CtrlK
BlogDocsLog inGet started
Tessl Logo

ce-handoff

Create a session handoff for another agent, or resume, find, and read any user-selected continuity source. Use when work or conversation must continue without access to the current session history.

65

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/ce-handoff/SKILL.md

The canonical home for this skill is ce-handoff in EveryInc/compound-engineering-plugin

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-structured, action-oriented overview with excellent progressive disclosure into two real one-level-deep reference files and explicit validation/stop gates on both create and resume paths. Its main weakness is conciseness: legalistic, repetitive phrasing could be tightened without losing any of the routing or safety content.

Suggestions

Trim or merge the repeated non-negotiable phrasing — e.g., state once that both reference reads are mandatory instead of 'That read is not optional' twice, and consolidate the two 'MUST stop' statements in Resume into a single gate.

Tighten the opening policy paragraph ('Creation and resume are deliberately open at their edges...') to one or two clauses; the open-edges principle is restated throughout the Create and Resume sections anyway.

Replace abstract directives like 'keep the handoff pointer-first' with a one-line concrete rule or a pointer to the exact section of references/create.md that defines it, so the body carries only the routing.

DimensionReasoningScore

Conciseness

The body is dense, policy-flavored prose with tighten-able passages: 'Creation and resume are deliberately open at their edges', 'That read is not optional' repeated for both reference files, and overlapping stop/confirmation statements in Resume ('MUST stop and ask the user' and 'MUST stop without acting until the user confirms'). Mostly efficient but with unnecessary explanation and redundancy, fitting anchor 3 rather than 4, and nowhere near the concept-explaining padding of 1-2.

3 / 5

Actionability

For an instruction-only skill the guidance is largely concrete: mandatory pre-reads of named files, 'redact secrets, credentials, and unrelated personal information', a specific default resume command ('/ce-handoff resume <source>') with an explicit rendering rule, and a fenced copyable command. Falls short of 5 only because some directives stay abstract at this level ('keep the handoff pointer-first', the body contract lives entirely in references/create.md); exceeds 3 because the steps given are directly executable, not pseudocode.

4 / 5

Workflow Clarity

The invocation is routed explicitly (bare/create/resume), and each path has validation checkpoints: 'Creation is complete only after confirming the destination contains the handoff', discovery containment checks before reading candidates, sufficiency assessment of the source, and hard 'MUST stop' gates for resume. Anchor 4 ('clear sequence with most checkpoints present') fits: the create-side step detail is delegated to references/create.md, and the sequence is staged via prose rather than an explicit numbered flow, so it does not reach the feedback-loop-rich 5.

4 / 5

Progressive Disclosure

The body is a ~55-line overview with clear sections that routes to two real, one-level-deep reference files, each strongly signaled ('Read `references/create.md` before writing anything. That read is not optional.'; same for resume.md). Both files exist and contain no nested further references, matching the 'clear overview with well-signaled one-level-deep references' anchor exactly.

5 / 5

Total

16

/

20

Passed

Description

87%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 cleanly answers both what the skill does and when to use it, with a distinct trigger niche around session handoff and continuity. Keyword coverage is solid though it misses a few natural synonyms, and 'continuity source' leaves one action slightly abstract.

DimensionReasoningScore

Specificity

Names the domain (session handoff/continuity) and several concrete actions — 'Create a session handoff for another agent', 'resume, find, and read any user-selected continuity source' — with minor gaps in coverage (e.g., no mention of what the handoff contains). Fits the 'lists several specific actions; minor gaps' anchor, not 5 since 'continuity source' keeps one action slightly abstract, and not 3 since more than 1-2 concrete actions are given.

4 / 5

Completeness

Explicitly answers both: what — 'Create a session handoff... or resume, find, and read any user-selected continuity source' — and when — 'Use when work or conversation must continue without access to the current session history', a concrete trigger phrase. Clearly matches the 5 anchor; not 4 because the 'when' clause is explicit and specific rather than improvable-vague.

5 / 5

Trigger Term Quality

Contains natural terms users would say — 'handoff', 'resume', 'continue' — plus explicit trigger framing ('Use when work or conversation must continue'). A few common variations are missing (e.g., 'pick up where we left off', 'context transfer'), which fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive synonym/extension coverage of 5.

4 / 5

Distinctiveness Conflict Risk

'Session handoff for another agent' plus 'without access to the current session history' carves a clear niche with distinct triggers and minimal overlap with generic session-continuation skills. Matches the 'clear niche with distinct triggers' anchor; not 4 because no closely related skill would plausibly fire on this phrasing.

5 / 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
crdant/compound-engineering-plugin
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.