CtrlK
BlogDocsLog inGet started
Tessl Logo

handoff

Resume the most recent agent session for the current working directory, leading with any unanswered question. Use when the user says "where were we", "resume", "handoff", "pick up where I left off", or starts a session with no fresh context.

73

Quality

91%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

An exemplary lean skill body: concrete tool calls, a precise matching rule with a WRONG/RIGHT anti-pattern pair, explicit fallbacks, and a self-check checklist. The only trimmable redundancy is the fourfold repetition of the directory-boundary rule and the opening filler sentence.

DimensionReasoningScore

Conciseness

The body is lean — no concept tutorials, tight tool-call examples — but the directory-boundary rule is stated four times ("Why", Workflow step 2, "Anti-patterns", "Checklist") and the opener "The user wants to resume work." is filler. This matches anchor 4 (efficient, minor over-explanation that could be trimmed) rather than anchor 5's every-token-earns-its-place; it is well above anchor 3's noticeable padding.

4 / 5

Actionability

Fully executable guidance: copy-paste tool calls (`memory_sessions { "limit": 20 }`, `memory_recall` with limit 10), an exact match predicate (`session.cwd === projectPath || session.cwd.startsWith(projectPath + sep)`), and a concrete expected-output example. This matches anchor 5 (copy-paste ready, covers common cases); anchor 4 would imply missing key details, which is not the case.

5 / 5

Workflow Clarity

Five clearly sequenced steps with explicit branches ("No match: fall back to the single most recent session overall", "Prefer completed over abandoned"), empty-session handling, question-first ordering, and a closing verification checklist. The read-only task needs no destructive/batch validation cap, and the explicit fallbacks plus checklist satisfy anchor 5 better than anchor 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

A ~60-line, well-sectioned single file (Quick start, Why, Workflow, Anti-patterns, Checklist, See also, Troubleshooting) whose only external pointer is one clearly-signaled, one-level-deep reference ("See ../_shared/TROUBLESHOOTING.md if memory_sessions or memory_recall is not available"). Nothing needs splitting out, so this matches the simple-skill exception and anchor 5; anchor 4 would require organization gaps that are not present.

5 / 5

Total

19

/

20

Passed

Description

91%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.

A strong description: third person, concise, with an explicit 'Use when' clause and excellent natural trigger-phrase coverage including synonyms. The only gap is that it does not distinguish itself from closely related session-recap skills and slightly undersells the full behavior (summarize, next step).

DimensionReasoningScore

Specificity

Quotes concrete actions — "Resume the most recent agent session for the current working directory, leading with any unanswered question" — naming the domain and 2 specific actions. It fits anchor 4 (several specific actions, minor gaps): the summarization/next-step behavior from the body is not reflected, keeping it below comprehensive anchor 5, but it is more concrete than the 1-2-action anchor 3 example.

4 / 5

Completeness

Explicitly answers both: what ("Resume the most recent agent session for the current working directory, leading with any unanswered question") and when ("Use when the user says...") with concrete trigger phrases. This mirrors the anchor-5 example exactly; the explicit 'Use when' clause rules out anchor 4.

5 / 5

Trigger Term Quality

Natural trigger phrases are comprehensive: "where were we", "resume", "handoff", "pick up where I left off", plus the context condition "starts a session with no fresh context". Synonym coverage matches the anchor-5 example pattern; no common variation is obviously missing, so it is above anchor 4.

5 / 5

Distinctiveness Conflict Risk

"resume", "handoff", and "pick up where I left off" define a clear niche, but the skill body's own 'See also' lists closely related siblings (recap, session-history, recall) that the description does not disambiguate from — matching anchor 4 (mostly distinct, minor overlap risk with closely related skills) rather than anchor 5's minimal conflict risk.

4 / 5

Total

18

/

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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
rohitg00/agentmemory
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.