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

The body is a tightly written, fully executable two-mode workflow with explicit sequencing, validation gates, blocked-output handling, and clean delegation to two real, well-scoped reference files. Its only weakness is mild redundancy in the execution-contract section, which could be trimmed slightly without losing clarity.

DimensionReasoningScore

Conciseness

The body is directive throughout — exact commands, path patterns, and rejection rules with no concept explanations Claude already knows — matching 'Efficient; minor instances of over-explanation that could be trimmed'. It is not a 5 because the execution-contract section repeats similar prohibitions ("Do not expose raw internal state..." later re-echoed by layout/stop rules in each path) that could be tightened; it is clearly above a 3 with only minor trimming opportunities.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: exact git commands (`git status`, `git diff`, `git diff --cached`), concrete path resolution rules with a worked example (`context/handovers/{plan_name}-{task_id}.md`, `T01`), a timestamped fallback format, explicit loader rejection criteria, and named output layouts. This matches 'concrete code or commands; specific examples cover the common cases' — the top anchor; the only mild spot ("Recent commits") is minor and not enough to drop to 4.

5 / 5

Workflow Clarity

Both paths are clearly sequenced with explicit validation checkpoints: writer step 5 validates the written file against the template's Completeness contract before reporting success, loader steps 1-2 validate the path and completeness, and error recovery is specified (never overwrite; fall back to a timestamped name, or render the blocked layout and stop). This matches the anchor 'Clear sequence with explicit validation steps; feedback loops for error recovery'.

5 / 5

Progressive Disclosure

The SKILL.md is a clear overview that appropriately delegates the persisted schema to `references/handover-template.md` and terminal layouts to `references/output.md` — both real files, clearly signaled, one level deep (the template's mention of output.md stays within the same bundle). Content is appropriately split with easy navigation, matching the top anchor.

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 distinct, specific capability, but it answers only the 'what'. It entirely lacks trigger guidance and natural trigger phrasing, which caps both completeness and trigger-term quality. Adding a 'Use when...' clause with common user phrases would lift most dimensions.

Suggestions

Append an explicit trigger clause, e.g., 'Use when the user asks to hand off, handover, or summarize work for a future session, or to resume/continue work from a previous session.'

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

Optionally name one or two more concrete capabilities (e.g., 'grounds the document in git status, diffs, and the active plan') to raise specificity beyond two generic actions.

DimensionReasoningScore

Specificity

"Write a session handover document, or load one for continuation" names the domain and exactly two concrete actions (write, load), matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because no further specific capabilities are listed (e.g., composing from session/repository facts, validating against a template).

3 / 5

Completeness

The 'what' is clear (write or load a session handover document) but there is no 'when' — no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. It has a clear 'what' with 'when' missing entirely, the exact anchor-3 example.

3 / 5

Trigger Term Quality

Relevant keywords are present ("session handover", "handover document", "continuation") but common variations and synonyms users naturally say are missing — e.g., "handoff", "resume", "pick up where the last session left off". This matches 'Some relevant keywords but missing common variations or synonyms', not the good coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

"Session handover" is a fairly specific niche with minimal overlap risk against typical skills, matching 'Mostly distinct; minor overlap risk'. It is not a 5 because the description gives no explicit trigger phrases, so it is not fully distinguishable from adjacent skills like session summarization; it is clearly above a 3 since the domain is not generic.

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

.claude/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.