CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sce-handover

Write a session handover document, or load one for continuation

Quality

78%

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 ./.agents/skills/sce-handover/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

93%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 exemplar of a lean, fully actionable instruction-only skill: exact commands, paths, naming schemes, and validation gates with template and layout details correctly delegated to two real one-level-deep reference files. The only notable gap is the absence of a defined recovery loop if the writer's post-write completeness validation fails.

DimensionReasoningScore

Conciseness

The body is uniformly imperative and operational (e.g. "Never overwrite an existing file", "Loading is read-only: do not edit any file") with zero explanation of concepts Claude already knows; it even explicitly avoids duplicating the completeness contract ("satisfy that contract without redefining the required-section set here"). Every token earns its place, matching the 'Lean and efficient' anchor.

5 / 5

Actionability

Guidance is fully concrete: exact commands ("git status, git diff, and git diff --cached"), exact path schemes with worked examples ("context/handovers/{plan_name}-{task_id}.md ... (for example T01)", "$sce-handover context/handovers/2026-08-24-session.md"), explicit reject rules for the loader, and named output layouts. An instruction-only skill, its guidance is copy-paste actionable throughout, matching the top anchor.

5 / 5

Workflow Clarity

Both paths are cleanly sequenced with numbered steps and strong validation gates — input-mode validation, path rejection rules, context-root check before writing, completeness validation "before reporting success", and explicit blocked/stop states. It falls short of 5 because writer step 5 says to validate the written file but defines no recovery action if that validation fails (no fix-and-revalidate loop), a minor validation gap per the 'most checkpoints present' anchor.

4 / 5

Progressive Disclosure

The body keeps the workflow while the persisted schema (references/handover-template.md) and all output layouts (references/output.md) are split into real, clearly signaled, one-level-deep bundle files — both verified to exist. Structure matches 'Clear overview with well-signaled one-level-deep references; content appropriately split'.

5 / 5

Total

19

/

20

Passed

Description

53%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 concise and names a clear niche with two concrete actions, but it lacks any 'when to use' trigger guidance and has thin keyword coverage. It communicates what the skill does yet gives a user or model little help in deciding when to reach for it.

Suggestions

Add an explicit trigger clause, e.g. "Use when ending a session with unfinished work, or when starting a session from a previous handoff or the user mentions a handover/handoff file."

Include natural synonyms users would actually say — "handoff", "session summary", "resume a session", "continue where we left off" — to improve trigger term coverage.

Mention the concrete artifact location (context/handovers/*.md) in the description to sharpen specificity and distinguish the skill from generic summary tools.

DimensionReasoningScore

Specificity

"Write a session handover document, or load one for continuation" names the domain and exactly two concrete actions (write, load), but says nothing about the document's content, location, or structure. This matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'; it falls short of 4 because it does not list several specific actions.

3 / 5

Completeness

The "what" is clear (write or load a session handover document), but there is no "Use when..." or equivalent trigger clause; "for continuation" only weakly implies when to invoke it. The rubric guideline explicitly caps a missing 'Use when...' clause at 3.

3 / 5

Trigger Term Quality

"session handover" and "continuation" are natural terms a user might say, but the description omits common variations and synonyms such as "handoff", "session summary", "resume", or "context transfer". This fits 'Some relevant keywords but missing common variations or synonyms' rather than 4's 'good keyword coverage'.

3 / 5

Distinctiveness Conflict Risk

"Session handover" is a fairly specific niche (persisting/loading session continuity state), mostly distinct with only minor overlap risk against generic note-taking or summarization skills. It does not reach 5 because the short description offers no distinct trigger phrasing to fully disambiguate it from adjacent session-summary skills.

4 / 5

Total

13

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

crocoder-dev/shared-context-engineering

Path

.agents/skills/sce-handover/SKILL.md

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.