CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-resume

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

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-resume/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A highly actionable, clearly sequenced restoration workflow with executable commands, validation via expected-output formats, and intelligent routing. Its main weaknesses are redundancy (the example outputs and quick-reference/bottom-line sections restate earlier material) and a monolithic structure with references to script and reference files that are not part of the bundle.

Suggestions

Collapse the four full Example Outputs into one canonical restoration example plus one-line deltas for the blocked/paused variants, cutting ~70 lines of template duplication.

Move Best Practices, Red Flags, and the phase-specific guidance into a reference file (e.g. references/routing.md) and link to it from SKILL.md, converting the monolithic body into a lean overview.

Delete the Quick Reference table (four of five rows say 'Same as resume') and 'The Bottom Line' section, which restate the core principle already given in the Overview and Phase 6.

DimensionReasoningScore

Conciseness

The phased core is operational and tight, but the ~100-line Example Outputs section largely restates the Phase 5 template with different data, Example 1 duplicates the Phase 1 failure message verbatim, and the Quick Reference and 'The Bottom Line' sections repeat earlier content — noticeably padded in places, though it avoids explaining concepts Claude already knows, fitting the 'mostly efficient but could be tightened' anchor better than the 'several unnecessary explanations' anchor.

3 / 5

Actionability

The body provides copy-paste-ready bash (octopus state-path resolution, ./scripts/octo-state.sh read_state and get_context_tier, grep/sed extraction pipelines), expected output formats for each step, fill-in templates, and concrete status-routing and phase-guidance tables — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Phases 0-6 are explicitly sequenced with per-step expected output formats serving as validation, hard stop conditions ('Stop here - do not proceed to Phase 2'), fallback handling when state or the handoff file is missing, and a status-based routing table with recovery guidance — matching the clear-sequence-with-explicit-validation anchor; no destructive or batch operations apply a cap.

5 / 5

Progressive Disclosure

The single file is well-sectioned and navigable, but it is monolithic: the four full example outputs, best-practices, and red-flag sections are inline content that could sit in a reference file, and the body references './scripts/octo-state.sh' and 'skills/blocks/codex-host-adapter.md' which are not present in the bundle — matching 'some structure; content that should be separate is inline' rather than the well-split anchor 4 or the minimal-structure anchor 2.

3 / 5

Total

16

/

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 has an explicit use-when clause with natural trigger phrases and a clear niche, but the what-side is thin — it states a purpose rather than concrete actions. Adding one or two specific capabilities (restore workflow state, reload context, show history and blockers) would lift it into the top anchors.

Suggestions

Replace the purpose-only opening with 1-2 concrete actions, e.g. 'Restore previous session state, reload workflow context, and show where you left off' instead of the vague 'Pick up where you left off'.

Add the highest-frequency user triggers — 'resume', 'continue', 'restore session' — to the use-when clause, since the skill body already lists them.

DimensionReasoningScore

Specificity

The description names the session-restoration domain with one implied action ("Pick up where you left off from a previous session") but lists no concrete operations such as restoring state, reloading context, or displaying a summary, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor.

3 / 5

Completeness

Both a what ("Pick up where you left off from a previous session") and an explicit when ("use after context resets, compaction, or new conversations") are present; the when is explicit but the what is thin and lacks concrete capability statements, fitting 'both present; when could be more explicit/specific' rather than the fully concrete anchor 5 and clearly above the missing-when anchor 3.

4 / 5

Trigger Term Quality

It includes natural phrases users would say ("pick up where you left off", "context resets", "compaction", "new conversations") with good coverage, but omits the most common triggers "resume", "continue", and "restore session" that the body itself lists, so it falls short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The session-restoration niche with triggers like 'context resets' and 'compaction' is mostly distinct with minimal conflict risk, though generic phrasing like 'pick up where you left off' could mildly overlap with general continue/continue-working skills, placing it just below the clear-niche anchor.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (521 lines); consider splitting into references/ and linking

Warning

Total

15

/

16

Passed

Repository
nyldn/claude-octopus
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.