does not apply.	3 / 3
Progressive Disclosure	Sections are clearly organized, but the skill is monolithic — four full example outputs, best practices, red flags, and integration notes are all inline rather than split into reference files, and no bundle files exist to offload detail.	2 / 3
	Total	10 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 answers both what and when and occupies a recognizable niche, but its vague action phrasing, missing common trigger terms, and second-person voice limit its quality. Specificity is the weakest dimension due to the voice penalty and lack of concrete actions.

Suggestions

Replace the vague 'Pick up where you left off' with concrete actions, e.g. 'Restores prior session state, reloads adaptive context, displays a history-and-blockers summary, and routes to the next workflow step.'

Add natural trigger terms users actually say ('resume', 'continue', 'what was I doing', 'restore session') directly in the description, not only in the body's When-to-Use section.

Rewrite in third person ('Restores...', 'Use when...') to avoid the second-person voice penalty on the specificity score.

Dimension	Reasoning	Score
Specificity	The description uses the vague phrase 'Pick up where you left off from a previous session' without naming concrete restoration actions, and its second-person voice ('you left off', 'use after') triggers the voice penalty, reducing the score from a base of 2.	1 / 3
Completeness	It states both what it does (resume a previous session) and when to use it ('use after context resets, compaction, or new conversations'), providing explicit trigger guidance that satisfies the what-and-when requirement.	3 / 3
Trigger Term Quality	'Pick up where you left off' is a natural user phrase, but common variations users actually say ('resume', 'continue', 'what was I doing', 'restore session') are absent from the description itself.	2 / 3
Distinctiveness Conflict Risk	Session restoration is a recognizable niche, but the triggers 'context resets, compaction, or new conversations' are generic enough to overlap with general context-management skills, and no tooling-specific anchors distinguish it.	2 / 3
	Total	8 / 12 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
skill_md_line_count	SKILL.md is long (526 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: nyldn/claude-octopus
Path: .claude/skills/skill-resume/SKILL.md
Commit: 9f39f0c

Reviewed: 7 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.