CtrlK
BlogDocsLog inGet started
Tessl Logo

handoff

Draft a cold-start prompt for a manually operated Claude Code session. Use when the user asks for a handoff, continuation prompt, or something to copy and paste into Claude Code, not when the active agent should ask Claude to review or implement the work.

68

Quality

84%

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

86%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 efficient, well-structured guide for drafting handoff prompts with a clear ground-write-close workflow. Its main improvement opportunity is actionability: a concrete example handoff prompt would make the guidance copy-paste ready.

Suggestions

Add one short, complete example handoff prompt (with the mission, live state, paths, hazards, and done-criteria) so the guidance is copy-paste ready rather than described.

Optional: make the grounding-to-writing handoff explicit with a one-line checkpoint (e.g. 'after grounding, list which commands already passed before drafting') to nudge workflow_clarity toward a feedback loop.

DimensionReasoningScore

Conciseness

The body is lean and opinionated ("This skill is a transport fallback: it never launches Claude and never supervises execution"), with no padding of concepts Claude already knows; every paragraph carries skill-specific guidance that earns its place.

5 / 5

Actionability

Provides an executable git grounding block and concrete specifics ("A small handoff is 12 to 20 dense lines", done-criteria examples), but never shows a complete example handoff prompt, leaving a minor gap for an instruction-only skill.

4 / 5

Workflow Clarity

A clear sequenced workflow (Ground it first -> Write it -> posture -> close with verification) with grounding and done-criteria checkpoints, but lacks an explicit validate/retry feedback loop; the destructive-cap does not apply to this drafting skill.

4 / 5

Progressive Disclosure

Self-contained single-purpose skill with no bundle files needed, organized into well-signaled sections (## Ground it first, ## Write it, ## The posture that makes it work); the only link is an appropriate cross-skill pointer to agent-goal.

5 / 5

Total

18

/

20

Passed

Description

82%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 well-constructed: it states a concrete purpose, gives explicit natural-language triggers, and draws a clear boundary against adjacent skills. Its only soft spot is specificity, since it names a single action rather than enumerating several.

DimensionReasoningScore

Specificity

Names the domain and one concrete action ("Draft a cold-start prompt for a manually operated Claude Code session"), but does not list several specific actions, so it sits at the 1-2 concrete actions anchor rather than the multi-action anchors above.

3 / 5

Completeness

Explicitly answers both what ("Draft a cold-start prompt for a manually operated Claude Code session") and when ("Use when the user asks for a handoff, continuation prompt..."), with concrete trigger phrases plus a negative boundary, matching the top anchor.

5 / 5

Trigger Term Quality

Good natural trigger coverage ("handoff", "continuation prompt", "something to copy and paste into Claude Code") that users would plausibly say, but not an exhaustive set of synonyms, so it is one step below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (cold-start handoff prompt) with distinct triggers and an explicit exclusion ("not when the active agent should ask Claude to review or implement the work"), giving minimal conflict risk.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

14

/

16

Passed

Repository
EpicenterHQ/epicenter
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.